Merge pull request #175 from epi052/174-add-similar-page-filter

add fuzzy page filter

.github/dependabot.yml

@@ -0,0 +1,7 @@
+version: 2
+updates:
+- package-ecosystem: cargo
+  directory: "/"
+  schedule:
+    interval: daily
+  open-pull-requests-limit: 10

.github/pull_request_template.md

@@ -4,7 +4,7 @@ Long form explanations of most of the items below can be found in the [CONTRIBUT
 
 ## Branching checklist
 - [ ] There is an issue associated with your PR (bug, feature, etc.. if not, create one)
-- [ ] Your PR description references the associated issue (i.e. fixes #123)
+- [ ] Your PR description references the associated issue (i.e. fixes #123456)
 - [ ] Code is in its own branch
 - [ ] Branch name is related to the PR contents
 - [ ] PR targets master

.github/stale.yml

@@ -0,0 +1,17 @@
+# Number of days of inactivity before an issue becomes stale
+daysUntilStale: 14
+# Number of days of inactivity before a stale issue is closed
+daysUntilClose: 7
+# Issues with these labels will never be considered stale
+exemptLabels:
+  - pinned
+  - security
+# Label to use when marking an issue as stale
+staleLabel: stale
+# Comment to post when marking an issue as stale. Set to `false` to disable
+markComment: >
+  This issue has been automatically marked as stale because it has not had
+  recent activity. It will be closed if no further activity occurs. Thank you
+  for your contributions.
+# Comment to post when closing a stale issue. Set to `false` to disable
+closeComment: false

.github/workflows/check.yml

@@ -61,4 +61,4 @@ jobs:
       - uses: actions-rs/cargo@v1
         with:
           command: clippy
-          args: --all-targets --all-features -- -D warnings -A clippy::unnecessary_unwrap -A clippy::deref_addrof
+          args: --all-targets --all-features -- -D warnings -A clippy::deref_addrof

.gitignore

@@ -22,3 +22,6 @@ img/**
 # scripts to check code coverage using nightly compiler
 check-coverage.sh
 lcov_cobertura.py
+
+# dockerignore file that makes it so i can work on the docker config without copying a 4GB manifest or w/e it is
+.dockerignore

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "feroxbuster"
-version = "1.6.3"
+version = "1.11.0"
 authors = ["Ben 'epi' Risher <epibar052@gmail.com>"]
 license = "MIT"
 edition = "2018"
@@ -10,10 +10,16 @@ description = "A fast, simple, recursive content discovery tool."
 categories = ["command-line-utilities"]
 keywords = ["pentest", "enumeration", "url-bruteforce", "content-discovery", "web"]
 exclude = [".github/*", "img/*", "check-coverage.sh"]
+build = "build.rs"
 
 [badges]
 maintenance = { status = "actively-developed" }
 
+[build-dependencies]
+clap = "2.33"
+regex = "1"
+lazy_static = "1.4"
+
 [dependencies]
 futures = { version = "0.3"}
 tokio = { version = "0.2", features = ["full"] }
@@ -21,23 +27,25 @@ tokio-util = {version = "0.3", features = ["codec"]}
 log = "0.4"
 env_logger = "0.8"
 reqwest = { version = "0.10", features = ["socks"] }
-clap = "2"
+clap = "2.33"
 lazy_static = "1.4"
 toml = "0.5"
 serde = { version = "1.0", features = ["derive"] }
 serde_json = "1.0"
 uuid = { version = "0.8", features = ["v4"] }
 indicatif = "0.15"
-console = "0.12"
+console = "0.13"
 openssl = { version = "0.10", features = ["vendored"] }
 dirs = "3.0"
 regex = "1"
 crossterm = "0.18"
 rlimit = "0.5"
+ctrlc = "3.1"
+fuzzyhash = "0.2"
 
 [dev-dependencies]
 tempfile = "3.1"
-httpmock = "0.4.5"
+httpmock = "0.5.2"
 assert_cmd = "1.0.1"
 predicates = "1.0.5"
 

Dockerfile

@@ -1,8 +1,10 @@
 FROM alpine:latest
 LABEL maintainer="wfnintr@null.net"
 
+RUN sed -i -e 's/v[[:digit:]]\..*\//edge\//g' /etc/apk/repositories && apk upgrade --update-cache --available
+
 # download default wordlists 
-RUN apk add --no-cache --virtual .depends subversion && \
+RUN apk add --no-cache --virtual .depends subversion font-noto-emoji && \
 	svn export https://github.com/danielmiessler/SecLists/trunk/Discovery/Web-Content /usr/share/seclists/Discovery/Web-Content && \
 	apk del .depends
 

README.md

@@ -22,7 +22,7 @@
   <a href="https://crates.io/crates/feroxbuster">
     <img src="https://img.shields.io/crates/v/feroxbuster?color=blue&label=version&logo=rust">
   </a>
- 
+
   <a href="https://crates.io/crates/feroxbuster">
     <img src="https://img.shields.io/crates/d/feroxbuster?label=downloads&logo=rust&color=inactive">
   </a>
@@ -45,20 +45,26 @@
 
 ## 😕 What the heck is a ferox anyway?
 
-Ferox is short for Ferric Oxide. Ferric Oxide, simply put, is rust.  The name rustbuster was taken, so I decided on a variation.  🤷	
+Ferox is short for Ferric Oxide. Ferric Oxide, simply put, is rust. The name rustbuster was taken, so I decided on a
+variation. 🤷
 
-## 🤔 What's it do tho? 
+## 🤔 What's it do tho?
 
-`feroxbuster` is a tool designed to perform [Forced Browsing](https://owasp.org/www-community/attacks/Forced_browsing).  
+`feroxbuster` is a tool designed to perform [Forced Browsing](https://owasp.org/www-community/attacks/Forced_browsing).
 
-Forced browsing is an attack where the aim is to enumerate and access resources that are not referenced by the web application, but are still accessible by an attacker.
+Forced browsing is an attack where the aim is to enumerate and access resources that are not referenced by the web
+application, but are still accessible by an attacker.
 
-`feroxbuster` uses brute force combined with a wordlist to search for unlinked content in target directories. These resources may store sensitive information about web applications and operational systems, such as source code, credentials, internal network addressing, etc...
+`feroxbuster` uses brute force combined with a wordlist to search for unlinked content in target directories. These
+resources may store sensitive information about web applications and operational systems, such as source code,
+credentials, internal network addressing, etc...
 
-This attack is also known as Predictable Resource Location, File Enumeration, Directory Enumeration, and Resource Enumeration.
+This attack is also known as Predictable Resource Location, File Enumeration, Directory Enumeration, and Resource
+Enumeration.
 
 📖 Table of Contents
 -----------------
+
 - [Installation](#-installation)
     - [Download a Release](#download-a-release)
     - [Snap Install](#snap-install)
@@ -73,30 +79,41 @@ This attack is also known as Predictable Resource Location, File Enumeration, Di
     - [ferox-config.toml](#ferox-configtoml)
     - [Command Line Parsing](#command-line-parsing)
 - [Example Usage](#-example-usage)
-    - [Pause and Resume Scans (new in `v1.4.0`)](#pause-and-resume-scans-new-in-v140)
     - [Multiple Values](#multiple-values)
-    - [Extract Links from Response Body (new in `v1.1.0`)](#extract-links-from-response-body-new-in-v110)
     - [Include Headers](#include-headers)
     - [IPv6, Non-recursive scan with INFO logging enabled](#ipv6-non-recursive-scan-with-info-level-logging-enabled)
     - [Read urls from STDIN; pipe only resulting urls out to another tool](#read-urls-from-stdin-pipe-only-resulting-urls-out-to-another-tool)
     - [Proxy traffic through Burp](#proxy-traffic-through-burp)
-    - [Proxy traffic through a SOCKS proxy](#proxy-traffic-through-a-socks-proxy)
+    - [Proxy traffic through a SOCKS proxy (including DNS lookups)](#proxy-traffic-through-a-socks-proxy-including-dns-lookups)
     - [Pass auth token via query parameter](#pass-auth-token-via-query-parameter)
+    - [Extract Links from Response Body (new in `v1.1.0`)](#extract-links-from-response-body-new-in-v110)
     - [Limit Total Number of Concurrent Scans (new in `v1.2.0`)](#limit-total-number-of-concurrent-scans-new-in-v120)
     - [Filter Response by Status Code  (new in `v1.3.0`)](#filter-response-by-status-code--new-in-v130)
+    - [Pause an Active Scan (new in `v1.4.0`)](#pause-an-active-scan-new-in-v140)
     - [Replay Responses to a Proxy based on Status Code (new in `v1.5.0`)](#replay-responses-to-a-proxy-based-on-status-code-new-in-v150)
+    - [Filter Response by Word Count & Line Count  (new in `v1.6.0`)](#filter-response-by-word-count--line-count--new-in-v160)
+    - [Filter Response Using a Regular Expression (new in `v1.8.0`)](#filter-response-using-a-regular-expression-new-in-v180)
+    - [Stop and Resume Scans (save scan's state to disk) (new in `v1.9.0`)](#stop-and-resume-scans---resume-from-file-new-in-v190)
+    - [Enforce a Time Limit on Your Scan (new in `v1.10.0`)](#enforce-a-time-limit-on-your-scan-new-in-v1100)
+    - [Extract Links from robots.txt (New in `v1.10.2`)](#extract-links-from-robotstxt-new-in-v1102)
+    - [Filter Response by Similarity to A Given Page (fuzzy filter) (new in `v1.11.0`)](#filter-response-by-similarity-to-a-given-page-fuzzy-filter-new-in-v1110)
 - [Comparison w/ Similar Tools](#-comparison-w-similar-tools)
 - [Common Problems/Issues (FAQ)](#-common-problemsissues-faq)
     - [No file descriptors available](#no-file-descriptors-available)
     - [Progress bars print one line at a time](#progress-bars-print-one-line-at-a-time)
+    - [What do each of the numbers beside the URL mean?](#what-do-each-of-the-numbers-beside-the-url-mean)
+    - [Connection closed before message completed](#connection-closed-before-message-completed)
+    - [SSL Error routines:tls_process_server_certificate:certificate verify failed](#ssl-error-routinestls_process_server_certificatecertificate-verify-failed)
 
 ## 💿 Installation
 
 ### Download a Release
 
-Releases for multiple architectures can be found in the [Releases](https://github.com/epi052/feroxbuster/releases) section.  The latest release for each of the following systems can be downloaded and executed as shown below.
+Releases for multiple architectures can be found in the [Releases](https://github.com/epi052/feroxbuster/releases)
+section. The latest release for each of the following systems can be downloaded and executed as shown below.
 
 #### Linux (32 and 64-bit) & MacOS
+
 ```
 curl -sL https://raw.githubusercontent.com/epi052/feroxbuster/master/install-nix.sh | bash
 ```
@@ -125,7 +142,7 @@ Install using `snap`
 sudo snap install feroxbuster
 ```
 
-The only gotcha here is that the snap package can only read wordlists from a few specific locations. There are a few 
+The only gotcha here is that the snap package can only read wordlists from a few specific locations. There are a few
 possible solutions, of which two are shown below.
 
 If the wordlist is on the same partition as your home directory, it can be hard-linked into `~/snap/feroxbuster/common`
@@ -135,7 +152,7 @@ ln /path/to/the/wordlist ~/snap/feroxbuster/common
 ./feroxbuster -u http://localhost -w ~/snap/feroxbuster/common/wordlist
 ``` 
 
-If the wordlist is on a separate partition, hard-linking won't work.  You'll need to copy it into the snap directory.
+If the wordlist is on a separate partition, hard-linking won't work. You'll need to copy it into the snap directory.
 
 ```
 cp /path/to/the/wordlist ~/snap/feroxbuster/common
@@ -170,7 +187,8 @@ cargo install feroxbuster
 
 ### apt Install
 
-Download `feroxbuster_amd64.deb` from the [Releases](https://github.com/epi052/feroxbuster/releases) section.  After that, use your favorite package manager to install the `.deb`.
+Download `feroxbuster_amd64.deb` from the [Releases](https://github.com/epi052/feroxbuster/releases) section. After
+that, use your favorite package manager to install the `.deb`.
 
 ```
 wget -sLO https://github.com/epi052/feroxbuster/releases/latest/download/feroxbuster_amd64.deb.zip
@@ -219,7 +237,9 @@ cat targets.txt | sudo docker run --net=host --init -i feroxbuster --stdin -x js
 
 #### Mount a volume to pass in `ferox-config.toml`
 
-You've got some options available if you want to pass in a config file.  [`ferox-buster.toml`](#ferox-configtoml) can live in multiple locations and still be valid, so it's up to you how you'd like to pass it in.  Below are a few valid examples:
+You've got some options available if you want to pass in a config file.  [`ferox-buster.toml`](#ferox-configtoml) can
+live in multiple locations and still be valid, so it's up to you how you'd like to pass it in. Below are a few valid
+examples:
 
 ```
 sudo docker run --init -v $(pwd)/ferox-config.toml:/etc/feroxbuster/ferox-config.toml -it feroxbuster -u http://example.com
@@ -242,7 +262,9 @@ alias feroxbuster="sudo docker run --init -v ~/.config/feroxbuster:/root/.config
 ```
 
 ## ⚙️ Configuration
+
 ### Default Values
+
 Configuration begins with with the following built-in default values baked into the binary:
 
 - timeout: `7` seconds
@@ -256,14 +278,24 @@ Configuration begins with with the following built-in default values baked into
 - recursion depth: `4`
 - auto-filter wildcards - `true`
 - output: `stdout`
+- save_state: `true` (create a state file in cwd when `Ctrl+C` is received)
 
 ### Threads and Connection Limits At A High-Level
 
-This section explains how the `-t` and `-L` options work together to determine the overall aggressiveness of a scan. The combination of the two values set by these options determines how hard your target will get hit and to some extent also determines how many resources will be consumed on your local machine.
+This section explains how the `-t` and `-L` options work together to determine the overall aggressiveness of a scan. The
+combination of the two values set by these options determines how hard your target will get hit and to some extent also
+determines how many resources will be consumed on your local machine.
 
 #### A Note on Green Threads
 
-`feroxbuster` uses so-called [green threads](https://en.wikipedia.org/wiki/Green_threads) as opposed to traditional kernel/OS threads. This means (at a high-level) that the threads are implemented entirely in userspace, within a single running process. As a result, a scan with 30 green threads will appear to the OS to be a single process with no additional light-weight processes associated with it as far as the kernel is concerned. As such, there will not be any impact to process (`nproc`) limits when specifying larger values for `-t`. However, these threads will still consume file descriptors, so you will need to ensure that you have a suitable `nlimit` set when scaling up the amount of threads. More detailed documentation on setting appropriate `nlimit` values can be found in the [No File Descriptors Available](#no-file-descriptors-available) section of the FAQ
+`feroxbuster` uses so-called [green threads](https://en.wikipedia.org/wiki/Green_threads) as opposed to traditional
+kernel/OS threads. This means (at a high-level) that the threads are implemented entirely in userspace, within a single
+running process. As a result, a scan with 30 green threads will appear to the OS to be a single process with no
+additional light-weight processes associated with it as far as the kernel is concerned. As such, there will not be any
+impact to process (`nproc`) limits when specifying larger values for `-t`. However, these threads will still consume
+file descriptors, so you will need to ensure that you have a suitable `nlimit` set when scaling up the amount of
+threads. More detailed documentation on setting appropriate `nlimit` values can be found in
+the [No File Descriptors Available](#no-file-descriptors-available) section of the FAQ
 
 #### Threads and Connection Limits: The Implementation
 
@@ -272,13 +304,18 @@ This section explains how the `-t` and `-L` options work together to determine t
 
 #### Threads and Connection Limits: Examples
 
-To truly have only 30 active requests to a site at any given time, `-t 30 -L 1` is necessary. Using `-t 30 -L 2` will result in a maximum of 60 total requests being processed at any given time for that site. And so on. For a conversation on this, please see [Issue #126](https://github.com/epi052/feroxbuster/issues/126) which may provide more (or less) clarity :wink:
+To truly have only 30 active requests to a site at any given time, `-t 30 -L 1` is necessary. Using `-t 30 -L 2` will
+result in a maximum of 60 total requests being processed at any given time for that site. And so on. For a conversation
+on this, please see [Issue #126](https://github.com/epi052/feroxbuster/issues/126) which may provide more (or less)
+clarity :wink:
 
 ### ferox-config.toml
+
 After setting built-in default values, any values defined in a `ferox-config.toml` config file will override the
-built-in defaults.  
+built-in defaults.
 
 `feroxbuster` searches for `ferox-config.toml` in the following locations (in the order shown):
+
 - `/etc/feroxbuster/` (global)
 - `CONFIG_DIR/ferxobuster/` (per-user)
 - The same directory as the `feroxbuster` executable (per-user)
@@ -289,14 +326,15 @@ built-in defaults.
 > - MacOs: `$HOME/Library/Application Support` i.e. `/Users/bob/Library/Application Support`
 > - Windows: `{FOLDERID_RoamingAppData}` i.e. `C:\Users\Bob\AppData\Roaming`
 
-If more than one valid configuration file is found, each one overwrites the values found previously.  
+If more than one valid configuration file is found, each one overwrites the values found previously.
 
 If no configuration file is found, nothing happens at this stage.
 
-As an example, let's say that we prefer to use a different wordlist as our default when scanning; we can
-set the `wordlist` value in the config file to override the baked-in default.
+As an example, let's say that we prefer to use a different wordlist as our default when scanning; we can set
+the `wordlist` value in the config file to override the baked-in default.
 
 Notes of interest:
+
 - it's ok to only specify values you want to change without specifying anything else
 - variable names in `ferox-config.toml` must match their command-line counterpart
 
@@ -307,6 +345,7 @@ wordlist = "/wordlists/jhaddix/all.txt"
 ```
 
 A pre-made configuration file with examples of all available settings can be found in `ferox-config.toml.example`.
+
 ```toml
 # ferox-config.toml
 # Example configuration for feroxbuster
@@ -321,15 +360,17 @@ A pre-made configuration file with examples of all available settings can be fou
 # wordlist = "/wordlists/jhaddix/all.txt"
 # status_codes = [200, 500]
 # filter_status = [301]
-# replay_codes = [301]
 # threads = 1
 # timeout = 5
 # proxy = "http://127.0.0.1:8080"
 # replay_proxy = "http://127.0.0.1:8081"
+# replay_codes = [200, 302]
 # verbosity = 1
 # scan_limit = 6
 # quiet = true
+# json = true
 # output = "/targets/ellingson_mineral_company/gibson.txt"
+# debug_log = "/var/log/find-the-derp.log"
 # user_agent = "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:47.0) Gecko/20100101 Firefox/47.0"
 # redirects = true
 # insecure = true
@@ -341,9 +382,13 @@ A pre-made configuration file with examples of all available settings can be fou
 # extract_links = true
 # depth = 1
 # filter_size = [5174]
+# filter_regex = ["^ignore me$"]
+# filter_similar = ["https://somesite.com/soft404"]
 # filter_word_count = [993]
 # filter_line_count = [35, 36]
 # queries = [["name","value"], ["rick", "astley"]]
+# save_state = false
+# time_limit = 10m
 
 # headers can be specified on multiple lines or as an inline table
 #
@@ -360,7 +405,9 @@ A pre-made configuration file with examples of all available settings can be fou
 ```
 
 ### Command Line Parsing
-Finally, after parsing the available config file, any options/arguments given on the commandline will override any values that were set as a built-in or config-file value.
+
+Finally, after parsing the available config file, any options/arguments given on the commandline will override any
+values that were set as a built-in or config-file value.
 
 ```
 USAGE:
@@ -373,32 +420,40 @@ FLAGS:
                            findings (default: false)
     -h, --help             Prints help information
     -k, --insecure         Disables TLS certificate validation
+        --json             Emit JSON logs to --output and --debug-log instead of normal text
     -n, --no-recursion     Do not scan recursively
     -q, --quiet            Only print URLs; Don't print status codes, response size, running config, etc...
     -r, --redirects        Follow redirects
         --stdin            Read url(s) from STDIN
     -V, --version          Prints version information
-    -v, --verbosity        Increase verbosity level (use -vv or more for greater effect)
+    -v, --verbosity        Increase verbosity level (use -vv or more for greater effect. [CAUTION] 4 -v's is probably
+                           too much)
 
 OPTIONS:
+        --debug-log <FILE>                  Output file to write log entries (use w/ --json for JSON entries)
     -d, --depth <RECURSION_DEPTH>           Maximum recursion depth, a depth of 0 is infinite recursion (default: 4)
     -x, --extensions <FILE_EXTENSION>...    File extension(s) to search for (ex: -x php -x pdf js)
     -N, --filter-lines <LINES>...           Filter out messages of a particular line count (ex: -N 20 -N 31,30)
+    -X, --filter-regex <REGEX>...           Filter out messages via regular expression matching on the response's body
+                                            (ex: -X '^ignore me$')
     -S, --filter-size <SIZE>...             Filter out messages of a particular size (ex: -S 5120 -S 4927,1970)
     -C, --filter-status <STATUS_CODE>...    Filter out status codes (deny list) (ex: -C 200 -C 401)
     -W, --filter-words <WORDS>...           Filter out messages of a particular word count (ex: -W 312 -W 91,82)
     -H, --headers <HEADER>...               Specify HTTP headers (ex: -H Header:val 'stuff: things')
-    -o, --output <FILE>                     Output file to write results to (default: stdout)
-    -p, --proxy <PROXY>                     Proxy to use for requests (ex: http(s)://host:port, socks5://host:port)
+    -o, --output <FILE>                     Output file to write results to (use w/ --json for JSON entries)
+    -p, --proxy <PROXY>                     Proxy to use for requests (ex: http(s)://host:port, socks5(h)://host:port)
     -Q, --query <QUERY>...                  Specify URL query parameters (ex: -Q token=stuff -Q secret=key)
-    -R, --replay-codes <REPLAY_CODE>...     Status Codes to send through a Replay Proxy when found (default: --status
-                                            -codes value)
+    -R, --replay-codes <REPLAY_CODE>...     Status Codes to send through a Replay Proxy when found (default: --status-
+                                            codes value)
     -P, --replay-proxy <REPLAY_PROXY>       Send only unfiltered requests through a Replay Proxy, instead of all
                                             requests
+        --resume-from <STATE_FILE>          State file from which to resume a partially complete scan (ex. --resume-from
+                                            ferox-1606586780.state)
     -L, --scan-limit <SCAN_LIMIT>           Limit total number of concurrent scans (default: 0, i.e. no limit)
     -s, --status-codes <STATUS_CODE>...     Status Codes to include (allow list) (default: 200 204 301 302 307 308 401
                                             403 405)
     -t, --threads <THREADS>                 Number of concurrent threads (default: 50)
+        --time-limit <TIME_SPEC>            Limit total run time of all scans (ex: --time-limit 10m)
     -T, --timeout <SECONDS>                 Number of seconds before a request times out (default: 7)
     -u, --url <URL>...                      The target URL(s) (required, unless --stdin used)
     -a, --user-agent <USER_AGENT>           Sets the User-Agent (default: feroxbuster/VERSION)
@@ -407,15 +462,9 @@ OPTIONS:
 
 ## 🧰 Example Usage
 
-### Pause and Resume Scans (new in `v1.4.0`)
-
-Scans can be paused and resumed by pressing the ENTER key (shown below)
-
-![pause-resume-demo](img/pause-resume-demo.gif)
-
 ### Multiple Values
 
-Options that take multiple values are very flexible.  Consider the following ways of specifying extensions:
+Options that take multiple values are very flexible. Consider the following ways of specifying extensions:
 
 ```
 ./feroxbuster -u http://127.1 -x pdf -x js,html -x php txt json,docx
@@ -423,7 +472,8 @@ Options that take multiple values are very flexible.  Consider the following way
 
 The command above adds .pdf, .js, .html, .php, .txt, .json, and .docx to each url
 
-All of the methods above (multiple flags, space separated, comma separated, etc...) are valid and interchangeable.  The same goes for urls, headers, status codes, queries, and size filters.
+All of the methods above (multiple flags, space separated, comma separated, etc...) are valid and interchangeable. The
+same goes for urls, headers, status codes, queries, and size filters.
 
 ### Include Headers
 
@@ -431,37 +481,6 @@ All of the methods above (multiple flags, space separated, comma separated, etc.
 ./feroxbuster -u http://127.1 -H Accept:application/json "Authorization: Bearer {token}"
 ```
 
-### Extract Links from Response Body (New in `v1.1.0`) 
-
-Search through the body of valid responses (html, javascript, etc...) for additional endpoints to scan. This turns
-`feroxbuster` into a hybrid that looks for both linked and unlinked content. 
-
-Example request/response with `--extract-links` enabled:
-- Make request to `http://example.com/index.html`
-- Receive, and read in, the `body` of the response
-- Search the `body` for absolute and relative links (i.e. `homepage/assets/img/icons/handshake.svg`)
-- Add the following directories for recursive scanning:
-    - `http://example.com/homepage`
-    - `http://example.com/homepage/assets`
-    - `http://example.com/homepage/assets/img`
-    - `http://example.com/homepage/assets/img/icons`
-- Make a single request to `http://example.com/homepage/assets/img/icons/handshake.svg`
-
-```
-./feroxbuster -u http://127.1 --extract-links
-```
-
-Here's a comparison of a wordlist-only scan vs `--extract-links` using [Feline](https://www.hackthebox.eu/home/machines/profile/274) from Hack the Box:
-
-Wordlist only
-
-![normal-scan-cmp-extract](img/normal-scan-cmp-extract.gif)
-
-With `--extract-links`
-
-![extract-scan-cmp-normal](img/extract-scan-cmp-normal.gif)
-
-
 ### IPv6, non-recursive scan with INFO-level logging enabled
 
 ```
@@ -480,22 +499,54 @@ cat targets | ./feroxbuster --stdin --quiet -s 200 301 302 --redirects -x js | f
 ./feroxbuster -u http://127.1 --insecure --proxy http://127.0.0.1:8080
 ```
 
-### Proxy traffic through a SOCKS proxy
+### Proxy traffic through a SOCKS proxy (including DNS lookups)
 
 ```
-./feroxbuster -u http://127.1 --proxy socks5://127.0.0.1:9050
+./feroxbuster -u http://127.1 --proxy socks5h://127.0.0.1:9050
 ```
 
-### Pass auth token via query parameter 
+### Pass auth token via query parameter
 
 ```
 ./feroxbuster -u http://127.1 --query token=0123456789ABCDEF
 ```
 
+### Extract Links from Response Body (New in `v1.1.0`)
+
+Search through the body of valid responses (html, javascript, etc...) for additional endpoints to scan. This turns
+`feroxbuster` into a hybrid that looks for both linked and unlinked content.
+
+Example request/response with `--extract-links` enabled:
+
+- Make request to `http://example.com/index.html`
+- Receive, and read in, the `body` of the response
+- Search the `body` for absolute and relative links (i.e. `homepage/assets/img/icons/handshake.svg`)
+- Add the following directories for recursive scanning:
+    - `http://example.com/homepage`
+    - `http://example.com/homepage/assets`
+    - `http://example.com/homepage/assets/img`
+    - `http://example.com/homepage/assets/img/icons`
+- Make a single request to `http://example.com/homepage/assets/img/icons/handshake.svg`
+
+```
+./feroxbuster -u http://127.1 --extract-links
+```
+
+Here's a comparison of a wordlist-only scan vs `--extract-links`
+using [Feline](https://www.hackthebox.eu/home/machines/profile/274) from Hack the Box:
+
+Wordlist only
+
+![normal-scan-cmp-extract](img/normal-scan-cmp-extract.gif)
+
+With `--extract-links`
+
+![extract-scan-cmp-normal](img/extract-scan-cmp-normal.gif)
+
 ### Limit Total Number of Concurrent Scans (new in `v1.2.0`)
 
-Limit the number of scans permitted to run at any given time.  Recursion will still identify new directories, but newly
-discovered directories can only begin scanning when the total number of active scans drops below the value passed to 
+Limit the number of scans permitted to run at any given time. Recursion will still identify new directories, but newly
+discovered directories can only begin scanning when the total number of active scans drops below the value passed to
 `--scan-limit`.
 
 ```
@@ -506,70 +557,240 @@ discovered directories can only begin scanning when the total number of active s
 
 ### Filter Response by Status Code  (new in `v1.3.0`)
 
-Version 1.3.0 included an overhaul to the filtering system which will allow for a wide array of filters to be added 
-with minimal effort. The first such filter is a Status Code Filter. As responses come back from the scanned server,
-each one is checked against a list of known filters and either displayed or not according to which filters are set.
+Version 1.3.0 included an overhaul to the filtering system which will allow for a wide array of filters to be added with
+minimal effort. The first such filter is a Status Code Filter. As responses come back from the scanned server, each one
+is checked against a list of known filters and either displayed or not according to which filters are set.
 
 ```
 ./feroxbuster -u http://127.1 --filter-status 301
 ```
 
+### Pause an Active Scan (new in `v1.4.0`)
+
+Scans can be paused and resumed by pressing the ENTER key (shown below)
+
+![pause-resume-demo](img/pause-resume-demo.gif)
+
 ### Replay Responses to a Proxy based on Status Code (new in `v1.5.0`)
 
-The `--replay-proxy` and `--replay-codes` options were added as a way to only send a select few responses to a proxy.  This is in stark contrast to `--proxy` which proxies EVERY request.  
+The `--replay-proxy` and `--replay-codes` options were added as a way to only send a select few responses to a proxy.
+This is in stark contrast to `--proxy` which proxies EVERY request.
 
-Imagine you only care about proxying responses that have either the status code `200` or `302` (or you just don't want to clutter up your Burp history).  These two options will allow you to fine-tune what gets proxied and what doesn't.  
+Imagine you only care about proxying responses that have either the status code `200` or `302` (or you just don't want
+to clutter up your Burp history). These two options will allow you to fine-tune what gets proxied and what doesn't.
 
 ```
 ./feroxbuster -u http://127.1 --replay-proxy http://localhost:8080 --replay-codes 200 302 --insecure
 ```
 
-Of note: this means that for every response that matches your replay criteria, you'll end up sending the request that generated that response a second time.  Depending on the target and your engagement terms (if any), it may not make sense from a traffic generated perspective.
+Of note: this means that for every response that matches your replay criteria, you'll end up sending the request that
+generated that response a second time. Depending on the target and your engagement terms (if any), it may not make sense
+from a traffic generated perspective.
 
 ![replay-proxy-demo](img/replay-proxy-demo.gif)
 
+### Filter Response by Word Count & Line Count  (new in `v1.6.0`)
+
+In addition to filtering on the size of a response, version 1.6.0 added the ability to filter out responses based on the
+number of lines and/or words contained within the response body. This change drove a change to the information displayed
+to the user as well. This section will detail the new information and how to make use of it with the new filters
+provided.
+
+Example output:
+
+```
+200        10l        212w       38437c https://example-site.com/index.html
+```
+
+There are five columns of output above:
+
+- column 1: status code - can be filtered with `-C|--filter-status`
+- column 2: number of lines - can be filtered with `-N|--filter-lines`
+- column 3: number of words - can be filtered with `-W|--filter-words`
+- column 4: number of bytes (overall size) - can be filtered with `-S|--filter-size`
+- column 5: url to discovered resource
+
+### Filter Response Using a Regular Expression (new in `v1.8.0`)
+
+Version 1.3.0 included an overhaul to the filtering system which will allow for a wide array of filters to be added with
+minimal effort. The latest addition is a Regular Expression Filter. As responses come back from the scanned server,
+the **body** of the response is checked against the filter's regular expression. If the expression is found in the body,
+then that response is filtered out.
+
+**NOTE: Using regular expressions to filter large responses or many regular expressions may negatively impact
+performance.**
+
+```
+./feroxbuster -u http://127.1 --filter-regex '[aA]ccess [dD]enied.?' --output results.txt --json
+```
+
+### Stop and Resume Scans (`--resume-from FILE`) (new in `v1.9.0`)
+
+Version 1.9.0 adds a few features that allow for completely stopping a scan, and resuming that same scan from a file on
+disk.
+
+A simple `Ctrl+C` during a scan will create a file that contains information about the scan that was cancelled.
+
+![save-state](img/save-state.png)
+
+```json
+// example snippet of state file
+
+{
+  "scans": [
+    {
+      "id": "057016a14769414aac9a7a62707598cb",
+      "url": "https://localhost.com",
+      "scan_type": "Directory",
+      "complete": true
+    },
+    {
+      "id": "400b2323a16f43468a04ffcbbeba34c6",
+      "url": "https://localhost.com/css",
+      "scan_type": "Directory",
+      "complete": false
+    }
+  ],
+  "config": {
+    "wordlist": "/wordlists/seclists/Discovery/Web-Content/common.txt",
+    "...": "..."
+  },
+  "responses": [
+    {
+      "type": "response",
+      "url": "https://localhost.com/Login",
+      "path": "/Login",
+      "wildcard": false,
+      "status": 302,
+      "content_length": 0,
+      "line_count": 0,
+      "word_count": 0,
+      "headers": {
+        "content-length": "0",
+        "server": "nginx/1.16.1"
+      }
+    }
+  ]
+},
+```
+
+Based on the example image above, the same scan can be resumed by
+using `feroxbuster --resume-from ferox-http_localhost-1606947491.state`. Directories that were already complete are not
+rescanned, however partially complete scans are started from the beginning.
+
+![resumed-scan](img/resumed-scan.gif)
+
+In order to prevent state file creation when `Ctrl+C` is pressed, you can simply add the entry below to
+your `ferox-config.toml`.
+
+```toml
+# ferox-config.toml
+
+save_state = false
+```
+
+### Enforce a Time Limit on Your Scan (new in `v1.10.0`)
+
+Version 1.10.0 adds the ability to set a maximum runtime, or time limit, on your scan. The usage is pretty simple: a
+number followed directly by a single character representing seconds, minutes, hours, or days.  `feroxbuster` refers to
+this combination as a time_spec.
+
+Examples of possible time_specs:
+
+- `30s` - 30 seconds
+- `20m` - 20 minutes
+- `1h`  - 1 hour
+- `1d`  - 1 day (why??)
+
+A valid time_spec can be passed to `--time-limit` in order to force a shutdown after the given time has elapsed.
+
+![time-limit](img/time-limit.gif)
+
+### Extract Links from robots.txt (New in `v1.10.2`)
+
+In addition to [extracting links from the response body](#extract-links-from-response-body-new-in-v110), using
+`--extract-links` makes a request to `/robots.txt` and examines all `Allow` and `Disallow` entries. Directory entries
+are added to the scan queue, while file entries are requested and then reported if appropriate.
+
+### Filter Response by Similarity to A Given Page (fuzzy filter) (new in `v1.11.0`)
+
+Version 1.11.0 adds the ability to specify an example page for filtering pages that are similar to the given example.
+
+For example, consider a site that attempts to redirect new users to a `/register` endpoint. The `/register` page has a
+CSRF token that alters the page's response slightly with each new request (sometimes affecting overall length). This
+means that a simple line/word/char filter won't be able to filter all responses. In order to filter those redirects out,
+one could use a command like this:
+
+```
+./feroxbuster -u https://somesite.xyz --filter-similar-to https://somesite.xyz/register
+```
+
+`--filter-similar-to` requests the page passed to it via CLI (`https://somesite.xyz/register`), after which it hashes 
+the response body using the [SSDeep algorithm](https://ssdeep-project.github.io/ssdeep/index.html).  All subsequent 
+pages are hashed and compared to the original request's hash. If the comparison of the two hashes meets a certain 
+percentage of similarity (currently 95%), then that request will be filtered out.
+
+SSDeep was selected as it does a good job of identifying near-duplicate pages once content-length reaches a certain 
+size, while remaining performant.  Other algorithms were tested but resulted in huge performance hits (orders of 
+magnitude slower on requests/second).
+
+**NOTE**
+- SSDeep/`--filter-similar-to` does not do well at detecting similarity of very small responses
+  - The lack of accuracy with very small responses is considered a fair trade-off for not negatively impacting performance
+- Using a bunch of `--filter-similar-to` values **may** negatively impact performance
+
 ## 🧐 Comparison w/ Similar Tools
 
-There are quite a few similar tools for forced browsing/content discovery.  Burp Suite Pro, Dirb, Dirbuster, etc... 
-However, in my opinion, there are two that set the standard: [gobuster](https://github.com/OJ/gobuster) and 
-[ffuf](https://github.com/ffuf/ffuf).  Both are mature, feature-rich, and all-around incredible tools to use.
+There are quite a few similar tools for forced browsing/content discovery. Burp Suite Pro, Dirb, Dirbuster, etc...
+However, in my opinion, there are two that set the standard: [gobuster](https://github.com/OJ/gobuster) and
+[ffuf](https://github.com/ffuf/ffuf). Both are mature, feature-rich, and all-around incredible tools to use.
 
-So, why would you ever want to use feroxbuster over ffuf/gobuster?  In most cases, you probably won't.  ffuf in particular
-can do the vast majority of things that feroxbuster can, while still offering boatloads more functionality.  Here are
-a few of the use-cases in which feroxbuster may be a better fit:
+So, why would you ever want to use feroxbuster over ffuf/gobuster? In most cases, you probably won't. ffuf in particular
+can do the vast majority of things that feroxbuster can, while still offering boatloads more functionality. Here are a
+few of the use-cases in which feroxbuster may be a better fit:
 
 - You want a **simple** tool usage experience
 - You want to be able to run your content discovery as part of some crazy 12 command unix **pipeline extravaganza**
 - You want to scan through a **SOCKS** proxy
 - You want **auto-filtering** of Wildcard responses by default
-- You want an integrated **link extractor** to increase discovered endpoints
+- You want an integrated **link extractor/robots.txt parser** to increase discovered endpoints
 - You want **recursion** along with some other thing mentioned above (ffuf also does recursion)
 - You want a **configuration file** option for overriding built-in default values for your scans
 
-|                                                                  | feroxbuster | gobuster | ffuf |
-|------------------------------------------------------------------|---|---|---|
-| fast                                                             | ✔ | ✔ | ✔ |
-| easy to use                                                      | ✔ | ✔ |   |
-| filter out responses by status code (new in `v1.3.0`)            | ✔ | ✔ | ✔ |
-| allows recursion                                                 | ✔ |   | ✔ |
-| can specify query parameters                                     | ✔ |   | ✔ |
-| SOCKS proxy support                                              | ✔ |   |   |
-| extracts links from response body to increase scan coverage      | ✔ |   |   |
-| multiple target scan (via stdin or multiple -u)                  | ✔ |   | ✔ |
-| configuration file for default value override                    | ✔ |   | ✔ |
-| can accept urls via STDIN as part of a pipeline                  | ✔ |   | ✔ |
-| can accept wordlists via STDIN                                   |   | ✔ | ✔ |
-| filter based on response size, wordcount, and linecount          | ✔ |   | ✔ |
-| auto-filter wildcard responses                                   | ✔ |   | ✔ |
-| performs other scans (vhost, dns, etc)                           |   | ✔ | ✔ |
-| time delay / rate limiting                                       |   | ✔ | ✔ |
-| **huge** number of other options                                 |   |   | ✔ |
+|                                                          | feroxbuster | gobuster | ffuf |
+|------------------------------------------------------------------------------|---|---|---|
+| fast                                                                         | ✔ | ✔ | ✔ |
+| easy to use                                                                  | ✔ | ✔ |   |
+| allows recursion                                                             | ✔ |   | ✔ |
+| can specify query parameters                                                 | ✔ |   | ✔ |
+| SOCKS proxy support                                                          | ✔ |   |   |
+| multiple target scan (via stdin or multiple -u)                              | ✔ |   | ✔ |
+| configuration file for default value override                                | ✔ |   | ✔ |
+| can accept urls via STDIN as part of a pipeline                              | ✔ |   | ✔ |
+| can accept wordlists via STDIN                                               |   | ✔ | ✔ |
+| filter based on response size, wordcount, and linecount                      | ✔ |   | ✔ |
+| auto-filter wildcard responses                                               | ✔ |   | ✔ |
+| performs other scans (vhost, dns, etc)                                       |   | ✔ | ✔ |
+| time delay / rate limiting                                                   |   | ✔ | ✔ |
+| extracts links from response body to increase scan coverage (`v1.1.0`)       | ✔ |   |   |
+| limit number of concurrent recursive scans (`v1.2.0`)                        | ✔ |   |   |
+| filter out responses by status code (`v1.3.0`)                               | ✔ | ✔ | ✔ |
+| interactive pause and resume of active scan (`v1.4.0`)                       | ✔ |   |   |
+| replay only matched requests to a proxy (`v1.5.0`)                           | ✔ |   | ✔ |
+| filter out responses by line & word count (`v1.6.0`)                         | ✔ |   | ✔ |
+| json output (ffuf supports other formats as well) (`v1.7.0`)                 | ✔ |   | ✔ |
+| filter out responses by regular expression (`v1.8.0`)                        | ✔ |   | ✔ |
+| save scan's state to disk (can pick up where it left off) (`v1.9.0`)         | ✔ |   |   |
+| maximum run time limit (`v1.10.0`)                                           | ✔ |   | ✔ |
+| use robots.txt to increase scan coverage (`v1.10.2`)                         | ✔ |   |   |
+| use example page's response to fuzzily filter similar pages  (`v1.11.0`)     | ✔ |   |   |
+| **huge** number of other options                                             |   |   | ✔ |
 
-Of note, there's another written-in-rust content discovery tool, [rustbuster](https://github.com/phra/rustbuster). I 
-came across rustbuster when I was naming my tool (😢). I don't have any experience using it, but it appears to 
-be able to do POST requests with an HTTP body, has SOCKS support, and has an 8.3 shortname scanner (in addition to vhost
-dns, directory, etc...).  In short, it definitely looks interesting and may be what you're looking for as it has some 
-capability I haven't seen in similar tools.  
+Of note, there's another written-in-rust content discovery tool, [rustbuster](https://github.com/phra/rustbuster). I
+came across rustbuster when I was naming my tool (😢). I don't have any experience using it, but it appears to be able
+to do POST requests with an HTTP body, has SOCKS support, and has an 8.3 shortname scanner (in addition to vhost dns,
+directory, etc...). In short, it definitely looks interesting and may be what you're looking for as it has some
+capability I haven't seen in similar tools.
 
 ## 🤯 Common Problems/Issues (FAQ)
 
@@ -579,21 +800,24 @@ Why do I get a bunch of `No file descriptors available (os error 24)` errors?
 
 ---
 
-There are a few potential causes of this error.  The simplest is that your operating system sets an open file limit that is aggressively low.  Through personal testing, I've found that `4096` is a reasonable open file limit (this will vary based on your exact setup).
+There are a few potential causes of this error. The simplest is that your operating system sets an open file limit that
+is aggressively low. Through personal testing, I've found that `4096` is a reasonable open file limit (this will vary
+based on your exact setup).
 
-There are quite a few options to solve this particular problem, of which a handful are shown below.  
+There are quite a few options to solve this particular problem, of which a handful are shown below.
 
 #### Increase the Number of Open Files
 
-We'll start by increasing the number of open files the OS allows. On my Kali install, the default was `1024`, and I know some MacOS installs use `256` 😕.
+We'll start by increasing the number of open files the OS allows. On my Kali install, the default was `1024`, and I know
+some MacOS installs use `256` 😕.
 
 ##### Edit `/etc/security/limits.conf`
 
-One option to up the limit is to edit `/etc/security/limits.conf` so that it includes the two lines below.  
+One option to up the limit is to edit `/etc/security/limits.conf` so that it includes the two lines below.
 
 - `*` represents all users
-- `hard` and `soft` indicate the hard and soft limits for the OS 
-- `nofile` is the number of open files option. 
+- `hard` and `soft` indicate the hard and soft limits for the OS
+- `nofile` is the number of open files option.
 
 ```
 /etc/security/limits.conf
@@ -614,20 +838,25 @@ ulimit -n 4096
 
 #### Additional Tweaks (may not be needed)
 
-If you still find yourself hitting the file limit with the above changes, there are a few additional tweaks that may help.  
+If you still find yourself hitting the file limit with the above changes, there are a few additional tweaks that may
+help.
 
-> This section was shamelessly stolen from this [stackoverflow answer](https://stackoverflow.com/a/3923785).  More information is included in that post and is recommended reading if you end up needing to use this section.
+> This section was shamelessly stolen from this [stackoverflow answer](https://stackoverflow.com/a/3923785). More information is included in that post and is recommended reading if you end up needing to use this section.
 
-✨ Special thanks to HTB user [@sparkla](https://www.hackthebox.eu/home/users/profile/221599) for their help with identifying these additional tweaks ✨
+✨ Special thanks to HTB user [@sparkla](https://www.hackthebox.eu/home/users/profile/221599) for their help with
+identifying these additional tweaks ✨
 
 ##### Increase the ephemeral port range, and decrease the tcp_fin_timeout.
 
-The ephermal port range defines the maximum number of outbound sockets a host can create from a particular I.P. address. The fin_timeout defines the minimum time these sockets will stay in TIME_WAIT state (unusable after being used once). Usual system defaults are
+The ephermal port range defines the maximum number of outbound sockets a host can create from a particular I.P. address.
+The fin_timeout defines the minimum time these sockets will stay in TIME_WAIT state (unusable after being used once).
+Usual system defaults are
 
 - `net.ipv4.ip_local_port_range = 32768   61000`
 - `net.ipv4.tcp_fin_timeout = 60`
 
-This basically means your system cannot consistently guarantee more than `(61000 - 32768) / 60 = 470` sockets per second.
+This basically means your system cannot consistently guarantee more than `(61000 - 32768) / 60 = 470` sockets per
+second.
 
 ```
 sudo sysctl net.ipv4.ip_local_port_range="15000 61000"
@@ -636,7 +865,9 @@ sudo sysctl net.ipv4.tcp_fin_timeout=30
 
 ##### Allow socket reuse while in a `TIME_WAIT` status
 
-This allows fast cycling of sockets in time_wait state and re-using them. Make sure to read post [Coping with the TCP TIME-WAIT](https://vincent.bernat.ch/en/blog/2014-tcp-time-wait-state-linux) from Vincent Bernat to understand the implications.
+This allows fast cycling of sockets in time_wait state and re-using them. Make sure to read
+post [Coping with the TCP TIME-WAIT](https://vincent.bernat.ch/en/blog/2014-tcp-time-wait-state-linux) from Vincent
+Bernat to understand the implications.
 
 ```
 sudo sysctl net.ipv4.tcp_tw_reuse=1 
@@ -644,9 +875,47 @@ sudo sysctl net.ipv4.tcp_tw_reuse=1
 
 ### Progress bars print one line at a time
 
-`feroxbuster` needs a terminal width of at least the size of what's being printed in order to do progress bar printing correctly.  If your width is too small, you may see output like what's shown below.
+`feroxbuster` needs a terminal width of at least the size of what's being printed in order to do progress bar printing
+correctly. If your width is too small, you may see output like what's shown below.
 
 ![small-term](img/small-term.png)
 
-If you can, simply make the terminal wider and rerun.  If you're unable to make your terminal wider
-consider using `-q` to suppress the progress bars.
+If you can, simply make the terminal wider and rerun. If you're unable to make your terminal wider consider using `-q`
+to suppress the progress bars.
+
+### What do each of the numbers beside the URL mean?
+
+Please refer to [this section](#filter-response-by-word-count--line-count--new-in-v160) where each number's meaning and
+how to use it to filter responses is discussed.
+
+### Connection closed before message completed
+
+The error in question can be boiled down to 'networking stuff'. `feroxbuster`
+uses [reqwest](https://docs.rs/reqwest/latest/) which uses [hyper](https://docs.rs/hyper/latest/hyper/) to make requests
+to the server. [This issue report](https://github.com/hyperium/hyper/issues/2136#issuecomment-589345238) to the hyper
+project explains what is happening (quoted below to save you a click). This isn't a bug so much as it's a
+target-specific tuning issue. When lowering the `-t` value, the error doesn't occur (or happens much less frequently).
+
+This isn't a bug. Simply slow down the scan. A `-t` value of 50 was chosen as a sane default that's still quite fast out
+of the box. However, network related errors may occur when the client and/or server become over-saturated.
+The [Threads and Connection Limits At A High-Level](#threads-and-connection-limits-at-a-high-level) section details how
+to accomplish per-target tuning.
+
+> This is just due to the racy nature of networking.
+>
+> hyper has a connection pool of idle connections, and it selected one to send your request. Most of the time, hyper will receive the server's FIN and drop the dead connection from its pool. But occasionally, a connection will be selected from the pool and written to at the same time the server is deciding to close the connection. Since hyper already wrote some of the request, it can't really retry it automatically on a new connection, since the server may have acted already.
+
+### SSL Error routines:tls_process_server_certificate:certificate verify failed
+
+In the event you see an error similar to
+
+![self-signed](img/insecure.png)
+
+```
+error trying to connect: error:1416F086:SSL routines:tls_process_server_certificate:certificate verify failed:ssl/statem/statem_clnt.c:1913: (self signed certificate)
+```
+
+You just need to add the `-k|--insecure` flag to your command.
+
+`feroxbuster` rejects self-signed certs and other "insecure" certificates/site configurations by default. You can choose
+to scan these services anyway by telling `feroxbuster` to ignore insecure server certs.

build.rs

@@ -0,0 +1,23 @@
+extern crate clap;
+
+use clap::Shell;
+
+include!("src/parser.rs");
+
+fn main() {
+    println!("cargo:rerun-if-env-changed=src/parser.rs");
+
+    if std::env::var("DOCS_RS").is_ok() {
+        return; // only build when we're not generating docs
+    }
+
+    let outdir = "shell_completions";
+
+    let mut app = initialize();
+
+    let shells: [Shell; 4] = [Shell::Bash, Shell::Fish, Shell::Zsh, Shell::PowerShell];
+
+    for shell in &shells {
+        app.gen_completions("feroxbuster", *shell, outdir);
+    }
+}

ferox-config.toml.example

@@ -18,7 +18,9 @@
 # verbosity = 1
 # scan_limit = 6
 # quiet = true
+# json = true
 # output = "/targets/ellingson_mineral_company/gibson.txt"
+# debug_log = "/var/log/find-the-derp.log"
 # user_agent = "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:47.0) Gecko/20100101 Firefox/47.0"
 # redirects = true
 # insecure = true
@@ -30,9 +32,13 @@
 # extract_links = true
 # depth = 1
 # filter_size = [5174]
+# filter_regex = ["^ignore me$"]
+# filter_similar = ["https://somesite.com/soft404"]
 # filter_word_count = [993]
 # filter_line_count = [35, 36]
 # queries = [["name","value"], ["rick", "astley"]]
+# save_state = false
+# time_limit = "10m"
 
 # headers can be specified on multiple lines or as an inline table
 #

shell_completions/_feroxbuster

@@ -0,0 +1,96 @@
+#compdef feroxbuster
+
+autoload -U is-at-least
+
+_feroxbuster() {
+    typeset -A opt_args
+    typeset -a _arguments_options
+    local ret=1
+
+    if is-at-least 5.2; then
+        _arguments_options=(-s -S -C)
+    else
+        _arguments_options=(-s -C)
+    fi
+
+    local context curcontext="$curcontext" state line
+    _arguments "${_arguments_options[@]}" \
+'-w+[Path to the wordlist]' \
+'--wordlist=[Path to the wordlist]' \
+'*-u+[The target URL(s) (required, unless --stdin used)]' \
+'*--url=[The target URL(s) (required, unless --stdin used)]' \
+'-t+[Number of concurrent threads (default: 50)]' \
+'--threads=[Number of concurrent threads (default: 50)]' \
+'-d+[Maximum recursion depth, a depth of 0 is infinite recursion (default: 4)]' \
+'--depth=[Maximum recursion depth, a depth of 0 is infinite recursion (default: 4)]' \
+'-T+[Number of seconds before a request times out (default: 7)]' \
+'--timeout=[Number of seconds before a request times out (default: 7)]' \
+'-p+[Proxy to use for requests (ex: http(s)://host:port, socks5(h)://host:port)]' \
+'--proxy=[Proxy to use for requests (ex: http(s)://host:port, socks5(h)://host:port)]' \
+'-P+[Send only unfiltered requests through a Replay Proxy, instead of all requests]' \
+'--replay-proxy=[Send only unfiltered requests through a Replay Proxy, instead of all requests]' \
+'*-R+[Status Codes to send through a Replay Proxy when found (default: --status-codes value)]' \
+'*--replay-codes=[Status Codes to send through a Replay Proxy when found (default: --status-codes value)]' \
+'*-s+[Status Codes to include (allow list) (default: 200 204 301 302 307 308 401 403 405)]' \
+'*--status-codes=[Status Codes to include (allow list) (default: 200 204 301 302 307 308 401 403 405)]' \
+'-o+[Output file to write results to (use w/ --json for JSON entries)]' \
+'--output=[Output file to write results to (use w/ --json for JSON entries)]' \
+'(-u --url)--resume-from=[State file from which to resume a partially complete scan (ex. --resume-from ferox-1606586780.state)]' \
+'--debug-log=[Output file to write log entries (use w/ --json for JSON entries)]' \
+'-a+[Sets the User-Agent (default: feroxbuster/VERSION)]' \
+'--user-agent=[Sets the User-Agent (default: feroxbuster/VERSION)]' \
+'*-x+[File extension(s) to search for (ex: -x php -x pdf js)]' \
+'*--extensions=[File extension(s) to search for (ex: -x php -x pdf js)]' \
+'*-H+[Specify HTTP headers (ex: -H Header:val '\''stuff: things'\'')]' \
+'*--headers=[Specify HTTP headers (ex: -H Header:val '\''stuff: things'\'')]' \
+'*-Q+[Specify URL query parameters (ex: -Q token=stuff -Q secret=key)]' \
+'*--query=[Specify URL query parameters (ex: -Q token=stuff -Q secret=key)]' \
+'*-S+[Filter out messages of a particular size (ex: -S 5120 -S 4927,1970)]' \
+'*--filter-size=[Filter out messages of a particular size (ex: -S 5120 -S 4927,1970)]' \
+'*-X+[Filter out messages via regular expression matching on the response'\''s body (ex: -X '\''^ignore me$'\'')]' \
+'*--filter-regex=[Filter out messages via regular expression matching on the response'\''s body (ex: -X '\''^ignore me$'\'')]' \
+'*-W+[Filter out messages of a particular word count (ex: -W 312 -W 91,82)]' \
+'*--filter-words=[Filter out messages of a particular word count (ex: -W 312 -W 91,82)]' \
+'*-N+[Filter out messages of a particular line count (ex: -N 20 -N 31,30)]' \
+'*--filter-lines=[Filter out messages of a particular line count (ex: -N 20 -N 31,30)]' \
+'*-C+[Filter out status codes (deny list) (ex: -C 200 -C 401)]' \
+'*--filter-status=[Filter out status codes (deny list) (ex: -C 200 -C 401)]' \
+'*--filter-similar-to=[Filter out pages that are similar to the given page (ex. --filter-similar-to http://site.xyz/soft404)]' \
+'-L+[Limit total number of concurrent scans (default: 0, i.e. no limit)]' \
+'--scan-limit=[Limit total number of concurrent scans (default: 0, i.e. no limit)]' \
+'--time-limit=[Limit total run time of all scans (ex: --time-limit 10m)]' \
+'*-v[Increase verbosity level (use -vv or more for greater effect. \[CAUTION\] 4 -v'\''s is probably too much)]' \
+'*--verbosity[Increase verbosity level (use -vv or more for greater effect. \[CAUTION\] 4 -v'\''s is probably too much)]' \
+'-q[Only print URLs; Don'\''t print status codes, response size, running config, etc...]' \
+'--quiet[Only print URLs; Don'\''t print status codes, response size, running config, etc...]' \
+'--json[Emit JSON logs to --output and --debug-log instead of normal text]' \
+'-D[Don'\''t auto-filter wildcard responses]' \
+'--dont-filter[Don'\''t auto-filter wildcard responses]' \
+'-r[Follow redirects]' \
+'--redirects[Follow redirects]' \
+'-k[Disables TLS certificate validation]' \
+'--insecure[Disables TLS certificate validation]' \
+'-n[Do not scan recursively]' \
+'--no-recursion[Do not scan recursively]' \
+'(-x --extensions)-f[Append / to each request]' \
+'(-x --extensions)--add-slash[Append / to each request]' \
+'(-u --url)--stdin[Read url(s) from STDIN]' \
+'-e[Extract links from response body (html, javascript, etc...); make new requests based on findings (default: false)]' \
+'--extract-links[Extract links from response body (html, javascript, etc...); make new requests based on findings (default: false)]' \
+'-h[Prints help information]' \
+'--help[Prints help information]' \
+'-V[Prints version information]' \
+'--version[Prints version information]' \
+&& ret=0
+    
+}
+
+(( $+functions[_feroxbuster_commands] )) ||
+_feroxbuster_commands() {
+    local commands; commands=(
+        
+    )
+    _describe -t commands 'feroxbuster commands' commands "$@"
+}
+
+_feroxbuster "$@"

shell_completions/_feroxbuster.ps1

@@ -0,0 +1,95 @@
+
+using namespace System.Management.Automation
+using namespace System.Management.Automation.Language
+
+Register-ArgumentCompleter -Native -CommandName 'feroxbuster' -ScriptBlock {
+    param($wordToComplete, $commandAst, $cursorPosition)
+
+    $commandElements = $commandAst.CommandElements
+    $command = @(
+        'feroxbuster'
+        for ($i = 1; $i -lt $commandElements.Count; $i++) {
+            $element = $commandElements[$i]
+            if ($element -isnot [StringConstantExpressionAst] -or
+                $element.StringConstantType -ne [StringConstantType]::BareWord -or
+                $element.Value.StartsWith('-')) {
+                break
+        }
+        $element.Value
+    }) -join ';'
+
+    $completions = @(switch ($command) {
+        'feroxbuster' {
+            [CompletionResult]::new('-w', 'w', [CompletionResultType]::ParameterName, 'Path to the wordlist')
+            [CompletionResult]::new('--wordlist', 'wordlist', [CompletionResultType]::ParameterName, 'Path to the wordlist')
+            [CompletionResult]::new('-u', 'u', [CompletionResultType]::ParameterName, 'The target URL(s) (required, unless --stdin used)')
+            [CompletionResult]::new('--url', 'url', [CompletionResultType]::ParameterName, 'The target URL(s) (required, unless --stdin used)')
+            [CompletionResult]::new('-t', 't', [CompletionResultType]::ParameterName, 'Number of concurrent threads (default: 50)')
+            [CompletionResult]::new('--threads', 'threads', [CompletionResultType]::ParameterName, 'Number of concurrent threads (default: 50)')
+            [CompletionResult]::new('-d', 'd', [CompletionResultType]::ParameterName, 'Maximum recursion depth, a depth of 0 is infinite recursion (default: 4)')
+            [CompletionResult]::new('--depth', 'depth', [CompletionResultType]::ParameterName, 'Maximum recursion depth, a depth of 0 is infinite recursion (default: 4)')
+            [CompletionResult]::new('-T', 'T', [CompletionResultType]::ParameterName, 'Number of seconds before a request times out (default: 7)')
+            [CompletionResult]::new('--timeout', 'timeout', [CompletionResultType]::ParameterName, 'Number of seconds before a request times out (default: 7)')
+            [CompletionResult]::new('-p', 'p', [CompletionResultType]::ParameterName, 'Proxy to use for requests (ex: http(s)://host:port, socks5(h)://host:port)')
+            [CompletionResult]::new('--proxy', 'proxy', [CompletionResultType]::ParameterName, 'Proxy to use for requests (ex: http(s)://host:port, socks5(h)://host:port)')
+            [CompletionResult]::new('-P', 'P', [CompletionResultType]::ParameterName, 'Send only unfiltered requests through a Replay Proxy, instead of all requests')
+            [CompletionResult]::new('--replay-proxy', 'replay-proxy', [CompletionResultType]::ParameterName, 'Send only unfiltered requests through a Replay Proxy, instead of all requests')
+            [CompletionResult]::new('-R', 'R', [CompletionResultType]::ParameterName, 'Status Codes to send through a Replay Proxy when found (default: --status-codes value)')
+            [CompletionResult]::new('--replay-codes', 'replay-codes', [CompletionResultType]::ParameterName, 'Status Codes to send through a Replay Proxy when found (default: --status-codes value)')
+            [CompletionResult]::new('-s', 's', [CompletionResultType]::ParameterName, 'Status Codes to include (allow list) (default: 200 204 301 302 307 308 401 403 405)')
+            [CompletionResult]::new('--status-codes', 'status-codes', [CompletionResultType]::ParameterName, 'Status Codes to include (allow list) (default: 200 204 301 302 307 308 401 403 405)')
+            [CompletionResult]::new('-o', 'o', [CompletionResultType]::ParameterName, 'Output file to write results to (use w/ --json for JSON entries)')
+            [CompletionResult]::new('--output', 'output', [CompletionResultType]::ParameterName, 'Output file to write results to (use w/ --json for JSON entries)')
+            [CompletionResult]::new('--resume-from', 'resume-from', [CompletionResultType]::ParameterName, 'State file from which to resume a partially complete scan (ex. --resume-from ferox-1606586780.state)')
+            [CompletionResult]::new('--debug-log', 'debug-log', [CompletionResultType]::ParameterName, 'Output file to write log entries (use w/ --json for JSON entries)')
+            [CompletionResult]::new('-a', 'a', [CompletionResultType]::ParameterName, 'Sets the User-Agent (default: feroxbuster/VERSION)')
+            [CompletionResult]::new('--user-agent', 'user-agent', [CompletionResultType]::ParameterName, 'Sets the User-Agent (default: feroxbuster/VERSION)')
+            [CompletionResult]::new('-x', 'x', [CompletionResultType]::ParameterName, 'File extension(s) to search for (ex: -x php -x pdf js)')
+            [CompletionResult]::new('--extensions', 'extensions', [CompletionResultType]::ParameterName, 'File extension(s) to search for (ex: -x php -x pdf js)')
+            [CompletionResult]::new('-H', 'H', [CompletionResultType]::ParameterName, 'Specify HTTP headers (ex: -H Header:val ''stuff: things'')')
+            [CompletionResult]::new('--headers', 'headers', [CompletionResultType]::ParameterName, 'Specify HTTP headers (ex: -H Header:val ''stuff: things'')')
+            [CompletionResult]::new('-Q', 'Q', [CompletionResultType]::ParameterName, 'Specify URL query parameters (ex: -Q token=stuff -Q secret=key)')
+            [CompletionResult]::new('--query', 'query', [CompletionResultType]::ParameterName, 'Specify URL query parameters (ex: -Q token=stuff -Q secret=key)')
+            [CompletionResult]::new('-S', 'S', [CompletionResultType]::ParameterName, 'Filter out messages of a particular size (ex: -S 5120 -S 4927,1970)')
+            [CompletionResult]::new('--filter-size', 'filter-size', [CompletionResultType]::ParameterName, 'Filter out messages of a particular size (ex: -S 5120 -S 4927,1970)')
+            [CompletionResult]::new('-X', 'X', [CompletionResultType]::ParameterName, 'Filter out messages via regular expression matching on the response''s body (ex: -X ''^ignore me$'')')
+            [CompletionResult]::new('--filter-regex', 'filter-regex', [CompletionResultType]::ParameterName, 'Filter out messages via regular expression matching on the response''s body (ex: -X ''^ignore me$'')')
+            [CompletionResult]::new('-W', 'W', [CompletionResultType]::ParameterName, 'Filter out messages of a particular word count (ex: -W 312 -W 91,82)')
+            [CompletionResult]::new('--filter-words', 'filter-words', [CompletionResultType]::ParameterName, 'Filter out messages of a particular word count (ex: -W 312 -W 91,82)')
+            [CompletionResult]::new('-N', 'N', [CompletionResultType]::ParameterName, 'Filter out messages of a particular line count (ex: -N 20 -N 31,30)')
+            [CompletionResult]::new('--filter-lines', 'filter-lines', [CompletionResultType]::ParameterName, 'Filter out messages of a particular line count (ex: -N 20 -N 31,30)')
+            [CompletionResult]::new('-C', 'C', [CompletionResultType]::ParameterName, 'Filter out status codes (deny list) (ex: -C 200 -C 401)')
+            [CompletionResult]::new('--filter-status', 'filter-status', [CompletionResultType]::ParameterName, 'Filter out status codes (deny list) (ex: -C 200 -C 401)')
+            [CompletionResult]::new('--filter-similar-to', 'filter-similar-to', [CompletionResultType]::ParameterName, 'Filter out pages that are similar to the given page (ex. --filter-similar-to http://site.xyz/soft404)')
+            [CompletionResult]::new('-L', 'L', [CompletionResultType]::ParameterName, 'Limit total number of concurrent scans (default: 0, i.e. no limit)')
+            [CompletionResult]::new('--scan-limit', 'scan-limit', [CompletionResultType]::ParameterName, 'Limit total number of concurrent scans (default: 0, i.e. no limit)')
+            [CompletionResult]::new('--time-limit', 'time-limit', [CompletionResultType]::ParameterName, 'Limit total run time of all scans (ex: --time-limit 10m)')
+            [CompletionResult]::new('-v', 'v', [CompletionResultType]::ParameterName, 'Increase verbosity level (use -vv or more for greater effect. [CAUTION] 4 -v''s is probably too much)')
+            [CompletionResult]::new('--verbosity', 'verbosity', [CompletionResultType]::ParameterName, 'Increase verbosity level (use -vv or more for greater effect. [CAUTION] 4 -v''s is probably too much)')
+            [CompletionResult]::new('-q', 'q', [CompletionResultType]::ParameterName, 'Only print URLs; Don''t print status codes, response size, running config, etc...')
+            [CompletionResult]::new('--quiet', 'quiet', [CompletionResultType]::ParameterName, 'Only print URLs; Don''t print status codes, response size, running config, etc...')
+            [CompletionResult]::new('--json', 'json', [CompletionResultType]::ParameterName, 'Emit JSON logs to --output and --debug-log instead of normal text')
+            [CompletionResult]::new('-D', 'D', [CompletionResultType]::ParameterName, 'Don''t auto-filter wildcard responses')
+            [CompletionResult]::new('--dont-filter', 'dont-filter', [CompletionResultType]::ParameterName, 'Don''t auto-filter wildcard responses')
+            [CompletionResult]::new('-r', 'r', [CompletionResultType]::ParameterName, 'Follow redirects')
+            [CompletionResult]::new('--redirects', 'redirects', [CompletionResultType]::ParameterName, 'Follow redirects')
+            [CompletionResult]::new('-k', 'k', [CompletionResultType]::ParameterName, 'Disables TLS certificate validation')
+            [CompletionResult]::new('--insecure', 'insecure', [CompletionResultType]::ParameterName, 'Disables TLS certificate validation')
+            [CompletionResult]::new('-n', 'n', [CompletionResultType]::ParameterName, 'Do not scan recursively')
+            [CompletionResult]::new('--no-recursion', 'no-recursion', [CompletionResultType]::ParameterName, 'Do not scan recursively')
+            [CompletionResult]::new('-f', 'f', [CompletionResultType]::ParameterName, 'Append / to each request')
+            [CompletionResult]::new('--add-slash', 'add-slash', [CompletionResultType]::ParameterName, 'Append / to each request')
+            [CompletionResult]::new('--stdin', 'stdin', [CompletionResultType]::ParameterName, 'Read url(s) from STDIN')
+            [CompletionResult]::new('-e', 'e', [CompletionResultType]::ParameterName, 'Extract links from response body (html, javascript, etc...); make new requests based on findings (default: false)')
+            [CompletionResult]::new('--extract-links', 'extract-links', [CompletionResultType]::ParameterName, 'Extract links from response body (html, javascript, etc...); make new requests based on findings (default: false)')
+            [CompletionResult]::new('-h', 'h', [CompletionResultType]::ParameterName, 'Prints help information')
+            [CompletionResult]::new('--help', 'help', [CompletionResultType]::ParameterName, 'Prints help information')
+            [CompletionResult]::new('-V', 'V', [CompletionResultType]::ParameterName, 'Prints version information')
+            [CompletionResult]::new('--version', 'version', [CompletionResultType]::ParameterName, 'Prints version information')
+            break
+        }
+    })
+
+    $completions.Where{ $_.CompletionText -like "$wordToComplete*" } |
+        Sort-Object -Property ListItemText
+}

shell_completions/feroxbuster.bash

@@ -0,0 +1,217 @@
+_feroxbuster() {
+    local i cur prev opts cmds
+    COMPREPLY=()
+    cur="${COMP_WORDS[COMP_CWORD]}"
+    prev="${COMP_WORDS[COMP_CWORD-1]}"
+    cmd=""
+    opts=""
+
+    for i in ${COMP_WORDS[@]}
+    do
+        case "${i}" in
+            feroxbuster)
+                cmd="feroxbuster"
+                ;;
+            
+            *)
+                ;;
+        esac
+    done
+
+    case "${cmd}" in
+        feroxbuster)
+            opts=" -v -q -D -r -k -n -f -e -h -V -w -u -t -d -T -p -P -R -s -o -a -x -H -Q -S -X -W -N -C -L  --verbosity --quiet --json --dont-filter --redirects --insecure --no-recursion --add-slash --stdin --extract-links --help --version --wordlist --url --threads --depth --timeout --proxy --replay-proxy --replay-codes --status-codes --output --resume-from --debug-log --user-agent --extensions --headers --query --filter-size --filter-regex --filter-words --filter-lines --filter-status --filter-similar-to --scan-limit --time-limit  "
+            if [[ ${cur} == -* || ${COMP_CWORD} -eq 1 ]] ; then
+                COMPREPLY=( $(compgen -W "${opts}" -- "${cur}") )
+                return 0
+            fi
+            case "${prev}" in
+                
+                --wordlist)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -w)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --url)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -u)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --threads)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -t)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --depth)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -d)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --timeout)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -T)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --proxy)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -p)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --replay-proxy)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -P)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --replay-codes)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -R)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --status-codes)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -s)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --output)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -o)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --resume-from)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --debug-log)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --user-agent)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -a)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --extensions)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -x)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --headers)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -H)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --query)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -Q)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --filter-size)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -S)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --filter-regex)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -X)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --filter-words)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -W)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --filter-lines)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -N)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --filter-status)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -C)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --filter-similar-to)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --scan-limit)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                    -L)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                --time-limit)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
+                *)
+                    COMPREPLY=()
+                    ;;
+            esac
+            COMPREPLY=( $(compgen -W "${opts}" -- "${cur}") )
+            return 0
+            ;;
+        
+    esac
+}
+
+complete -F _feroxbuster -o bashdefault -o default feroxbuster

shell_completions/feroxbuster.fish

@@ -0,0 +1,36 @@
+complete -c feroxbuster -n "__fish_use_subcommand" -s w -l wordlist -d 'Path to the wordlist'
+complete -c feroxbuster -n "__fish_use_subcommand" -s u -l url -d 'The target URL(s) (required, unless --stdin used)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s t -l threads -d 'Number of concurrent threads (default: 50)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s d -l depth -d 'Maximum recursion depth, a depth of 0 is infinite recursion (default: 4)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s T -l timeout -d 'Number of seconds before a request times out (default: 7)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s p -l proxy -d 'Proxy to use for requests (ex: http(s)://host:port, socks5(h)://host:port)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s P -l replay-proxy -d 'Send only unfiltered requests through a Replay Proxy, instead of all requests'
+complete -c feroxbuster -n "__fish_use_subcommand" -s R -l replay-codes -d 'Status Codes to send through a Replay Proxy when found (default: --status-codes value)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s s -l status-codes -d 'Status Codes to include (allow list) (default: 200 204 301 302 307 308 401 403 405)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s o -l output -d 'Output file to write results to (use w/ --json for JSON entries)'
+complete -c feroxbuster -n "__fish_use_subcommand" -l resume-from -d 'State file from which to resume a partially complete scan (ex. --resume-from ferox-1606586780.state)'
+complete -c feroxbuster -n "__fish_use_subcommand" -l debug-log -d 'Output file to write log entries (use w/ --json for JSON entries)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s a -l user-agent -d 'Sets the User-Agent (default: feroxbuster/VERSION)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s x -l extensions -d 'File extension(s) to search for (ex: -x php -x pdf js)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s H -l headers -d 'Specify HTTP headers (ex: -H Header:val \'stuff: things\')'
+complete -c feroxbuster -n "__fish_use_subcommand" -s Q -l query -d 'Specify URL query parameters (ex: -Q token=stuff -Q secret=key)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s S -l filter-size -d 'Filter out messages of a particular size (ex: -S 5120 -S 4927,1970)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s X -l filter-regex -d 'Filter out messages via regular expression matching on the response\'s body (ex: -X \'^ignore me$\')'
+complete -c feroxbuster -n "__fish_use_subcommand" -s W -l filter-words -d 'Filter out messages of a particular word count (ex: -W 312 -W 91,82)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s N -l filter-lines -d 'Filter out messages of a particular line count (ex: -N 20 -N 31,30)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s C -l filter-status -d 'Filter out status codes (deny list) (ex: -C 200 -C 401)'
+complete -c feroxbuster -n "__fish_use_subcommand" -l filter-similar-to -d 'Filter out pages that are similar to the given page (ex. --filter-similar-to http://site.xyz/soft404)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s L -l scan-limit -d 'Limit total number of concurrent scans (default: 0, i.e. no limit)'
+complete -c feroxbuster -n "__fish_use_subcommand" -l time-limit -d 'Limit total run time of all scans (ex: --time-limit 10m)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s v -l verbosity -d 'Increase verbosity level (use -vv or more for greater effect. [CAUTION] 4 -v\'s is probably too much)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s q -l quiet -d 'Only print URLs; Don\'t print status codes, response size, running config, etc...'
+complete -c feroxbuster -n "__fish_use_subcommand" -l json -d 'Emit JSON logs to --output and --debug-log instead of normal text'
+complete -c feroxbuster -n "__fish_use_subcommand" -s D -l dont-filter -d 'Don\'t auto-filter wildcard responses'
+complete -c feroxbuster -n "__fish_use_subcommand" -s r -l redirects -d 'Follow redirects'
+complete -c feroxbuster -n "__fish_use_subcommand" -s k -l insecure -d 'Disables TLS certificate validation'
+complete -c feroxbuster -n "__fish_use_subcommand" -s n -l no-recursion -d 'Do not scan recursively'
+complete -c feroxbuster -n "__fish_use_subcommand" -s f -l add-slash -d 'Append / to each request'
+complete -c feroxbuster -n "__fish_use_subcommand" -l stdin -d 'Read url(s) from STDIN'
+complete -c feroxbuster -n "__fish_use_subcommand" -s e -l extract-links -d 'Extract links from response body (html, javascript, etc...); make new requests based on findings (default: false)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s h -l help -d 'Prints help information'
+complete -c feroxbuster -n "__fish_use_subcommand" -s V -l version -d 'Prints version information'

src/banner.rs

@@ -1,6 +1,6 @@
 use crate::config::{Configuration, CONFIGURATION};
 use crate::utils::{make_request, status_colorizer};
-use console::style;
+use console::{style, Emoji};
 use reqwest::{Client, Url};
 use serde_json::Value;
 use std::io::Write;
@@ -126,6 +126,14 @@ async fn needs_update(client: &Client, url: &str, bin_version: &str) -> UpdateSt
     unknown
 }
 
+/// Simple wrapper for emoji or fallback when terminal doesn't support emoji
+fn format_emoji(emoji: &str) -> String {
+    let width = console::measure_text_width(emoji);
+    let pad_len = width * width;
+    let pad = format!("{:<pad_len$}", "\u{0020}", pad_len = pad_len);
+    Emoji(emoji, &pad).to_string()
+}
+
 /// Prints the banner to stdout.
 ///
 /// Only prints those settings which are either always present, or passed in by the user.
@@ -138,10 +146,10 @@ where
  ___  ___  __   __     __      __         __   ___
 |__  |__  |__) |__) | /  `    /  \ \_/ | |  \ |__
 |    |___ |  \ |  \ | \__,    \__/ / \ | |__/ |___
-by Ben "epi" Risher {}                  ver: {}"#,
-        '\u{1F913}', version
+by Ben "epi" Risher {}                 ver: {}"#,
+        Emoji("🤓", &format!("{:<2}", "\u{0020}")),
+        version
     );
-
     let status = needs_update(&CONFIGURATION.client, UPDATE_URL, version).await;
 
     let top = "───────────────────────────┬──────────────────────";
@@ -156,7 +164,7 @@ by Ben "epi" Risher {}                  ver: {}"#,
         writeln!(
             &mut writer,
             "{}",
-            format_banner_entry!("\u{1F3af}", "Target Url", target)
+            format_banner_entry!(format_emoji("🎯"), "Target Url", target)
         )
         .unwrap_or_default(); // 🎯
     }
@@ -170,14 +178,14 @@ by Ben "epi" Risher {}                  ver: {}"#,
     writeln!(
         &mut writer,
         "{}",
-        format_banner_entry!("\u{1F680}", "Threads", config.threads)
+        format_banner_entry!(format_emoji("🚀"), "Threads", config.threads)
     )
     .unwrap_or_default(); // 🚀
 
     writeln!(
         &mut writer,
         "{}",
-        format_banner_entry!("\u{1f4d6}", "Wordlist", config.wordlist)
+        format_banner_entry!(format_emoji("📖"), "Wordlist", config.wordlist)
     )
     .unwrap_or_default(); // 📖
 
@@ -185,7 +193,7 @@ by Ben "epi" Risher {}                  ver: {}"#,
         &mut writer,
         "{}",
         format_banner_entry!(
-            "\u{1F197}",
+            format_emoji("🆗"),
             "Status Codes",
             format!("[{}]", codes.join(", "))
         )
@@ -205,7 +213,7 @@ by Ben "epi" Risher {}                  ver: {}"#,
             &mut writer,
             "{}",
             format_banner_entry!(
-                "\u{1f5d1}",
+                format_emoji("🗑"),
                 "Status Code Filters",
                 format!("[{}]", code_filters.join(", "))
             )
@@ -216,14 +224,14 @@ by Ben "epi" Risher {}                  ver: {}"#,
     writeln!(
         &mut writer,
         "{}",
-        format_banner_entry!("\u{1f4a5}", "Timeout (secs)", config.timeout)
+        format_banner_entry!(format_emoji("💥"), "Timeout (secs)", config.timeout)
     )
     .unwrap_or_default(); // 💥
 
     writeln!(
         &mut writer,
         "{}",
-        format_banner_entry!("\u{1F9a1}", "User-Agent", config.user_agent)
+        format_banner_entry!(format_emoji("🦡"), "User-Agent", config.user_agent)
     )
     .unwrap_or_default(); // 🦡
 
@@ -232,7 +240,7 @@ by Ben "epi" Risher {}                  ver: {}"#,
         writeln!(
             &mut writer,
             "{}",
-            format_banner_entry!("\u{1f489}", "Config File", config.config)
+            format_banner_entry!(format_emoji("💉"), "Config File", config.config)
         )
         .unwrap_or_default(); // 💉
     }
@@ -241,7 +249,7 @@ by Ben "epi" Risher {}                  ver: {}"#,
         writeln!(
             &mut writer,
             "{}",
-            format_banner_entry!("\u{1f48e}", "Proxy", config.proxy)
+            format_banner_entry!(format_emoji("💎"), "Proxy", config.proxy)
         )
         .unwrap_or_default(); // 💎
     }
@@ -255,7 +263,7 @@ by Ben "epi" Risher {}                  ver: {}"#,
         writeln!(
             &mut writer,
             "{}",
-            format_banner_entry!("\u{1f3a5}", "Replay Proxy", config.replay_proxy)
+            format_banner_entry!(format_emoji("🎥"), "Replay Proxy", config.replay_proxy)
         )
         .unwrap_or_default(); // 🎥
 
@@ -267,7 +275,7 @@ by Ben "epi" Risher {}                  ver: {}"#,
             &mut writer,
             "{}",
             format_banner_entry!(
-                "\u{1f4fc}",
+                format_emoji("📼"),
                 "Replay Proxy Codes",
                 format!("[{}]", replay_codes.join(", "))
             )
@@ -280,7 +288,7 @@ by Ben "epi" Risher {}                  ver: {}"#,
             writeln!(
                 &mut writer,
                 "{}",
-                format_banner_entry!("\u{1f92f}", "Header", name, value)
+                format_banner_entry!(format_emoji("🤯"), "Header", name, value)
             )
             .unwrap_or_default(); // 🤯
         }
@@ -291,7 +299,18 @@ by Ben "epi" Risher {}                  ver: {}"#,
             writeln!(
                 &mut writer,
                 "{}",
-                format_banner_entry!("\u{1f4a2}", "Size Filter", filter)
+                format_banner_entry!(format_emoji("💢"), "Size Filter", filter)
+            )
+            .unwrap_or_default(); // 💢
+        }
+    }
+
+    if !config.filter_similar.is_empty() {
+        for filter in &config.filter_similar {
+            writeln!(
+                &mut writer,
+                "{}",
+                format_banner_entry!(format_emoji("💢"), "Similarity Filter", filter)
             )
             .unwrap_or_default(); // 💢
         }
@@ -301,7 +320,7 @@ by Ben "epi" Risher {}                  ver: {}"#,
         writeln!(
             &mut writer,
             "{}",
-            format_banner_entry!("\u{1f4a2}", "Word Count Filter", filter)
+            format_banner_entry!(format_emoji("💢"), "Word Count Filter", filter)
         )
         .unwrap_or_default(); // 💢
     }
@@ -310,7 +329,16 @@ by Ben "epi" Risher {}                  ver: {}"#,
         writeln!(
             &mut writer,
             "{}",
-            format_banner_entry!("\u{1f4a2}", "Line Count Filter", filter)
+            format_banner_entry!(format_emoji("💢"), "Line Count Filter", filter)
+        )
+        .unwrap_or_default(); // 💢
+    }
+
+    for filter in &config.filter_regex {
+        writeln!(
+            &mut writer,
+            "{}",
+            format_banner_entry!(format_emoji("💢"), "Regex Filter", filter)
         )
         .unwrap_or_default(); // 💢
     }
@@ -319,18 +347,27 @@ by Ben "epi" Risher {}                  ver: {}"#,
         writeln!(
             &mut writer,
             "{}",
-            format_banner_entry!("\u{1F50E}", "Extract Links", config.extract_links)
+            format_banner_entry!(format_emoji("🔎"), "Extract Links", config.extract_links)
         )
         .unwrap_or_default(); // 🔎
     }
 
+    if config.json {
+        writeln!(
+            &mut writer,
+            "{}",
+            format_banner_entry!(format_emoji("🧔"), "JSON Output", config.json)
+        )
+        .unwrap_or_default(); // 🧔
+    }
+
     if !config.queries.is_empty() {
         for query in &config.queries {
             writeln!(
                 &mut writer,
                 "{}",
                 format_banner_entry!(
-                    "\u{1f914}",
+                    format_emoji("🤔"),
                     "Query Parameter",
                     format!("{}={}", query.0, query.1)
                 )
@@ -343,17 +380,26 @@ by Ben "epi" Risher {}                  ver: {}"#,
         writeln!(
             &mut writer,
             "{}",
-            format_banner_entry!("\u{1f4be}", "Output File", config.output)
+            format_banner_entry!(format_emoji("💾"), "Output File", config.output)
         )
         .unwrap_or_default(); // 💾
     }
 
+    if !config.debug_log.is_empty() {
+        writeln!(
+            &mut writer,
+            "{}",
+            format_banner_entry!(format_emoji("🪲"), "Debugging Log", config.debug_log)
+        )
+        .unwrap_or_default(); // 🪲
+    }
+
     if !config.extensions.is_empty() {
         writeln!(
             &mut writer,
             "{}",
             format_banner_entry!(
-                "\u{1f4b2}",
+                format_emoji("💲"),
                 "Extensions",
                 format!("[{}]", config.extensions.join(", "))
             )
@@ -365,7 +411,7 @@ by Ben "epi" Risher {}                  ver: {}"#,
         writeln!(
             &mut writer,
             "{}",
-            format_banner_entry!("\u{1f513}", "Insecure", config.insecure)
+            format_banner_entry!(format_emoji("🔓"), "Insecure", config.insecure)
         )
         .unwrap_or_default(); // 🔓
     }
@@ -374,7 +420,7 @@ by Ben "epi" Risher {}                  ver: {}"#,
         writeln!(
             &mut writer,
             "{}",
-            format_banner_entry!("\u{1f4cd}", "Follow Redirects", config.redirects)
+            format_banner_entry!(format_emoji("📍"), "Follow Redirects", config.redirects)
         )
         .unwrap_or_default(); // 📍
     }
@@ -383,53 +429,31 @@ by Ben "epi" Risher {}                  ver: {}"#,
         writeln!(
             &mut writer,
             "{}",
-            format_banner_entry!("\u{1f92a}", "Filter Wildcards", !config.dont_filter)
+            format_banner_entry!(format_emoji("🤪"), "Filter Wildcards", !config.dont_filter)
         )
         .unwrap_or_default(); // 🤪
     }
 
-    match config.verbosity {
+    let volume = ["🔈", "🔉", "🔊", "📢"];
+    if let 1..=4 = config.verbosity {
         //speaker medium volume (increasing with verbosity to loudspeaker)
-        1 => {
-            writeln!(
-                &mut writer,
-                "{}",
-                format_banner_entry!("\u{1f508}", "Verbosity", config.verbosity)
+        writeln!(
+            &mut writer,
+            "{}",
+            format_banner_entry!(
+                format_emoji(volume[config.verbosity as usize - 1]),
+                "Verbosity",
+                config.verbosity
             )
-            .unwrap_or_default(); // 🔈
-        }
-        2 => {
-            writeln!(
-                &mut writer,
-                "{}",
-                format_banner_entry!("\u{1f509}", "Verbosity", config.verbosity)
-            )
-            .unwrap_or_default(); // 🔉
-        }
-        3 => {
-            writeln!(
-                &mut writer,
-                "{}",
-                format_banner_entry!("\u{1f50a}", "Verbosity", config.verbosity)
-            )
-            .unwrap_or_default(); // 🔊
-        }
-        4 => {
-            writeln!(
-                &mut writer,
-                "{}",
-                format_banner_entry!("\u{1f4e2}", "Verbosity", config.verbosity)
-            )
-            .unwrap_or_default(); // 📢
-        }
-        _ => {}
+        )
+        .unwrap_or_default();
     }
 
     if config.add_slash {
         writeln!(
             &mut writer,
             "{}",
-            format_banner_entry!("\u{1fa93}", "Add Slash", config.add_slash)
+            format_banner_entry!(format_emoji("🪓"), "Add Slash", config.add_slash)
         )
         .unwrap_or_default(); // 🪓
     }
@@ -439,14 +463,14 @@ by Ben "epi" Risher {}                  ver: {}"#,
             writeln!(
                 &mut writer,
                 "{}",
-                format_banner_entry!("\u{1f503}", "Recursion Depth", "INFINITE")
+                format_banner_entry!(format_emoji("🔃"), "Recursion Depth", "INFINITE")
             )
             .unwrap_or_default(); // 🔃
         } else {
             writeln!(
                 &mut writer,
                 "{}",
-                format_banner_entry!("\u{1f503}", "Recursion Depth", config.depth)
+                format_banner_entry!(format_emoji("🔃"), "Recursion Depth", config.depth)
             )
             .unwrap_or_default(); // 🔃
         }
@@ -454,7 +478,7 @@ by Ben "epi" Risher {}                  ver: {}"#,
         writeln!(
             &mut writer,
             "{}",
-            format_banner_entry!("\u{1f6ab}", "Do Not Recurse", config.no_recursion)
+            format_banner_entry!(format_emoji("🚫"), "Do Not Recurse", config.no_recursion)
         )
         .unwrap_or_default(); // 🚫
     }
@@ -463,17 +487,30 @@ by Ben "epi" Risher {}                  ver: {}"#,
         writeln!(
             &mut writer,
             "{}",
-            format_banner_entry!("\u{1f9a5}", "Concurrent Scan Limit", config.scan_limit)
+            format_banner_entry!(
+                format_emoji("🦥"),
+                "Concurrent Scan Limit",
+                config.scan_limit
+            )
         )
         .unwrap_or_default(); // 🦥
     }
 
+    if !CONFIGURATION.time_limit.is_empty() {
+        writeln!(
+            &mut writer,
+            "{}",
+            format_banner_entry!(format_emoji("🕖"), "Time Limit", config.time_limit)
+        )
+        .unwrap_or_default(); // 🕖
+    }
+
     if matches!(status, UpdateStatus::OutOfDate) {
         writeln!(
             &mut writer,
             "{}",
             format_banner_entry!(
-                "\u{1f389}",
+                format_emoji("🎉"),
                 "New Version Available",
                 "https://github.com/epi052/feroxbuster/releases/latest"
             )
@@ -485,12 +522,14 @@ by Ben "epi" Risher {}                  ver: {}"#,
     // ⏯
     writeln!(
         &mut writer,
-        " \u{23ef}   Press [{}] to {}|{} your scan",
+        " {}   Press [{}] to {}|{} your scan",
+        format_emoji("⏯"),
         style("ENTER").yellow(),
         style("pause").red(),
         style("resume").green()
     )
     .unwrap_or_default();
+
     writeln!(&mut writer, "{}", addl_section).unwrap_or_default();
 }
 
@@ -499,7 +538,7 @@ mod tests {
     use super::*;
     use crate::VERSION;
     use httpmock::Method::GET;
-    use httpmock::{Mock, MockServer};
+    use httpmock::MockServer;
     use std::fs::read_to_string;
     use std::io::stderr;
     use std::time::Duration;
@@ -584,16 +623,14 @@ mod tests {
     async fn banner_needs_update_returns_up_to_date() {
         let srv = MockServer::start();
 
-        let mock = Mock::new()
-            .expect_method(GET)
-            .expect_path("/latest")
-            .return_status(200)
-            .return_body("{\"tag_name\":\"v1.1.0\"}")
-            .create_on(&srv);
+        let mock = srv.mock(|when, then| {
+            when.method(GET).path("/latest");
+            then.status(200).body("{\"tag_name\":\"v1.1.0\"}");
+        });
 
         let result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.1.0").await;
 
-        assert_eq!(mock.times_called(), 1);
+        assert_eq!(mock.hits(), 1);
         assert!(matches!(result, UpdateStatus::UpToDate));
     }
 
@@ -602,16 +639,14 @@ mod tests {
     async fn banner_needs_update_returns_out_of_date() {
         let srv = MockServer::start();
 
-        let mock = Mock::new()
-            .expect_method(GET)
-            .expect_path("/latest")
-            .return_status(200)
-            .return_body("{\"tag_name\":\"v1.1.0\"}")
-            .create_on(&srv);
+        let mock = srv.mock(|when, then| {
+            when.method(GET).path("/latest");
+            then.status(200).body("{\"tag_name\":\"v1.1.0\"}");
+        });
 
         let result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.0.1").await;
 
-        assert_eq!(mock.times_called(), 1);
+        assert_eq!(mock.hits(), 1);
         assert!(matches!(result, UpdateStatus::OutOfDate));
     }
 
@@ -620,17 +655,16 @@ mod tests {
     async fn banner_needs_update_returns_unknown_on_timeout() {
         let srv = MockServer::start();
 
-        let mock = Mock::new()
-            .expect_method(GET)
-            .expect_path("/latest")
-            .return_status(200)
-            .return_body("{\"tag_name\":\"v1.1.0\"}")
-            .return_with_delay(Duration::from_secs(8))
-            .create_on(&srv);
+        let mock = srv.mock(|when, then| {
+            when.method(GET).path("/latest");
+            then.status(200)
+                .body("{\"tag_name\":\"v1.1.0\"}")
+                .delay(Duration::from_secs(8));
+        });
 
         let result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.0.1").await;
 
-        assert_eq!(mock.times_called(), 1);
+        assert_eq!(mock.hits(), 1);
         assert!(matches!(result, UpdateStatus::Unknown));
     }
 
@@ -639,16 +673,14 @@ mod tests {
     async fn banner_needs_update_returns_unknown_on_bad_json_response() {
         let srv = MockServer::start();
 
-        let mock = Mock::new()
-            .expect_method(GET)
-            .expect_path("/latest")
-            .return_status(200)
-            .return_body("not json")
-            .create_on(&srv);
+        let mock = srv.mock(|when, then| {
+            when.method(GET).path("/latest");
+            then.status(200).body("not json");
+        });
 
         let result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.0.1").await;
 
-        assert_eq!(mock.times_called(), 1);
+        assert_eq!(mock.hits(), 1);
         assert!(matches!(result, UpdateStatus::Unknown));
     }
 
@@ -657,16 +689,15 @@ mod tests {
     async fn banner_needs_update_returns_unknown_on_json_without_correct_tag() {
         let srv = MockServer::start();
 
-        let mock = Mock::new()
-            .expect_method(GET)
-            .expect_path("/latest")
-            .return_status(200)
-            .return_body("{\"no tag_name\": \"doesn't exist\"}")
-            .create_on(&srv);
+        let mock = srv.mock(|when, then| {
+            when.method(GET).path("/latest");
+            then.status(200)
+                .body("{\"no tag_name\": \"doesn't exist\"}");
+        });
 
         let result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.0.1").await;
 
-        assert_eq!(mock.times_called(), 1);
+        assert_eq!(mock.hits(), 1);
         assert!(matches!(result, UpdateStatus::Unknown));
     }
 }

src/config.rs

@@ -1,11 +1,12 @@
+use crate::scan_manager::resume_scan;
 use crate::utils::{module_colorizer, status_colorizer};
 use crate::{client, parser, progress};
-use crate::{DEFAULT_CONFIG_NAME, DEFAULT_STATUS_CODES, DEFAULT_WORDLIST, VERSION};
-use clap::value_t;
+use crate::{FeroxSerialize, DEFAULT_CONFIG_NAME, DEFAULT_STATUS_CODES, DEFAULT_WORDLIST, VERSION};
+use clap::{value_t, ArgMatches};
 use indicatif::{MultiProgress, ProgressBar, ProgressDrawTarget};
 use lazy_static::lazy_static;
 use reqwest::{Client, StatusCode};
-use serde::Deserialize;
+use serde::{Deserialize, Serialize};
 use std::collections::HashMap;
 use std::env::{current_dir, current_exe};
 use std::fs::read_to_string;
@@ -21,7 +22,33 @@ lazy_static! {
     pub static ref PROGRESS_BAR: MultiProgress = MultiProgress::with_draw_target(ProgressDrawTarget::stdout());
 
     /// Global progress bar that is only used for printing messages that don't jack up other bars
-    pub static ref PROGRESS_PRINTER: ProgressBar = progress::add_bar("", 0, true);
+    pub static ref PROGRESS_PRINTER: ProgressBar = progress::add_bar("", 0, true, false);
+}
+
+/// macro helper to abstract away repetitive configuration updates
+macro_rules! update_config_if_present {
+    ($c:expr, $m:ident, $v:expr, $t:ty) => {
+        match value_t!($m, $v, $t) {
+            Ok(value) => *$c = value, // Update value
+            Err(clap::Error {
+                kind: clap::ErrorKind::ArgumentNotFound,
+                message: _,
+                info: _,
+            }) => {
+                // Do nothing if argument not found
+            }
+            Err(e) => e.exit(), // Exit with error on parse error
+        }
+    };
+}
+
+/// macro helper to abstract away repetitive if not default: update checks
+macro_rules! update_if_not_default {
+    ($old:expr, $new:expr, $default:expr) => {
+        if $new != $default {
+            *$old = $new;
+        }
+    };
 }
 
 /// simple helper to clean up some code reuse below; panics under test / exits in prod
@@ -49,8 +76,12 @@ fn report_and_exit(err: &str) -> ! {
 /// In that order.
 ///
 /// Inspired by and derived from https://github.com/PhilipDaniels/rust-config-example
-#[derive(Debug, Clone, Deserialize)]
+#[derive(Debug, Clone, Deserialize, Serialize)]
 pub struct Configuration {
+    #[serde(rename = "type", default = "serialized_type")]
+    /// Name of this type of struct, used for serialization, i.e. `{"type":"configuration"}`
+    kind: String,
+
     /// Path to the wordlist
     #[serde(default = "wordlist")]
     pub wordlist: String,
@@ -59,11 +90,11 @@ pub struct Configuration {
     #[serde(default)]
     pub config: String,
 
-    /// Proxy to use for requests (ex: http(s)://host:port, socks5://host:port)
+    /// Proxy to use for requests (ex: http(s)://host:port, socks5(h)://host:port)
     #[serde(default)]
     pub proxy: String,
 
-    /// Replay Proxy to use for requests (ex: http(s)://host:port, socks5://host:port)
+    /// Replay Proxy to use for requests (ex: http(s)://host:port, socks5(h)://host:port)
     #[serde(default)]
     pub replay_proxy: String,
 
@@ -76,7 +107,7 @@ pub struct Configuration {
     pub status_codes: Vec<u16>,
 
     /// Status Codes to replay to the Replay Proxy (default: whatever is passed to --status-code)
-    #[serde(default)]
+    #[serde(default = "status_codes")]
     pub replay_codes: Vec<u16>,
 
     /// Status Codes to filter out (deny list)
@@ -107,10 +138,19 @@ pub struct Configuration {
     #[serde(default)]
     pub quiet: bool,
 
+    /// Store log output as NDJSON
+    #[serde(default)]
+    pub json: bool,
+
     /// Output file to write results to (default: stdout)
     #[serde(default)]
     pub output: String,
 
+    /// File in which to store debug output, used in conjunction with verbosity to dictate which
+    /// logs are written
+    #[serde(default)]
+    pub debug_log: String,
+
     /// Sets the User-Agent (default: feroxbuster/VERSION)
     #[serde(default = "user_agent")]
     pub user_agent: String,
@@ -171,20 +211,53 @@ pub struct Configuration {
     #[serde(default)]
     pub filter_word_count: Vec<usize>,
 
+    /// Filter out messages by regular expression
+    #[serde(default)]
+    pub filter_regex: Vec<String>,
+
     /// Don't auto-filter wildcard responses
     #[serde(default)]
     pub dont_filter: bool,
+
+    /// Scan started from a state file, not from CLI args
+    #[serde(default)]
+    pub resumed: bool,
+
+    /// Whether or not a scan's current state should be saved when user presses Ctrl+C
+    ///
+    /// Not configurable from CLI; can only be set from a config file
+    #[serde(default = "save_state")]
+    pub save_state: bool,
+
+    /// The maximum runtime for a scan, expressed as N[smdh] where N can be parsed into a
+    /// non-negative integer and the next character is either s, m, h, or d (case insensitive)
+    #[serde(default)]
+    pub time_limit: String,
+
+    /// Filter out response bodies that meet a certain threshold of similarity
+    #[serde(default)]
+    pub filter_similar: Vec<String>,
 }
 
-// functions timeout, threads, status_codes, user_agent, wordlist, and depth are used to provide
+// functions timeout, threads, status_codes, user_agent, wordlist, save_state, and depth are used to provide
 // defaults in the event that a ferox-config.toml is found but one or more of the values below
 // aren't listed in the config.  This way, we get the correct defaults upon Deserialization
 
+/// default Configuration type for use in json output
+fn serialized_type() -> String {
+    String::from("configuration")
+}
+
 /// default timeout value
 fn timeout() -> u64 {
     7
 }
 
+/// default save_state value
+fn save_state() -> bool {
+    true
+}
+
 /// default threads value
 fn threads() -> usize {
     50
@@ -222,8 +295,10 @@ impl Default for Configuration {
         let replay_client = None;
         let status_codes = status_codes();
         let replay_codes = status_codes.clone();
+        let kind = serialized_type();
 
         Configuration {
+            kind,
             client,
             timeout,
             user_agent,
@@ -232,7 +307,9 @@ impl Default for Configuration {
             replay_client,
             dont_filter: false,
             quiet: false,
+            resumed: false,
             stdin: false,
+            json: false,
             verbosity: 0,
             scan_limit: 0,
             add_slash: false,
@@ -240,17 +317,22 @@ impl Default for Configuration {
             redirects: false,
             no_recursion: false,
             extract_links: false,
+            save_state: true,
             proxy: String::new(),
             config: String::new(),
             output: String::new(),
+            debug_log: String::new(),
             target_url: String::new(),
+            time_limit: String::new(),
             replay_proxy: String::new(),
             queries: Vec::new(),
             extensions: Vec::new(),
             filter_size: Vec::new(),
+            filter_regex: Vec::new(),
             filter_line_count: Vec::new(),
             filter_word_count: Vec::new(),
             filter_status: Vec::new(),
+            filter_similar: Vec::new(),
             headers: HashMap::new(),
             depth: depth(),
             threads: threads(),
@@ -275,11 +357,15 @@ impl Configuration {
     /// - **status_codes**: [`DEFAULT_RESPONSE_CODES`](constant.DEFAULT_RESPONSE_CODES.html)
     /// - **filter_status**: `None`
     /// - **output**: `None` (print to stdout)
+    /// - **debug_log**: `None`
     /// - **quiet**: `false`
-    /// - **user_agent**: `feroxer/VERSION`
+    /// - **save_state**: `true`
+    /// - **user_agent**: `feroxbuster/VERSION`
     /// - **insecure**: `false` (don't be insecure, i.e. don't allow invalid certs)
     /// - **extensions**: `None`
     /// - **filter_size**: `None`
+    /// - **filter_similar**: `None`
+    /// - **filter_regex**: `None`
     /// - **filter_word_count**: `None`
     /// - **filter_line_count**: `None`
     /// - **headers**: `None`
@@ -287,9 +373,11 @@ impl Configuration {
     /// - **no_recursion**: `false` (recursively scan enumerated sub-directories)
     /// - **add_slash**: `false`
     /// - **stdin**: `false`
+    /// - **json**: `false`
     /// - **dont_filter**: `false` (auto filter wildcard responses)
     /// - **depth**: `4` (maximum recursion depth)
     /// - **scan_limit**: `0` (no limit on concurrent scans imposed)
+    /// - **time_limit**: `None` (no limit on length of scan imposed)
     /// - **replay_proxy**: `None` (no limit on concurrent scans imposed)
     /// - **replay_codes**: [`DEFAULT_RESPONSE_CODES`](constant.DEFAULT_RESPONSE_CODES.html)
     ///
@@ -313,13 +401,65 @@ impl Configuration {
     pub fn new() -> Self {
         // when compiling for test, we want to eliminate the runtime dependency of the parser
         if cfg!(test) {
-            return Configuration::default();
+            let mut test_config = Configuration::default();
+            test_config.save_state = false; // don't clutter up junk when testing
+            return test_config;
         }
 
+        let args = parser::initialize().get_matches();
+
         // Get the default configuration, this is what will apply if nothing
         // else is specified.
         let mut config = Configuration::default();
 
+        // read in all config files
+        Self::parse_config_files(&mut config);
+
+        // read in the user provided options, this produces a separate instance of Configuration
+        // in order to allow for potentially merging into a --resume-from Configuration
+        let cli_config = Self::parse_cli_args(&args);
+
+        // --resume-from used, need to first read the Configuration from disk, and then
+        // merge the cli_config into the resumed config
+        if let Some(filename) = args.value_of("resume_from") {
+            // when resuming a scan, instead of normal configuration loading, we just
+            // load the config from disk by calling resume_scan
+            let mut previous_config = resume_scan(filename);
+
+            // if any other arguments were passed on the command line, the theory is that the
+            // user meant to modify the previously cancelled/saved scan in some way that we
+            // should take into account
+            Self::merge_config(&mut previous_config, cli_config);
+
+            // the resumed flag isn't printed in the banner and really has no business being
+            // serialized or included in much of the usual config logic; simply setting it to true
+            // here and being done with it
+            previous_config.resumed = true;
+
+            // if the user used --stdin, we already have all the scans started (or complete), we
+            // need to flip stdin to false so that the 'read from stdin' logic doesn't fire (if
+            // not flipped to false, the program hangs waiting for input from stdin again)
+            previous_config.stdin = false;
+
+            // clients aren't serialized, have to remake them from the previous config
+            Self::try_rebuild_clients(&mut previous_config);
+
+            return previous_config;
+        }
+
+        // if we've gotten to this point in the code, --resume-from was not used, so we need to
+        // merge the cli options into the config file options and return the result
+        Self::merge_config(&mut config, cli_config);
+
+        // rebuild clients is the last step in either code branch
+        Self::try_rebuild_clients(&mut config);
+
+        config
+    }
+
+    /// Parse all possible versions of the ferox-config.toml file, adhering to the order of
+    /// precedence outlined above
+    fn parse_config_files(mut config: &mut Self) {
         // Next, we parse the ferox-config.toml file, if present and set the values
         // therein to overwrite our default values. Deserialized defaults are specified
         // in the Configuration struct so that we don't change anything that isn't
@@ -361,30 +501,20 @@ impl Configuration {
             let config_file = cwd.join(DEFAULT_CONFIG_NAME);
             Self::parse_and_merge_config(config_file, &mut config);
         }
+    }
 
-        let args = parser::initialize().get_matches();
-
-        macro_rules! update_config_if_present {
-            ($c:expr, $m:ident, $v:expr, $t:ty) => {
-                match value_t!($m, $v, $t) {
-                    Ok(value) => *$c = value, // Update value
-                    Err(clap::Error {
-                        kind: clap::ErrorKind::ArgumentNotFound,
-                        message: _,
-                        info: _,
-                    }) => {
-                        // Do nothing if argument not found
-                    }
-                    Err(e) => e.exit(), // Exit with error on parse error
-                }
-            };
-        }
+    /// Given a set of ArgMatches read from the CLI, update and return the default Configuration
+    /// settings
+    fn parse_cli_args(args: &ArgMatches) -> Self {
+        let mut config = Configuration::default();
 
         update_config_if_present!(&mut config.threads, args, "threads", usize);
         update_config_if_present!(&mut config.depth, args, "depth", usize);
         update_config_if_present!(&mut config.scan_limit, args, "scan_limit", usize);
         update_config_if_present!(&mut config.wordlist, args, "wordlist", String);
         update_config_if_present!(&mut config.output, args, "output", String);
+        update_config_if_present!(&mut config.debug_log, args, "debug_log", String);
+        update_config_if_present!(&mut config.time_limit, args, "time_limit", String);
 
         if let Some(arg) = args.values_of("status_codes") {
             config.status_codes = arg
@@ -424,6 +554,14 @@ impl Configuration {
             config.extensions = arg.map(|val| val.to_string()).collect();
         }
 
+        if let Some(arg) = args.values_of("filter_regex") {
+            config.filter_regex = arg.map(|val| val.to_string()).collect();
+        }
+
+        if let Some(arg) = args.values_of("filter_similar") {
+            config.filter_similar = arg.map(|val| val.to_string()).collect();
+        }
+
         if let Some(arg) = args.values_of("filter_size") {
             config.filter_size = arg
                 .map(|size| {
@@ -481,10 +619,14 @@ impl Configuration {
             config.extract_links = true;
         }
 
+        if args.is_present("json") {
+            config.json = true;
+        }
+
         if args.is_present("stdin") {
             config.stdin = true;
-        } else {
-            config.target_url = String::from(args.value_of("url").unwrap());
+        } else if let Some(url) = args.value_of("url") {
+            config.target_url = String::from(url);
         }
 
         ////
@@ -530,50 +672,53 @@ impl Configuration {
             }
         }
 
-        // this if statement determines if we've gotten a Client configuration change from
-        // either the config file or command line arguments; if we have, we need to rebuild
-        // the client and store it in the config struct
-        if !config.proxy.is_empty()
-            || config.timeout != timeout()
-            || config.user_agent != user_agent()
-            || config.redirects
-            || config.insecure
-            || !config.headers.is_empty()
+        config
+    }
+
+    /// this function determines if we've gotten a Client configuration change from
+    /// either the config file or command line arguments; if we have, we need to rebuild
+    /// the client and store it in the config struct
+    fn try_rebuild_clients(configuration: &mut Configuration) {
+        if !configuration.proxy.is_empty()
+            || configuration.timeout != timeout()
+            || configuration.user_agent != user_agent()
+            || configuration.redirects
+            || configuration.insecure
+            || !configuration.headers.is_empty()
+            || configuration.resumed
         {
-            if config.proxy.is_empty() {
-                config.client = client::initialize(
-                    config.timeout,
-                    &config.user_agent,
-                    config.redirects,
-                    config.insecure,
-                    &config.headers,
+            if configuration.proxy.is_empty() {
+                configuration.client = client::initialize(
+                    configuration.timeout,
+                    &configuration.user_agent,
+                    configuration.redirects,
+                    configuration.insecure,
+                    &configuration.headers,
                     None,
                 )
             } else {
-                config.client = client::initialize(
-                    config.timeout,
-                    &config.user_agent,
-                    config.redirects,
-                    config.insecure,
-                    &config.headers,
-                    Some(&config.proxy),
+                configuration.client = client::initialize(
+                    configuration.timeout,
+                    &configuration.user_agent,
+                    configuration.redirects,
+                    configuration.insecure,
+                    &configuration.headers,
+                    Some(&configuration.proxy),
                 )
             }
         }
 
-        if !config.replay_proxy.is_empty() {
+        if !configuration.replay_proxy.is_empty() {
             // only set replay_client when replay_proxy is set
-            config.replay_client = Some(client::initialize(
-                config.timeout,
-                &config.user_agent,
-                config.redirects,
-                config.insecure,
-                &config.headers,
-                Some(&config.replay_proxy),
+            configuration.replay_client = Some(client::initialize(
+                configuration.timeout,
+                &configuration.user_agent,
+                configuration.redirects,
+                configuration.insecure,
+                &configuration.headers,
+                Some(&configuration.replay_proxy),
             ));
         }
-
-        config
     }
 
     /// Given a configuration file's location and an instance of `Configuration`, read in
@@ -597,34 +742,69 @@ impl Configuration {
     }
 
     /// Given two Configurations, overwrite `settings` with the fields found in `settings_to_merge`
-    fn merge_config(settings: &mut Self, settings_to_merge: Self) {
-        settings.threads = settings_to_merge.threads;
-        settings.wordlist = settings_to_merge.wordlist;
-        settings.status_codes = settings_to_merge.status_codes;
-        settings.proxy = settings_to_merge.proxy;
-        settings.timeout = settings_to_merge.timeout;
-        settings.verbosity = settings_to_merge.verbosity;
-        settings.quiet = settings_to_merge.quiet;
-        settings.output = settings_to_merge.output;
-        settings.user_agent = settings_to_merge.user_agent;
-        settings.redirects = settings_to_merge.redirects;
-        settings.insecure = settings_to_merge.insecure;
-        settings.extract_links = settings_to_merge.extract_links;
-        settings.extensions = settings_to_merge.extensions;
-        settings.headers = settings_to_merge.headers;
-        settings.queries = settings_to_merge.queries;
-        settings.no_recursion = settings_to_merge.no_recursion;
-        settings.add_slash = settings_to_merge.add_slash;
-        settings.stdin = settings_to_merge.stdin;
-        settings.depth = settings_to_merge.depth;
-        settings.filter_size = settings_to_merge.filter_size;
-        settings.filter_word_count = settings_to_merge.filter_word_count;
-        settings.filter_line_count = settings_to_merge.filter_line_count;
-        settings.filter_status = settings_to_merge.filter_status;
-        settings.dont_filter = settings_to_merge.dont_filter;
-        settings.scan_limit = settings_to_merge.scan_limit;
-        settings.replay_proxy = settings_to_merge.replay_proxy;
-        settings.replay_codes = settings_to_merge.replay_codes;
+    fn merge_config(conf: &mut Self, new: Self) {
+        // does not include the following Configuration fields, as they don't make sense here
+        //  - kind
+        //  - client
+        //  - replay_client
+        //  - resumed
+        //  - config
+        update_if_not_default!(&mut conf.target_url, new.target_url, "");
+        update_if_not_default!(&mut conf.time_limit, new.time_limit, "");
+        update_if_not_default!(&mut conf.proxy, new.proxy, "");
+        update_if_not_default!(&mut conf.verbosity, new.verbosity, 0);
+        update_if_not_default!(&mut conf.quiet, new.quiet, false);
+        update_if_not_default!(&mut conf.output, new.output, "");
+        update_if_not_default!(&mut conf.redirects, new.redirects, false);
+        update_if_not_default!(&mut conf.insecure, new.insecure, false);
+        update_if_not_default!(&mut conf.extract_links, new.extract_links, false);
+        update_if_not_default!(&mut conf.extensions, new.extensions, Vec::<String>::new());
+        update_if_not_default!(&mut conf.headers, new.headers, HashMap::new());
+        update_if_not_default!(&mut conf.queries, new.queries, Vec::new());
+        update_if_not_default!(&mut conf.no_recursion, new.no_recursion, false);
+        update_if_not_default!(&mut conf.add_slash, new.add_slash, false);
+        update_if_not_default!(&mut conf.stdin, new.stdin, false);
+        update_if_not_default!(&mut conf.filter_size, new.filter_size, Vec::<u64>::new());
+        update_if_not_default!(
+            &mut conf.filter_regex,
+            new.filter_regex,
+            Vec::<String>::new()
+        );
+        update_if_not_default!(
+            &mut conf.filter_similar,
+            new.filter_similar,
+            Vec::<String>::new()
+        );
+        update_if_not_default!(
+            &mut conf.filter_word_count,
+            new.filter_word_count,
+            Vec::<usize>::new()
+        );
+        update_if_not_default!(
+            &mut conf.filter_line_count,
+            new.filter_line_count,
+            Vec::<usize>::new()
+        );
+        update_if_not_default!(
+            &mut conf.filter_status,
+            new.filter_status,
+            Vec::<u16>::new()
+        );
+        update_if_not_default!(&mut conf.dont_filter, new.dont_filter, false);
+        update_if_not_default!(&mut conf.scan_limit, new.scan_limit, 0);
+        update_if_not_default!(&mut conf.replay_proxy, new.replay_proxy, "");
+        update_if_not_default!(&mut conf.debug_log, new.debug_log, "");
+        update_if_not_default!(&mut conf.json, new.json, false);
+
+        update_if_not_default!(&mut conf.timeout, new.timeout, timeout());
+        update_if_not_default!(&mut conf.user_agent, new.user_agent, user_agent());
+        update_if_not_default!(&mut conf.threads, new.threads, threads());
+        update_if_not_default!(&mut conf.depth, new.depth, depth());
+        update_if_not_default!(&mut conf.wordlist, new.wordlist, wordlist());
+        update_if_not_default!(&mut conf.status_codes, new.status_codes, status_codes());
+        // status_codes() is the default for replay_codes, if they're not provided
+        update_if_not_default!(&mut conf.replay_codes, new.replay_codes, status_codes());
+        update_if_not_default!(&mut conf.save_state, new.save_state, save_state());
     }
 
     /// If present, read in `DEFAULT_CONFIG_NAME` and deserialize the specified values
@@ -650,6 +830,47 @@ impl Configuration {
     }
 }
 
+/// Implementation of FeroxMessage
+impl FeroxSerialize for Configuration {
+    /// Simple wrapper around create_report_string
+    fn as_str(&self) -> String {
+        format!("{:#?}\n", *self)
+    }
+
+    /// Create an NDJSON representation of the current scan's Configuration
+    ///
+    /// (expanded for clarity)
+    /// ex:
+    /// {
+    ///    "type":"configuration",
+    ///    "wordlist":"test",
+    ///    "config":"/home/epi/.config/feroxbuster/ferox-config.toml",
+    ///    "proxy":"",
+    ///    "replay_proxy":"",
+    ///    "target_url":"https://localhost.com",
+    ///    "status_codes":[
+    ///       200,
+    ///       204,
+    ///       301,
+    ///       302,
+    ///       307,
+    ///       308,
+    ///       401,
+    ///       403,
+    ///       405
+    ///    ],
+    /// ...
+    /// }\n
+    fn as_json(&self) -> String {
+        if let Ok(mut json) = serde_json::to_string(&self) {
+            json.push('\n');
+            json
+        } else {
+            String::from("{\"error\":\"could not Configuration convert to json\"}")
+        }
+    }
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
@@ -669,7 +890,9 @@ mod tests {
             quiet = true
             verbosity = 1
             scan_limit = 6
+            time_limit = "10m"
             output = "/some/otherpath"
+            debug_log = "/yet/anotherpath"
             redirects = true
             insecure = true
             extensions = ["html", "php", "js"]
@@ -680,8 +903,12 @@ mod tests {
             stdin = true
             dont_filter = true
             extract_links = true
+            json = true
+            save_state = false
             depth = 1
             filter_size = [4120]
+            filter_regex = ["^ignore me$"]
+            filter_similar = ["https://somesite.com/soft404"]
             filter_word_count = [994, 992]
             filter_line_count = [34]
             filter_status = [201]
@@ -699,6 +926,8 @@ mod tests {
         assert_eq!(config.wordlist, wordlist());
         assert_eq!(config.proxy, String::new());
         assert_eq!(config.target_url, String::new());
+        assert_eq!(config.time_limit, String::new());
+        assert_eq!(config.debug_log, String::new());
         assert_eq!(config.config, String::new());
         assert_eq!(config.replay_proxy, String::new());
         assert_eq!(config.status_codes, status_codes());
@@ -712,6 +941,8 @@ mod tests {
         assert_eq!(config.quiet, false);
         assert_eq!(config.dont_filter, false);
         assert_eq!(config.no_recursion, false);
+        assert_eq!(config.json, false);
+        assert_eq!(config.save_state, true);
         assert_eq!(config.stdin, false);
         assert_eq!(config.add_slash, false);
         assert_eq!(config.redirects, false);
@@ -720,6 +951,8 @@ mod tests {
         assert_eq!(config.queries, Vec::new());
         assert_eq!(config.extensions, Vec::<String>::new());
         assert_eq!(config.filter_size, Vec::<u64>::new());
+        assert_eq!(config.filter_regex, Vec::<String>::new());
+        assert_eq!(config.filter_similar, Vec::<String>::new());
         assert_eq!(config.filter_word_count, Vec::<usize>::new());
         assert_eq!(config.filter_line_count, Vec::<usize>::new());
         assert_eq!(config.filter_status, Vec::<u16>::new());
@@ -733,6 +966,13 @@ mod tests {
         assert_eq!(config.wordlist, "/some/path");
     }
 
+    #[test]
+    /// parse the test config and see that the value parsed is correct
+    fn config_reads_debug_log() {
+        let config = setup_config_test();
+        assert_eq!(config.debug_log, "/yet/anotherpath");
+    }
+
     #[test]
     /// parse the test config and see that the value parsed is correct
     fn config_reads_status_codes() {
@@ -796,6 +1036,13 @@ mod tests {
         assert_eq!(config.quiet, true);
     }
 
+    #[test]
+    /// parse the test config and see that the value parsed is correct
+    fn config_reads_json() {
+        let config = setup_config_test();
+        assert_eq!(config.json, true);
+    }
+
     #[test]
     /// parse the test config and see that the value parsed is correct
     fn config_reads_verbosity() {
@@ -866,6 +1113,20 @@ mod tests {
         assert_eq!(config.extensions, vec!["html", "php", "js"]);
     }
 
+    #[test]
+    /// parse the test config and see that the value parsed is correct
+    fn config_reads_filter_regex() {
+        let config = setup_config_test();
+        assert_eq!(config.filter_regex, vec!["^ignore me$"]);
+    }
+
+    #[test]
+    /// parse the test config and see that the value parsed is correct
+    fn config_reads_filter_similar() {
+        let config = setup_config_test();
+        assert_eq!(config.filter_similar, vec!["https://somesite.com/soft404"]);
+    }
+
     #[test]
     /// parse the test config and see that the value parsed is correct
     fn config_reads_filter_size() {
@@ -894,6 +1155,20 @@ mod tests {
         assert_eq!(config.filter_status, vec![201]);
     }
 
+    #[test]
+    /// parse the test config and see that the value parsed is correct
+    fn config_reads_save_state() {
+        let config = setup_config_test();
+        assert_eq!(config.save_state, false);
+    }
+
+    #[test]
+    /// parse the test config and see that the value parsed is correct
+    fn config_reads_time_limit() {
+        let config = setup_config_test();
+        assert_eq!(config.time_limit, "10m");
+    }
+
     #[test]
     /// parse the test config and see that the values parsed are correct
     fn config_reads_headers() {
@@ -920,4 +1195,32 @@ mod tests {
     fn config_report_and_exit_works() {
         report_and_exit("some message");
     }
+
+    #[test]
+    /// test as_str method of Configuration
+    fn as_str_returns_string_with_newline() {
+        let config = Configuration::new();
+        let config_str = config.as_str();
+        println!("{}", config_str);
+        assert!(config_str.starts_with("Configuration {"));
+        assert!(config_str.ends_with("}\n"));
+        assert!(config_str.contains("replay_codes:"));
+        assert!(config_str.contains("client: Client {"));
+        assert!(config_str.contains("user_agent: \"feroxbuster"));
+    }
+
+    #[test]
+    /// test as_json method of Configuration
+    fn as_json_returns_json_representation_of_configuration_with_newline() {
+        let mut config = Configuration::new();
+        config.timeout = 12;
+        config.depth = 2;
+        let config_str = config.as_json();
+        let json: Configuration = serde_json::from_str(&config_str).unwrap();
+        assert_eq!(json.config, config.config);
+        assert_eq!(json.wordlist, config.wordlist);
+        assert_eq!(json.replay_codes, config.replay_codes);
+        assert_eq!(json.timeout, config.timeout);
+        assert_eq!(json.depth, config.depth);
+    }
 }

src/extractor.rs

@@ -1,4 +1,10 @@
-use crate::FeroxResponse;
+use crate::{
+    client,
+    config::{Configuration, CONFIGURATION},
+    scanner::SCANNED_URLS,
+    utils::{format_url, make_request},
+    FeroxResponse,
+};
 use lazy_static::lazy_static;
 use regex::Regex;
 use reqwest::Url;
@@ -9,9 +15,18 @@ use std::collections::HashSet;
 /// Incorporates change from this [Pull Request](https://github.com/GerbenJavado/LinkFinder/pull/66/files)
 const LINKFINDER_REGEX: &str = r#"(?:"|')(((?:[a-zA-Z]{1,10}://|//)[^"'/]{1,}\.[a-zA-Z]{2,}[^"']{0,})|((?:/|\.\./|\./)[^"'><,;| *()(%%$^/\\\[\]][^"'><,;|()]{1,})|([a-zA-Z0-9_\-/]{1,}/[a-zA-Z0-9_\-/]{1,}\.(?:[a-zA-Z]{1,4}|action)(?:[\?|#][^"|']{0,}|))|([a-zA-Z0-9_\-/]{1,}/[a-zA-Z0-9_\-/]{3,}(?:[\?|#][^"|']{0,}|))|([a-zA-Z0-9_\-.]{1,}\.(?:php|asp|aspx|jsp|json|action|html|js|txt|xml)(?:[\?|#][^"|']{0,}|)))(?:"|')"#;
 
+/// Regular expression to pull url paths from robots.txt
+///
+/// ref: https://developers.google.com/search/reference/robots_txt
+const ROBOTS_TXT_REGEX: &str =
+    r#"(?m)^ *(Allow|Disallow): *(?P<url_path>[a-zA-Z0-9._/?#@!&'()+,;%=-]+?)$"#; // multi-line (?m)
+
 lazy_static! {
     /// `LINKFINDER_REGEX` as a regex::Regex type
-    static ref REGEX: Regex = Regex::new(LINKFINDER_REGEX).unwrap();
+    static ref LINKS_REGEX: Regex = Regex::new(LINKFINDER_REGEX).unwrap();
+
+    /// `ROBOTS_TXT_REGEX` as a regex::Regex type
+    static ref ROBOTS_REGEX: Regex = Regex::new(ROBOTS_TXT_REGEX).unwrap();
 }
 
 /// Iterate over a given path, return a list of every sub-path found
@@ -90,7 +105,7 @@ pub async fn get_links(response: &FeroxResponse) -> HashSet<String> {
 
     let body = response.text();
 
-    for capture in REGEX.captures_iter(&body) {
+    for capture in LINKS_REGEX.captures_iter(&body) {
         // remove single & double quotes from both ends of the capture
         // capture[0] is the entire match, additional capture groups start at [1]
         let link = capture[0].trim_matches(|c| c == '\'' || c == '"');
@@ -105,27 +120,14 @@ pub async fn get_links(response: &FeroxResponse) -> HashSet<String> {
                     continue;
                 }
 
-                for sub_path in get_sub_paths_from_path(absolute.path()) {
-                    // take a url fragment like homepage/assets/img/icons/handshake.svg and
-                    // incrementally add
-                    //     - homepage/assets/img/icons/
-                    //     - homepage/assets/img/
-                    //     - homepage/assets/
-                    //     - homepage/
-                    log::debug!("Adding {} to {:?}", sub_path, links);
-                    add_link_to_set_of_links(&sub_path, &response.url(), &mut links);
-                }
+                add_all_sub_paths(absolute.path(), &response, &mut links);
             }
             Err(e) => {
                 // this is the expected error that happens when we try to parse a url fragment
                 //     ex: Url::parse("/login") -> Err("relative URL without a base")
                 // while this is technically an error, these are good results for us
                 if e.to_string().contains("relative URL without a base") {
-                    for sub_path in get_sub_paths_from_path(link) {
-                        // incrementally save all sub-paths that led to the relative url's resource
-                        log::debug!("Adding {} to {:?}", sub_path, links);
-                        add_link_to_set_of_links(&sub_path, &response.url(), &mut links);
-                    }
+                    add_all_sub_paths(link, &response, &mut links);
                 } else {
                     // unexpected error has occurred
                     log::error!("Could not parse given url: {}", e);
@@ -135,6 +137,152 @@ pub async fn get_links(response: &FeroxResponse) -> HashSet<String> {
     }
 
     log::trace!("exit: get_links -> {:?}", links);
+
+    links
+}
+
+/// take a url fragment like homepage/assets/img/icons/handshake.svg and
+/// incrementally add
+///     - homepage/assets/img/icons/
+///     - homepage/assets/img/
+///     - homepage/assets/
+///     - homepage/
+fn add_all_sub_paths(url_path: &str, response: &FeroxResponse, mut links: &mut HashSet<String>) {
+    log::trace!(
+        "enter: add_all_sub_paths({}, {}, {:?})",
+        url_path,
+        response,
+        links
+    );
+
+    for sub_path in get_sub_paths_from_path(url_path) {
+        log::debug!("Adding {} to {:?}", sub_path, links);
+        add_link_to_set_of_links(&sub_path, &response.url(), &mut links);
+    }
+
+    log::trace!("exit: add_all_sub_paths");
+}
+
+/// Wrapper around link extraction logic
+/// currently used in two places:
+///   - links from response bodys
+///   - links from robots.txt responses
+///
+/// general steps taken:
+///   - create a new Url object based on cli options/args
+///   - check if the new Url has already been seen/scanned -> None
+///   - make a request to the new Url ? -> Some(response) : None
+pub async fn request_feroxresponse_from_new_link(url: &str) -> Option<FeroxResponse> {
+    log::trace!("enter: request_feroxresponse_from_new_link({})", url);
+
+    // create a url based on the given command line options, return None on error
+    let new_url = match format_url(
+        &url,
+        &"",
+        CONFIGURATION.add_slash,
+        &CONFIGURATION.queries,
+        None,
+    ) {
+        Ok(url) => url,
+        Err(_) => {
+            log::trace!("exit: request_feroxresponse_from_new_link -> None");
+            return None;
+        }
+    };
+
+    if SCANNED_URLS.get_scan_by_url(&new_url.to_string()).is_some() {
+        //we've seen the url before and don't need to scan again
+        log::trace!("exit: request_feroxresponse_from_new_link -> None");
+        return None;
+    }
+
+    // make the request and store the response
+    let new_response = match make_request(&CONFIGURATION.client, &new_url).await {
+        Ok(resp) => resp,
+        Err(_) => {
+            log::trace!("exit: request_feroxresponse_from_new_link -> None");
+            return None;
+        }
+    };
+
+    let new_ferox_response = FeroxResponse::from(new_response, true).await;
+
+    log::trace!(
+        "exit: request_feroxresponse_from_new_link -> {:?}",
+        new_ferox_response
+    );
+    Some(new_ferox_response)
+}
+
+/// helper function that simply requests /robots.txt on the given url's base url
+///
+/// example:
+///     http://localhost/api/users -> http://localhost/robots.txt
+///     
+/// The length of the given path has no effect on what's requested; it's always
+/// base url + /robots.txt
+pub async fn request_robots_txt(base_url: &str, config: &Configuration) -> Option<FeroxResponse> {
+    log::trace!("enter: get_robots_file({})", base_url);
+
+    // more often than not, domain/robots.txt will redirect to www.domain/robots.txt or something
+    // similar; to account for that, create a client that will follow redirects, regardless of
+    // what the user specified for the scanning client. Other than redirects, it will respect
+    // all other user specified settings
+    let follow_redirects = true;
+
+    let proxy = if config.proxy.is_empty() {
+        None
+    } else {
+        Some(config.proxy.as_str())
+    };
+
+    let client = client::initialize(
+        config.timeout,
+        &config.user_agent,
+        follow_redirects,
+        config.insecure,
+        &config.headers,
+        proxy,
+    );
+
+    if let Ok(mut url) = Url::parse(base_url) {
+        url.set_path("/robots.txt"); // overwrite existing path with /robots.txt
+
+        if let Ok(response) = make_request(&client, &url).await {
+            let ferox_response = FeroxResponse::from(response, true).await;
+
+            log::trace!("exit: get_robots_file -> {}", ferox_response);
+            return Some(ferox_response);
+        }
+    }
+
+    None
+}
+
+/// Entry point to perform link extraction from robots.txt
+///
+/// `base_url` can have paths and subpaths, however robots.txt will be requested from the
+/// root of the url
+/// given the url:
+///     http://localhost/stuff/things
+/// this function requests:
+///     http://localhost/robots.txt
+pub async fn extract_robots_txt(base_url: &str, config: &Configuration) -> HashSet<String> {
+    log::trace!("enter: extract_robots_txt({}, CONFIGURATION)", base_url);
+    let mut links = HashSet::new();
+
+    if let Some(response) = request_robots_txt(&base_url, &config).await {
+        for capture in ROBOTS_REGEX.captures_iter(response.text.as_str()) {
+            if let Some(new_path) = capture.name("url_path") {
+                if let Ok(mut new_url) = Url::parse(base_url) {
+                    new_url.set_path(new_path.as_str());
+                    add_all_sub_paths(new_url.path(), &response, &mut links);
+                }
+            }
+        }
+    }
+
+    log::trace!("exit: extract_robots_txt -> {:?}", links);
     links
 }
 
@@ -143,7 +291,7 @@ mod tests {
     use super::*;
     use crate::utils::make_request;
     use httpmock::Method::GET;
-    use httpmock::{Mock, MockServer};
+    use httpmock::MockServer;
     use reqwest::Client;
 
     #[test]
@@ -245,12 +393,12 @@ mod tests {
     ) -> Result<(), Box<dyn std::error::Error>> {
         let srv = MockServer::start();
 
-        let mock = Mock::new()
-            .expect_method(GET)
-            .expect_path("/some-path")
-            .return_status(200)
-            .return_body("\"http://defintely.not.a.thing.probably.com/homepage/assets/img/icons/handshake.svg\"")
-            .create_on(&srv);
+        let mock = srv.mock(|when, then|{
+            when.method(GET)
+                .path("/some-path");
+            then.status(200)
+                .body("\"http://defintely.not.a.thing.probably.com/homepage/assets/img/icons/handshake.svg\"");
+        });
 
         let client = Client::new();
         let url = Url::parse(&srv.url("/some-path")).unwrap();
@@ -263,7 +411,30 @@ mod tests {
 
         assert!(links.is_empty());
 
-        assert_eq!(mock.times_called(), 1);
+        assert_eq!(mock.hits(), 1);
         Ok(())
     }
+
+    #[tokio::test(core_threads = 1)]
+    /// test that /robots.txt is correctly requested given a base url (happy path)
+    async fn request_robots_txt_with_and_without_proxy() {
+        let srv = MockServer::start();
+
+        let mock = srv.mock(|when, then| {
+            when.method(GET).path("/robots.txt");
+            then.status(200).body("this is a test");
+        });
+
+        let mut config = Configuration::default();
+
+        request_robots_txt(&srv.url("/api/users/stuff/things"), &config).await;
+
+        // note: the proxy doesn't actually do anything other than hit a different code branch
+        // in this unit test; it would however have an effect on an integration test
+        config.proxy = srv.url("/ima-proxy");
+
+        request_robots_txt(&srv.url("/api/different/path"), &config).await;
+
+        assert_eq!(mock.hits(), 2);
+    }
 }

src/filters.rs

@@ -1,6 +1,8 @@
 use crate::config::CONFIGURATION;
 use crate::utils::get_url_path_length;
-use crate::FeroxResponse;
+use crate::{FeroxResponse, FeroxSerialize};
+use fuzzyhash::FuzzyHash;
+use regex::Regex;
 use std::any::Any;
 use std::fmt::Debug;
 
@@ -237,9 +239,92 @@ impl FeroxFilter for SizeFilter {
     }
 }
 
+/// Simple implementor of FeroxFilter; used to filter out responses based on a given regular
+/// expression; specified using -X|--filter-regex
+#[derive(Debug)]
+pub struct RegexFilter {
+    /// Regular expression to be applied to the response body for filtering, compiled
+    pub compiled: Regex,
+
+    /// Regular expression as passed in on the command line, not compiled
+    pub raw_string: String,
+}
+
+/// implementation of FeroxFilter for RegexFilter
+impl FeroxFilter for RegexFilter {
+    /// Check `expression` against the response body, if the expression matches, the response
+    /// should be filtered out
+    fn should_filter_response(&self, response: &FeroxResponse) -> bool {
+        log::trace!("enter: should_filter_response({:?} {})", self, response);
+
+        let result = self.compiled.is_match(response.text());
+
+        log::trace!("exit: should_filter_response -> {}", result);
+
+        result
+    }
+
+    /// Compare one SizeFilter to another
+    fn box_eq(&self, other: &dyn Any) -> bool {
+        other.downcast_ref::<Self>().map_or(false, |a| self == a)
+    }
+
+    /// Return self as Any for dynamic dispatch purposes
+    fn as_any(&self) -> &dyn Any {
+        self
+    }
+}
+
+/// PartialEq implementation for RegexFilter
+impl PartialEq for RegexFilter {
+    /// Simple comparison of the raw string passed in via the command line
+    fn eq(&self, other: &RegexFilter) -> bool {
+        self.raw_string == other.raw_string
+    }
+}
+
+/// Simple implementor of FeroxFilter; used to filter out responses based on the similarity of a
+/// Response body with a known response; specified using --filter-similar-to
+#[derive(Default, Debug, PartialEq)]
+pub struct SimilarityFilter {
+    /// Response's body to be used for comparison for similarity
+    pub text: String,
+
+    /// Percentage of similarity at which a page is determined to be a near-duplicate of another
+    pub threshold: u32,
+}
+
+/// implementation of FeroxFilter for SimilarityFilter
+impl FeroxFilter for SimilarityFilter {
+    /// Check `FeroxResponse::text` against what was requested from the site passed in via
+    /// --filter-similar-to
+    fn should_filter_response(&self, response: &FeroxResponse) -> bool {
+        let other = FuzzyHash::new(&response.text);
+
+        if let Ok(result) = FuzzyHash::compare(&self.text, &other.to_string()) {
+            return result >= self.threshold;
+        }
+
+        // couldn't hash the response, don't filter
+        log::warn!("Could not hash body from {}", response.as_str());
+        false
+    }
+
+    /// Compare one SimilarityFilter to another
+    fn box_eq(&self, other: &dyn Any) -> bool {
+        other.downcast_ref::<Self>().map_or(false, |a| self == a)
+    }
+
+    /// Return self as Any for dynamic dispatch purposes
+    fn as_any(&self) -> &dyn Any {
+        self
+    }
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
+    use reqwest::Url;
 
     #[test]
     /// just a simple test to increase code coverage by hitting as_any and the inner value
@@ -288,4 +373,141 @@ mod tests {
             filter
         );
     }
+
+    #[test]
+    /// just a simple test to increase code coverage by hitting as_any and the inner value
+    fn regex_filter_as_any() {
+        let raw = r".*\.txt$";
+        let compiled = Regex::new(raw).unwrap();
+        let filter = RegexFilter {
+            compiled,
+            raw_string: raw.to_string(),
+        };
+
+        assert_eq!(filter.raw_string, r".*\.txt$");
+        assert_eq!(
+            *filter.as_any().downcast_ref::<RegexFilter>().unwrap(),
+            filter
+        );
+    }
+
+    #[test]
+    /// test should_filter on WilcardFilter where static logic matches
+    fn wildcard_should_filter_when_static_wildcard_found() {
+        let resp = FeroxResponse {
+            text: String::new(),
+            wildcard: true,
+            url: Url::parse("http://localhost").unwrap(),
+            content_length: 100,
+            word_count: 50,
+            line_count: 25,
+            headers: reqwest::header::HeaderMap::new(),
+            status: reqwest::StatusCode::OK,
+        };
+
+        let filter = WildcardFilter {
+            size: 100,
+            dynamic: 0,
+        };
+
+        assert!(filter.should_filter_response(&resp));
+    }
+
+    #[test]
+    /// test should_filter on WilcardFilter where dynamic logic matches
+    fn wildcard_should_filter_when_dynamic_wildcard_found() {
+        let resp = FeroxResponse {
+            text: String::new(),
+            wildcard: true,
+            url: Url::parse("http://localhost/stuff").unwrap(),
+            content_length: 100,
+            word_count: 50,
+            line_count: 25,
+            headers: reqwest::header::HeaderMap::new(),
+            status: reqwest::StatusCode::OK,
+        };
+
+        let filter = WildcardFilter {
+            size: 0,
+            dynamic: 95,
+        };
+
+        assert!(filter.should_filter_response(&resp));
+    }
+
+    #[test]
+    /// test should_filter on RegexFilter where regex matches body
+    fn regexfilter_should_filter_when_regex_matches_on_response_body() {
+        let resp = FeroxResponse {
+            text: String::from("im a body response hurr durr!"),
+            wildcard: false,
+            url: Url::parse("http://localhost/stuff").unwrap(),
+            content_length: 100,
+            word_count: 50,
+            line_count: 25,
+            headers: reqwest::header::HeaderMap::new(),
+            status: reqwest::StatusCode::OK,
+        };
+
+        let raw = r"response...rr";
+
+        let filter = RegexFilter {
+            raw_string: raw.to_string(),
+            compiled: Regex::new(raw).unwrap(),
+        };
+
+        assert!(filter.should_filter_response(&resp));
+    }
+
+    #[test]
+    /// a few simple tests for similarity filter
+    fn similarity_filter_is_accurate() {
+        let mut resp = FeroxResponse {
+            text: String::from("sitting"),
+            wildcard: false,
+            url: Url::parse("http://localhost/stuff").unwrap(),
+            content_length: 100,
+            word_count: 50,
+            line_count: 25,
+            headers: reqwest::header::HeaderMap::new(),
+            status: reqwest::StatusCode::OK,
+        };
+
+        let mut filter = SimilarityFilter {
+            text: FuzzyHash::new("kitten").to_string(),
+            threshold: 95,
+        };
+
+        // kitten/sitting is 57% similar, so a threshold of 95 should not be filtered
+        assert!(!filter.should_filter_response(&resp));
+
+        resp.text = String::new();
+        filter.text = String::new();
+        filter.threshold = 100;
+
+        // two empty strings are the same, however ssdeep doesn't accept empty strings, expect false
+        assert!(!filter.should_filter_response(&resp));
+
+        resp.text = String::from("some data to hash for the purposes of running a test");
+        filter.text =
+            FuzzyHash::new("some data to hash for the purposes of running a te").to_string();
+        filter.threshold = 17;
+
+        assert!(filter.should_filter_response(&resp));
+    }
+
+    #[test]
+    /// just a simple test to increase code coverage by hitting as_any and the inner value
+    fn similarity_filter_as_any() {
+        let filter = SimilarityFilter {
+            text: String::from("stuff"),
+            threshold: 95,
+        };
+
+        assert_eq!(filter.text, "stuff");
+        assert_eq!(
+            *filter.as_any().downcast_ref::<SimilarityFilter>().unwrap(),
+            filter
+        );
+    }
 }

src/heuristics.rs

@@ -2,10 +2,7 @@ use crate::{
     config::{CONFIGURATION, PROGRESS_PRINTER},
     filters::WildcardFilter,
     scanner::should_filter_response,
-    utils::{
-        ferox_print, format_url, get_url_path_length, make_request, module_colorizer,
-        status_colorizer,
-    },
+    utils::{ferox_print, format_url, get_url_path_length, make_request, status_colorizer},
     FeroxResponse,
 };
 use console::style;
@@ -42,13 +39,13 @@ fn unique_string(length: usize) -> String {
 pub async fn wildcard_test(
     target_url: &str,
     bar: ProgressBar,
-    tx_file: UnboundedSender<String>,
+    tx_term: UnboundedSender<FeroxResponse>,
 ) -> Option<WildcardFilter> {
     log::trace!(
         "enter: wildcard_test({:?}, {:?}, {:?})",
         target_url,
         bar,
-        tx_file
+        tx_term
     );
 
     if CONFIGURATION.dont_filter {
@@ -57,10 +54,10 @@ pub async fn wildcard_test(
         return None;
     }
 
-    let clone_req_one = tx_file.clone();
-    let clone_req_two = tx_file.clone();
+    let tx_clone_one = tx_term.clone();
+    let tx_clone_two = tx_term.clone();
 
-    if let Some(ferox_response) = make_wildcard_request(&target_url, 1, clone_req_one).await {
+    if let Some(ferox_response) = make_wildcard_request(&target_url, 1, tx_clone_one).await {
         bar.inc(1);
 
         // found a wildcard response
@@ -75,7 +72,7 @@ pub async fn wildcard_test(
 
         // content length of wildcard is non-zero, perform additional tests:
         //   make a second request, with a known-sized (64) longer request
-        if let Some(resp_two) = make_wildcard_request(&target_url, 3, clone_req_two).await {
+        if let Some(resp_two) = make_wildcard_request(&target_url, 3, tx_clone_two).await {
             bar.inc(1);
 
             let wc2_length = resp_two.content_length();
@@ -89,46 +86,34 @@ pub async fn wildcard_test(
 
                 if !CONFIGURATION.quiet {
                     let msg = format!(
-                            "{} {:>8}l {:>8}w {:>8}c Wildcard response is dynamic; {} ({} + url length) responses; toggle this behavior by using {}\n",
+                            "{} {:>9} {:>9} {:>9} Wildcard response is dynamic; {} ({} + url length) responses; toggle this behavior by using {}\n",
                             status_colorizer("WLD"),
-                            ferox_response.line_count(),
-                            ferox_response.word_count(),
-                            wildcard.dynamic,
+                            "-",
+                            "-",
+                            "-",
                             style("auto-filtering").yellow(),
                             style(wc_length - url_len).cyan(),
                             style("--dont-filter").yellow()
-                        );
+                    );
 
                     ferox_print(&msg, &PROGRESS_PRINTER);
-
-                    try_send_message_to_file(
-                        &msg,
-                        tx_file.clone(),
-                        !CONFIGURATION.output.is_empty(),
-                    );
                 }
             } else if wc_length == wc2_length {
                 wildcard.size = wc_length;
 
                 if !CONFIGURATION.quiet {
                     let msg = format!(
-                        "{} {:>8}l {:>8}w {:>8}c Wildcard response is static; {} {} responses; toggle this behavior by using {}\n",
+                        "{} {:>9} {:>9} {:>9} Wildcard response is static; {} {} responses; toggle this behavior by using {}\n",
                         status_colorizer("WLD"),
-                        ferox_response.line_count(),
-                        ferox_response.word_count(),
-                        wc_length,
+                        "-",
+                        "-",
+                        "-",
                         style("auto-filtering").yellow(),
                         style(wc_length).cyan(),
                         style("--dont-filter").yellow()
                     );
 
                     ferox_print(&msg, &PROGRESS_PRINTER);
-
-                    try_send_message_to_file(
-                        &msg,
-                        tx_file.clone(),
-                        !CONFIGURATION.output.is_empty(),
-                    );
                 }
             }
         } else {
@@ -152,7 +137,7 @@ pub async fn wildcard_test(
 async fn make_wildcard_request(
     target_url: &str,
     length: usize,
-    tx_file: UnboundedSender<String>,
+    tx_file: UnboundedSender<FeroxResponse>,
 ) -> Option<FeroxResponse> {
     log::trace!(
         "enter: make_wildcard_request({}, {}, {:?})",
@@ -178,8 +163,6 @@ async fn make_wildcard_request(
         }
     };
 
-    let wildcard = status_colorizer("WLD");
-
     match make_request(&CONFIGURATION.client, &nonexistent.to_owned()).await {
         Ok(response) => {
             if CONFIGURATION
@@ -187,58 +170,16 @@ async fn make_wildcard_request(
                 .contains(&response.status().as_u16())
             {
                 // found a wildcard response
-                let ferox_response = FeroxResponse::from(response, true).await;
-                let url_len = get_url_path_length(&ferox_response.url());
-                let content_len = ferox_response.content_length();
-                let content_words = ferox_response.word_count();
-                let content_lines = ferox_response.line_count();
+                let mut ferox_response = FeroxResponse::from(response, true).await;
+                ferox_response.wildcard = true;
 
-                if !CONFIGURATION.quiet && !should_filter_response(&ferox_response) {
-                    let msg = format!(
-                        "{} {:>8}l {:>8}w {:>8}c Got {} for {} (url length: {})\n",
-                        wildcard,
-                        content_lines,
-                        content_words,
-                        content_len,
-                        status_colorizer(&ferox_response.status().as_str()),
-                        ferox_response.url(),
-                        url_len
-                    );
-
-                    ferox_print(&msg, &PROGRESS_PRINTER);
-
-                    try_send_message_to_file(
-                        &msg,
-                        tx_file.clone(),
-                        !CONFIGURATION.output.is_empty(),
-                    );
+                if !CONFIGURATION.quiet
+                    && !should_filter_response(&ferox_response)
+                    && tx_file.send(ferox_response.clone()).is_err()
+                {
+                    return None;
                 }
 
-                if ferox_response.status().is_redirection() {
-                    // show where it goes, if possible
-                    if let Some(next_loc) = ferox_response.headers().get("Location") {
-                        let next_loc_str = next_loc.to_str().unwrap_or("Unknown");
-                        if !CONFIGURATION.quiet && !should_filter_response(&ferox_response) {
-                            let msg = format!(
-                                "{} {:>8}l {:>8}w {:>8}c {} redirects to => {}\n",
-                                wildcard,
-                                content_lines,
-                                content_words,
-                                content_len,
-                                ferox_response.url(),
-                                next_loc_str
-                            );
-
-                            ferox_print(&msg, &PROGRESS_PRINTER);
-
-                            try_send_message_to_file(
-                                &msg,
-                                tx_file.clone(),
-                                !CONFIGURATION.output.is_empty(),
-                            );
-                        }
-                    }
-                }
                 log::trace!("exit: make_wildcard_request -> {}", ferox_response);
                 return Some(ferox_response);
             }
@@ -303,35 +244,9 @@ pub async fn connectivity_test(target_urls: &[String]) -> Vec<String> {
     good_urls
 }
 
-/// simple helper to keep DRY; sends a message using the transmitter side of the given mpsc channel
-/// the receiver is expected to be the side that saves the message to CONFIGURATION.output.
-fn try_send_message_to_file(msg: &str, tx_file: UnboundedSender<String>, save_output: bool) {
-    log::trace!("enter: try_send_message_to_file({}, {:?})", msg, tx_file);
-
-    if save_output {
-        match tx_file.send(msg.to_string()) {
-            Ok(_) => {
-                log::trace!(
-                    "sent message from heuristics::try_send_message_to_file to file handler"
-                );
-            }
-            Err(e) => {
-                log::error!(
-                    "{} {}",
-                    module_colorizer("heuristics::try_send_message_to_file"),
-                    e
-                );
-            }
-        }
-    }
-    log::trace!("exit: try_send_message_to_file");
-}
-
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::FeroxChannel;
-    use tokio::sync::mpsc;
 
     #[test]
     /// request a unique string of 32bytes * a value returns correct result
@@ -348,41 +263,4 @@ mod tests {
         assert_eq!(wcf.size, 0);
         assert_eq!(wcf.dynamic, 0);
     }
-
-    #[tokio::test(core_threads = 1)]
-    /// tests that given a message and transmitter, the function sends the message across the
-    /// channel
-    async fn heuristics_try_send_message_to_file_sends_when_true() {
-        let (tx, mut rx): FeroxChannel<String> = mpsc::unbounded_channel();
-        let msg = "It really tied the room together.";
-        let should_save = true;
-        try_send_message_to_file(&msg, tx, should_save);
-
-        assert_eq!(rx.recv().await.unwrap(), msg);
-    }
-
-    #[tokio::test(core_threads = 1)]
-    #[should_panic]
-    /// tests that when save_output is false, nothing is sent to the receiver
-    async fn heuristics_try_send_message_to_file_sends_when_false() {
-        let (tx, mut rx): FeroxChannel<String> = mpsc::unbounded_channel();
-        let msg = "I'm the Dude, so that's what you call me.";
-        let should_save = false;
-        try_send_message_to_file(&msg, tx, should_save);
-
-        assert_ne!(rx.recv().await.unwrap(), msg);
-    }
-
-    #[tokio::test(core_threads = 1)]
-    /// tests that when save_output is true, but the receiver is closed, nothing is sent to the receiver
-    /// this test doesn't assert anything, but reaches the error block of the given function and
-    /// can be verified with --nocapture and RUST_LOG being set
-    async fn heuristics_try_send_message_to_file_sends_with_closed_receiver() {
-        env_logger::init();
-        let (tx, mut rx): FeroxChannel<String> = mpsc::unbounded_channel();
-        let msg = "Hey, nice marmot.";
-        let should_save = true;
-        rx.close();
-        try_send_message_to_file(&msg, tx, should_save);
-    }
 }

src/lib.rs

@@ -12,7 +12,15 @@ pub mod scan_manager;
 pub mod scanner;
 pub mod utils;
 
+use crate::utils::{get_url_path_length, status_colorizer};
+use console::{style, Color};
+use reqwest::header::{HeaderName, HeaderValue};
 use reqwest::{header::HeaderMap, Response, StatusCode, Url};
+use serde::{ser::SerializeStruct, Deserialize, Deserializer, Serialize, Serializer};
+use serde_json::Value;
+use std::collections::HashMap;
+use std::convert::{TryFrom, TryInto};
+use std::str::FromStr;
 use std::{error, fmt};
 use tokio::sync::mpsc::{UnboundedReceiver, UnboundedSender};
 
@@ -43,6 +51,9 @@ pub const VERSION: &str = env!("CARGO_PKG_VERSION");
 /// Maximum number of file descriptors that can be opened during a scan
 pub const DEFAULT_OPEN_FILE_LIMIT: usize = 8192;
 
+/// Default value used to determine near-duplicate web pages (equivalent to 95%)
+pub const SIMILARITY_THRESHOLD: u32 = 95;
+
 /// Default wordlist to use when `-w|--wordlist` isn't specified and not `wordlist` isn't set
 /// in a [ferox-config.toml](constant.DEFAULT_CONFIG_NAME.html) config file.
 ///
@@ -82,6 +93,17 @@ pub const DEFAULT_STATUS_CODES: [StatusCode; 9] = [
 /// Expected location is in the same directory as the feroxbuster binary.
 pub const DEFAULT_CONFIG_NAME: &str = "ferox-config.toml";
 
+/// FeroxSerialize trait; represents different types that are Serialize and also implement
+/// as_str / as_json methods
+pub trait FeroxSerialize: Serialize {
+    /// Return a String representation of the object, generally the human readable version of the
+    /// implementor
+    fn as_str(&self) -> String;
+
+    /// Return an NDJSON representation of the object
+    fn as_json(&self) -> String;
+}
+
 /// A `FeroxResponse`, derived from a `Response` to a submitted `Request`
 #[derive(Debug, Clone)]
 pub struct FeroxResponse {
@@ -97,8 +119,17 @@ pub struct FeroxResponse {
     /// The content-length of this response, if known
     content_length: u64,
 
+    /// The number of lines contained in the body of this response, if known
+    line_count: usize,
+
+    /// The number of words contained in the body of this response, if known
+    word_count: usize,
+
     /// The `Headers` of this `FeroxResponse`
     headers: HeaderMap,
+
+    /// Wildcard response status
+    wildcard: bool,
 }
 
 /// Implement Display for FeroxResponse
@@ -176,15 +207,12 @@ impl FeroxResponse {
 
     /// Returns line count of the response text.
     pub fn line_count(&self) -> usize {
-        self.text().lines().count()
+        self.line_count
     }
 
     /// Returns word count of the response text.
     pub fn word_count(&self) -> usize {
-        self.text()
-            .lines()
-            .map(|s| s.split_whitespace().count())
-            .sum()
+        self.word_count
     }
 
     /// Create a new `FeroxResponse` from the given `Response`
@@ -210,16 +238,298 @@ impl FeroxResponse {
             String::new()
         };
 
+        let line_count = text.lines().count();
+        let word_count = text.lines().map(|s| s.split_whitespace().count()).sum();
+
         FeroxResponse {
             url,
             status,
             content_length,
             text,
             headers,
+            line_count,
+            word_count,
+            wildcard: false,
         }
     }
 }
 
+/// Implement FeroxSerialusize::from(ize for FeroxRespons)e
+impl FeroxSerialize for FeroxResponse {
+    /// Simple wrapper around create_report_string
+    fn as_str(&self) -> String {
+        let lines = self.line_count().to_string();
+        let words = self.word_count().to_string();
+        let chars = self.content_length().to_string();
+        let status = self.status().as_str();
+        let wild_status = status_colorizer("WLD");
+
+        if self.wildcard {
+            // response is a wildcard, special messages abound when this is the case...
+
+            // create the base message
+            let mut message = format!(
+                "{} {:>8}l {:>8}w {:>8}c Got {} for {} (url length: {})\n",
+                wild_status,
+                lines,
+                words,
+                chars,
+                status_colorizer(&status),
+                self.url(),
+                get_url_path_length(&self.url())
+            );
+
+            if self.status().is_redirection() {
+                // when it's a redirect, show where it goes, if possible
+                if let Some(next_loc) = self.headers().get("Location") {
+                    let next_loc_str = next_loc.to_str().unwrap_or("Unknown");
+
+                    let redirect_msg = format!(
+                        "{} {:>9} {:>9} {:>9} {} redirects to => {}\n",
+                        wild_status,
+                        "-",
+                        "-",
+                        "-",
+                        self.url(),
+                        next_loc_str
+                    );
+
+                    message.push_str(&redirect_msg);
+                }
+            }
+
+            // base message + redirection message (if appropriate)
+            message
+        } else {
+            // not a wildcard, just create a normal entry
+            utils::create_report_string(
+                self.status.as_str(),
+                &lines,
+                &words,
+                &chars,
+                self.url().as_str(),
+            )
+        }
+    }
+
+    /// Create an NDJSON representation of the FeroxResponse
+    ///
+    /// (expanded for clarity)
+    /// ex:
+    /// {
+    ///    "type":"response",
+    ///    "url":"https://localhost.com/images",
+    ///    "path":"/images",
+    ///    "status":301,
+    ///    "content_length":179,
+    ///    "line_count":10,
+    ///    "word_count":16,
+    ///    "headers":{
+    ///       "x-content-type-options":"nosniff",
+    ///       "strict-transport-security":"max-age=31536000; includeSubDomains",
+    ///       "x-frame-options":"SAMEORIGIN",
+    ///       "connection":"keep-alive",
+    ///       "server":"nginx/1.16.1",
+    ///       "content-type":"text/html; charset=UTF-8",
+    ///       "referrer-policy":"origin-when-cross-origin",
+    ///       "content-security-policy":"default-src 'none'",
+    ///       "access-control-allow-headers":"X-Requested-With",
+    ///       "x-xss-protection":"1; mode=block",
+    ///       "content-length":"179",
+    ///       "date":"Mon, 23 Nov 2020 15:33:24 GMT",
+    ///       "location":"/images/",
+    ///       "access-control-allow-origin":"https://localhost.com"
+    ///    }
+    /// }\n
+    fn as_json(&self) -> String {
+        if let Ok(mut json) = serde_json::to_string(&self) {
+            json.push('\n');
+            json
+        } else {
+            format!("{{\"error\":\"could not convert {} to json\"}}", self.url())
+        }
+    }
+}
+
+/// Serialize implementation for FeroxResponse
+impl Serialize for FeroxResponse {
+    /// Function that handles serialization of a FeroxResponse to NDJSON
+    fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
+    where
+        S: Serializer,
+    {
+        let mut headers = HashMap::new();
+        let mut state = serializer.serialize_struct("FeroxResponse", 7)?;
+
+        // need to convert the HeaderMap to a HashMap in order to pass it to the serializer
+        for (key, value) in &self.headers {
+            let k = key.as_str().to_owned();
+            let v = String::from_utf8_lossy(value.as_bytes());
+            headers.insert(k, v);
+        }
+
+        state.serialize_field("type", "response")?;
+        state.serialize_field("url", self.url.as_str())?;
+        state.serialize_field("path", self.url.path())?;
+        state.serialize_field("wildcard", &self.wildcard)?;
+        state.serialize_field("status", &self.status.as_u16())?;
+        state.serialize_field("content_length", &self.content_length)?;
+        state.serialize_field("line_count", &self.line_count)?;
+        state.serialize_field("word_count", &self.word_count)?;
+        state.serialize_field("headers", &headers)?;
+
+        state.end()
+    }
+}
+
+/// Deserialize implementation for FeroxResponse
+impl<'de> Deserialize<'de> for FeroxResponse {
+    /// Deserialize a FeroxResponse from a serde_json::Value
+    fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
+    where
+        D: Deserializer<'de>,
+    {
+        let mut response = Self {
+            url: Url::parse("http://localhost").unwrap(),
+            status: StatusCode::OK,
+            text: String::new(),
+            content_length: 0,
+            headers: HeaderMap::new(),
+            wildcard: false,
+            line_count: 0,
+            word_count: 0,
+        };
+
+        let map: HashMap<String, Value> = HashMap::deserialize(deserializer)?;
+
+        for (key, value) in &map {
+            match key.as_str() {
+                "url" => {
+                    if let Some(url) = value.as_str() {
+                        if let Ok(parsed) = Url::parse(url) {
+                            response.url = parsed;
+                        }
+                    }
+                }
+                "status" => {
+                    if let Some(num) = value.as_u64() {
+                        if let Ok(smaller) = u16::try_from(num) {
+                            if let Ok(status) = StatusCode::from_u16(smaller) {
+                                response.status = status;
+                            }
+                        }
+                    }
+                }
+                "content_length" => {
+                    if let Some(num) = value.as_u64() {
+                        response.content_length = num;
+                    }
+                }
+                "line_count" => {
+                    if let Some(num) = value.as_u64() {
+                        response.line_count = num.try_into().unwrap_or_default();
+                    }
+                }
+                "word_count" => {
+                    if let Some(num) = value.as_u64() {
+                        response.word_count = num.try_into().unwrap_or_default();
+                    }
+                }
+                "headers" => {
+                    let mut headers = HeaderMap::<HeaderValue>::default();
+
+                    if let Some(map_headers) = value.as_object() {
+                        for (h_key, h_value) in map_headers {
+                            let h_value_str = h_value.as_str().unwrap_or("");
+                            let h_name = HeaderName::from_str(h_key)
+                                .unwrap_or_else(|_| HeaderName::from_str("Unknown").unwrap());
+                            let h_value_parsed = HeaderValue::from_str(h_value_str)
+                                .unwrap_or_else(|_| HeaderValue::from_str("Unknown").unwrap());
+                            headers.insert(h_name, h_value_parsed);
+                        }
+                    }
+
+                    response.headers = headers;
+                }
+                "wildcard" => {
+                    if let Some(result) = value.as_bool() {
+                        response.wildcard = result;
+                    }
+                }
+                _ => {}
+            }
+        }
+
+        Ok(response)
+    }
+}
+
+#[derive(Serialize, Deserialize, Default)]
+/// Representation of a log entry, can be represented as a human readable string or JSON
+pub struct FeroxMessage {
+    #[serde(rename = "type")]
+    /// Name of this type of struct, used for serialization, i.e. `{"type":"log"}`
+    kind: String,
+
+    /// The log message
+    pub message: String,
+
+    /// The log level
+    pub level: String,
+
+    /// The number of seconds elapsed since the scan started
+    pub time_offset: f32,
+
+    /// The module from which log::* was called
+    pub module: String,
+}
+
+/// Implementation of FeroxMessage
+impl FeroxSerialize for FeroxMessage {
+    /// Create an NDJSON representation of the log message
+    ///
+    /// (expanded for clarity)
+    /// ex:
+    /// {
+    ///   "type": "log",
+    ///   "message": "Sent https://localhost/api to file handler",
+    ///   "level": "DEBUG",
+    ///   "time_offset": 0.86333454,
+    ///   "module": "feroxbuster::reporter"
+    /// }\n
+    fn as_json(&self) -> String {
+        if let Ok(mut json) = serde_json::to_string(&self) {
+            json.push('\n');
+            json
+        } else {
+            String::from("{\"error\":\"could not convert to json\"}")
+        }
+    }
+
+    /// Create a string representation of the log message
+    ///
+    /// ex:  301       10l       16w      173c https://localhost/api
+    fn as_str(&self) -> String {
+        let (level_name, level_color) = match self.level.as_str() {
+            "ERROR" => ("ERR", Color::Red),
+            "WARN" => ("WRN", Color::Red),
+            "INFO" => ("INF", Color::Cyan),
+            "DEBUG" => ("DBG", Color::Yellow),
+            "TRACE" => ("TRC", Color::Magenta),
+            "WILDCARD" => ("WLD", Color::Cyan),
+            _ => ("UNK", Color::White),
+        };
+
+        format!(
+            "{} {:10.03} {} {}\n",
+            style(level_name).bg(level_color).black(),
+            style(self.time_offset).dim(),
+            self.module,
+            style(&self.message).dim(),
+        )
+    }
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
@@ -244,4 +554,46 @@ mod tests {
     fn default_version() {
         assert_eq!(VERSION, env!("CARGO_PKG_VERSION"));
     }
+
+    #[test]
+    /// test as_str method of FeroxMessage
+    fn ferox_message_as_str_returns_string_with_newline() {
+        let message = FeroxMessage {
+            message: "message".to_string(),
+            module: "utils".to_string(),
+            time_offset: 1.0,
+            level: "INFO".to_string(),
+            kind: "log".to_string(),
+        };
+        let message_str = message.as_str();
+
+        assert!(message_str.contains("INF"));
+        assert!(message_str.contains("1.000"));
+        assert!(message_str.contains("utils"));
+        assert!(message_str.contains("message"));
+        assert!(message_str.ends_with('\n'));
+    }
+
+    #[test]
+    /// test as_json method of FeroxMessage
+    fn ferox_message_as_json_returns_json_representation_of_ferox_message_with_newline() {
+        let message = FeroxMessage {
+            message: "message".to_string(),
+            module: "utils".to_string(),
+            time_offset: 1.0,
+            level: "INFO".to_string(),
+            kind: "log".to_string(),
+        };
+
+        let message_str = message.as_json();
+
+        let error_margin = f32::EPSILON;
+
+        let json: FeroxMessage = serde_json::from_str(&message_str).unwrap();
+        assert_eq!(json.module, message.module);
+        assert_eq!(json.message, message.message);
+        assert!((json.time_offset - message.time_offset).abs() < error_margin);
+        assert_eq!(json.level, message.level);
+        assert_eq!(json.kind, message.kind);
+    }
 }

src/logger.rs

@@ -1,6 +1,9 @@
-use crate::config::{CONFIGURATION, PROGRESS_PRINTER};
-use crate::reporter::{get_cached_file_handle, safe_file_write};
-use console::{style, Color};
+use crate::{
+    config::{CONFIGURATION, PROGRESS_PRINTER},
+    reporter::safe_file_write,
+    utils::open_file,
+    FeroxMessage, FeroxSerialize,
+};
 use env_logger::Builder;
 use std::env;
 use std::time::Instant;
@@ -28,44 +31,27 @@ pub fn initialize(verbosity: u8) {
     let start = Instant::now();
     let mut builder = Builder::from_default_env();
 
-    // I REALLY wanted the logger to also use the reporting channels found in the `reporter`
-    // module. However, in order to properly clean up the channels, all references to the
-    // transmitter side of a channel need to go out of scope, then you can await the future into
-    // which the receiver was moved.
-    //
-    // The problem was that putting a transmitter reference in this closure, which gets initialized
-    // as part of the global logger, made it so that I couldn't destroy/leak/take/swap the last
-    // reference to allow the channels to gracefully close.
-    //
-    // The workaround was to have a RwLock around the file and allow both the logger and the
-    // file handler to both write independent of each other.
-    let locked_file = get_cached_file_handle(&CONFIGURATION.output);
+    let debug_file = open_file(&CONFIGURATION.debug_log);
+
+    if let Some(buffered_file) = debug_file.clone() {
+        // write out the configuration to the debug file if it exists
+        safe_file_write(&*CONFIGURATION, buffered_file, CONFIGURATION.json);
+    }
 
     builder
         .format(move |_, record| {
-            let t = start.elapsed().as_secs_f32();
-            let level = record.level();
-
-            let (level_name, level_color) = match level {
-                log::Level::Error => ("ERR", Color::Red),
-                log::Level::Warn => ("WRN", Color::Red),
-                log::Level::Info => ("INF", Color::Cyan),
-                log::Level::Debug => ("DBG", Color::Yellow),
-                log::Level::Trace => ("TRC", Color::Magenta),
+            let log_entry = FeroxMessage {
+                message: record.args().to_string(),
+                level: record.level().to_string(),
+                time_offset: start.elapsed().as_secs_f32(),
+                module: record.target().to_string(),
+                kind: "log".to_string(),
             };
 
-            let msg = format!(
-                "{} {:10.03} {} {}\n",
-                style(level_name).bg(level_color).black(),
-                style(t).dim(),
-                record.target(),
-                style(record.args()).dim(),
-            );
+            PROGRESS_PRINTER.println(&log_entry.as_str());
 
-            PROGRESS_PRINTER.println(&msg);
-
-            if let Some(buffered_file) = locked_file.clone() {
-                safe_file_write(&msg, buffered_file);
+            if let Some(buffered_file) = debug_file.clone() {
+                safe_file_write(&log_entry, buffered_file, CONFIGURATION.json);
             }
 
             Ok(())

src/main.rs

@@ -2,15 +2,19 @@ use crossterm::event::{self, Event, KeyCode};
 use feroxbuster::{
     banner,
     config::{CONFIGURATION, PROGRESS_BAR, PROGRESS_PRINTER},
-    heuristics, logger, reporter,
-    scan_manager::PAUSE_SCAN,
-    scanner::{self, scan_url},
+    extractor::{extract_robots_txt, request_feroxresponse_from_new_link},
+    heuristics, logger,
+    progress::add_bar,
+    reporter,
+    scan_manager::{self, PAUSE_SCAN},
+    scanner::{self, scan_url, send_report, RESPONSES, SCANNED_URLS},
     utils::{ferox_print, get_current_depth, module_colorizer, status_colorizer},
-    FeroxError, FeroxResponse, FeroxResult, SLEEP_DURATION, VERSION,
+    FeroxError, FeroxResponse, FeroxResult, FeroxSerialize, SLEEP_DURATION, VERSION,
 };
 #[cfg(not(target_os = "windows"))]
 use feroxbuster::{utils::set_open_file_limit, DEFAULT_OPEN_FILE_LIMIT};
 use futures::StreamExt;
+use std::convert::TryInto;
 use std::{
     collections::HashSet,
     fs::File,
@@ -95,9 +99,9 @@ fn get_unique_words_from_wordlist(path: &str) -> FeroxResult<Arc<HashSet<String>
 
 /// Determine whether it's a single url scan or urls are coming from stdin, then scan as needed
 async fn scan(
-    targets: Vec<String>,
+    mut targets: Vec<String>,
     tx_term: UnboundedSender<FeroxResponse>,
-    tx_file: UnboundedSender<String>,
+    tx_file: UnboundedSender<FeroxResponse>,
 ) -> FeroxResult<()> {
     log::trace!("enter: scan({:?}, {:?}, {:?})", targets, tx_term, tx_file);
     // cloning an Arc is cheap (it's basically a pointer into the heap)
@@ -113,17 +117,66 @@ async fn scan(
         return Err(Box::new(err));
     }
 
-    scanner::initialize(
-        words.len(),
-        CONFIGURATION.scan_limit,
-        &CONFIGURATION.extensions,
-        &CONFIGURATION.filter_status,
-        &CONFIGURATION.filter_line_count,
-        &CONFIGURATION.filter_word_count,
-        &CONFIGURATION.filter_size,
-    );
+    scanner::initialize(words.len(), &CONFIGURATION).await;
+
+    if CONFIGURATION.resumed {
+        if let Ok(scans) = SCANNED_URLS.scans.lock() {
+            for scan in scans.iter() {
+                if let Ok(locked_scan) = scan.lock() {
+                    if locked_scan.complete {
+                        // these scans are complete, and just need to be shown to the user
+                        let pb = add_bar(
+                            &locked_scan.url,
+                            words.len().try_into().unwrap_or_default(),
+                            false,
+                            true,
+                        );
+                        pb.finish();
+                    }
+                }
+            }
+        }
+
+        if let Ok(responses) = RESPONSES.responses.read() {
+            for response in responses.iter() {
+                PROGRESS_PRINTER.println(response.as_str());
+            }
+        }
+    }
+
+    if CONFIGURATION.extract_links {
+        for target in targets.clone() {
+            // modifying the targets vector, so we can't have a reference to it while we borrow
+            // it as mutable; thus the clone
+            let robots_links = extract_robots_txt(&target, &CONFIGURATION).await;
+
+            for robot_link in robots_links {
+                // create a url based on the given command line options, continue on error
+                let ferox_response = match request_feroxresponse_from_new_link(&robot_link).await {
+                    Some(resp) => resp,
+                    None => continue,
+                };
+
+                if ferox_response.is_file() {
+                    SCANNED_URLS.add_file_scan(&robot_link);
+                    send_report(tx_term.clone(), ferox_response);
+                } else {
+                    let (unknown, _) = SCANNED_URLS.add_directory_scan(&robot_link);
+
+                    if !unknown {
+                        // known directory; can skip (unlikely)
+                        continue;
+                    }
+
+                    // unknown directory; add to targets for scanning
+                    targets.push(robot_link);
+                }
+            }
+        }
+    }
 
     let mut tasks = vec![];
+    let num_targets = targets.len();
 
     for target in targets {
         let word_clone = words.clone();
@@ -132,7 +185,15 @@ async fn scan(
 
         let task = tokio::spawn(async move {
             let base_depth = get_current_depth(&target);
-            scan_url(&target, word_clone, base_depth, term_clone, file_clone).await;
+            scan_url(
+                &target,
+                word_clone,
+                base_depth,
+                num_targets,
+                term_clone,
+                file_clone,
+            )
+            .await;
         });
 
         tasks.push(task);
@@ -160,6 +221,22 @@ async fn get_targets() -> FeroxResult<Vec<String>> {
         while let Some(line) = reader.next().await {
             targets.push(line?);
         }
+    } else if CONFIGURATION.resumed {
+        // resume-from can't be used with --url, and --stdin is marked false for every resumed
+        // scan, making it mutually exclusive from either of the other two options
+        if let Ok(scans) = SCANNED_URLS.scans.lock() {
+            for scan in scans.iter() {
+                // SCANNED_URLS gets deserialized scans added to it at program start if --resume-from
+                // is used, so scans that aren't marked complete still need to be scanned
+                if let Ok(locked_scan) = scan.lock() {
+                    if locked_scan.complete {
+                        // this one's already done, ignore it
+                        continue;
+                    }
+                    targets.push(locked_scan.url.to_owned());
+                }
+            }
+        }
     } else {
         targets.push(CONFIGURATION.target_url.clone());
     }
@@ -185,9 +262,16 @@ async fn wrapped_main() {
         PROGRESS_BAR.join().unwrap();
     });
 
+    if !CONFIGURATION.time_limit.is_empty() {
+        // --time-limit value not an empty string, need to kick off the thread that enforces
+        // the limit
+        tokio::spawn(async move {
+            scan_manager::start_max_time_thread(&CONFIGURATION.time_limit).await
+        });
+    }
+
     // can't trace main until after logger is initialized and the above task is started
     log::trace!("enter: main");
-    log::debug!("{:#?}", *CONFIGURATION);
 
     // spawn a thread that listens for keyboard input on stdin, when a user presses enter
     // the input handler will toggle PAUSE_SCAN, which in turn is used to pause and resume
@@ -249,7 +333,7 @@ async fn wrapped_main() {
 async fn clean_up(
     tx_term: UnboundedSender<FeroxResponse>,
     term_handle: JoinHandle<()>,
-    tx_file: UnboundedSender<String>,
+    tx_file: UnboundedSender<FeroxResponse>,
     file_handle: Option<JoinHandle<()>>,
     save_output: bool,
 ) {
@@ -307,6 +391,11 @@ fn main() {
     // setup logging based on the number of -v's used
     logger::initialize(CONFIGURATION.verbosity);
 
+    if CONFIGURATION.save_state {
+        // start the ctrl+c handler
+        scan_manager::initialize();
+    }
+
     // this function uses rlimit, which is not supported on windows
     #[cfg(not(target_os = "windows"))]
     set_open_file_limit(DEFAULT_OPEN_FILE_LIMIT);

src/parser.rs

@@ -1,10 +1,23 @@
-use crate::VERSION;
-use clap::{App, Arg};
+use clap::{App, Arg, ArgGroup};
+use lazy_static::lazy_static;
+use regex::Regex;
+
+lazy_static! {
+    /// Regex used to validate values passed to --time-limit
+    ///
+    /// Examples of expected values that will this regex will match:
+    /// - 30s
+    /// - 20m
+    /// - 1h
+    /// - 1d
+    pub static ref TIMESPEC_REGEX: Regex =
+        Regex::new(r"^(?i)(?P<n>\d+)(?P<m>[smdh])$").expect("Could not compile regex");
+}
 
 /// Create and return an instance of [clap::App](https://docs.rs/clap/latest/clap/struct.App.html), i.e. the Command Line Interface's configuration
 pub fn initialize() -> App<'static, 'static> {
     App::new("feroxbuster")
-        .version(VERSION)
+        .version(env!("CARGO_PKG_VERSION"))
         .author("Ben 'epi' Risher (@epi052)")
         .about("A fast, simple, recursive content discovery tool written in Rust")
         .arg(
@@ -19,7 +32,7 @@ pub fn initialize() -> App<'static, 'static> {
             Arg::with_name("url")
                 .short("u")
                 .long("url")
-                .required_unless("stdin")
+                .required_unless_one(&["stdin", "resume_from"])
                 .value_name("URL")
                 .multiple(true)
                 .use_delimiter(true)
@@ -64,7 +77,7 @@ pub fn initialize() -> App<'static, 'static> {
                 .takes_value(true)
                 .value_name("PROXY")
                 .help(
-                    "Proxy to use for requests (ex: http(s)://host:port, socks5://host:port)",
+                    "Proxy to use for requests (ex: http(s)://host:port, socks5(h)://host:port)",
                 ),
         )
         .arg(
@@ -109,6 +122,13 @@ pub fn initialize() -> App<'static, 'static> {
                 .takes_value(false)
                 .help("Only print URLs; Don't print status codes, response size, running config, etc...")
         )
+        .arg(
+            Arg::with_name("json")
+                .long("json")
+                .takes_value(false)
+                .requires("output_files")
+                .help("Emit JSON logs to --output and --debug-log instead of normal text")
+        )
         .arg(
             Arg::with_name("dont_filter")
                 .short("D")
@@ -121,7 +141,22 @@ pub fn initialize() -> App<'static, 'static> {
                 .short("o")
                 .long("output")
                 .value_name("FILE")
-                .help("Output file to write results to (default: stdout)")
+                .help("Output file to write results to (use w/ --json for JSON entries)")
+                .takes_value(true),
+        )
+        .arg(
+            Arg::with_name("resume_from")
+                .long("resume-from")
+                .value_name("STATE_FILE")
+                .help("State file from which to resume a partially complete scan (ex. --resume-from ferox-1606586780.state)")
+                .conflicts_with("url")
+                .takes_value(true),
+        )
+        .arg(
+            Arg::with_name("debug_log")
+                .long("debug-log")
+                .value_name("FILE")
+                .help("Output file to write log entries (use w/ --json for JSON entries)")
                 .takes_value(true),
         )
         .arg(
@@ -218,6 +253,18 @@ pub fn initialize() -> App<'static, 'static> {
                     "Filter out messages of a particular size (ex: -S 5120 -S 4927,1970)",
                 ),
         )
+        .arg(
+            Arg::with_name("filter_regex")
+                .short("X")
+                .long("filter-regex")
+                .value_name("REGEX")
+                .takes_value(true)
+                .multiple(true)
+                .use_delimiter(true)
+                .help(
+                    "Filter out messages via regular expression matching on the response's body (ex: -X '^ignore me$')",
+                ),
+        )
         .arg(
             Arg::with_name("filter_words")
                 .short("W")
@@ -254,6 +301,17 @@ pub fn initialize() -> App<'static, 'static> {
                     "Filter out status codes (deny list) (ex: -C 200 -C 401)",
                 ),
         )
+        .arg(
+            Arg::with_name("filter_similar")
+                .long("filter-similar-to")
+                .value_name("UNWANTED_PAGE")
+                .takes_value(true)
+                .multiple(true)
+                .use_delimiter(true)
+                .help(
+                    "Filter out pages that are similar to the given page (ex. --filter-similar-to http://site.xyz/soft404)",
+                ),
+        )
         .arg(
             Arg::with_name("extract_links")
                 .short("e")
@@ -269,6 +327,18 @@ pub fn initialize() -> App<'static, 'static> {
                 .takes_value(true)
                 .help("Limit total number of concurrent scans (default: 0, i.e. no limit)")
         )
+        .arg(
+            Arg::with_name("time_limit")
+                .long("time-limit")
+                .value_name("TIME_SPEC")
+                .takes_value(true)
+                .validator(valid_time_spec)
+                .help("Limit total run time of all scans (ex: --time-limit 10m)")
+        )
+        .group(ArgGroup::with_name("output_files")
+            .args(&["debug_log", "output"])
+            .multiple(true)
+        )
         .after_help(r#"NOTE:
     Options that take multiple values are very flexible.  Consider the following ways of specifying
     extensions:
@@ -306,6 +376,20 @@ EXAMPLES:
     "#)
 }
 
+/// Validate that a string is formatted as a number followed by s, m, h, or d (10d, 30s, etc...)
+fn valid_time_spec(time_spec: String) -> Result<(), String> {
+    match TIMESPEC_REGEX.is_match(&time_spec) {
+        true => Ok(()),
+        false => {
+            let msg = format!(
+                "Expected a non-negative, whole number followed by s, m, h, or d (case insensitive); received {}",
+                time_spec
+            );
+            Err(msg)
+        }
+    }
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
@@ -316,4 +400,37 @@ mod tests {
         let app = initialize();
         assert_eq!(app.get_name(), "feroxbuster");
     }
+
+    #[test]
+    /// sanity checks that valid_time_spec correctly checks and rejects a given string
+    ///
+    /// instead of having a bunch of single tests here, they're all quick and are mostly checking
+    /// that i didn't hose up the regex.  Going to consolidate them into a single test
+    fn validate_valid_time_spec_validation() {
+        let float_rejected = "1.4m";
+        assert!(valid_time_spec(float_rejected.into()).is_err());
+
+        let negative_rejected = "-1m";
+        assert!(valid_time_spec(negative_rejected.into()).is_err());
+
+        let only_number_rejected = "1";
+        assert!(valid_time_spec(only_number_rejected.into()).is_err());
+
+        let only_measurement_rejected = "m";
+        assert!(valid_time_spec(only_measurement_rejected.into()).is_err());
+
+        for accepted_measurement in &["s", "m", "h", "d", "S", "M", "H", "D"] {
+            // all upper/lowercase should be good
+            assert!(valid_time_spec(format!("1{}", *accepted_measurement)).is_ok());
+        }
+
+        let leading_space_rejected = " 14m";
+        assert!(valid_time_spec(leading_space_rejected.into()).is_err());
+
+        let trailing_space_rejected = "14m ";
+        assert!(valid_time_spec(trailing_space_rejected.into()).is_err());
+
+        let space_between_rejected = "1 4m";
+        assert!(valid_time_spec(space_between_rejected.into()).is_err());
+    }
 }

src/progress.rs

@@ -3,9 +3,16 @@ use indicatif::{ProgressBar, ProgressStyle};
 
 /// Add an [indicatif::ProgressBar](https://docs.rs/indicatif/latest/indicatif/struct.ProgressBar.html)
 /// to the global [PROGRESS_BAR](../config/struct.PROGRESS_BAR.html)
-pub fn add_bar(prefix: &str, length: u64, hidden: bool) -> ProgressBar {
+pub fn add_bar(prefix: &str, length: u64, hidden: bool, hide_per_sec: bool) -> ProgressBar {
     let style = if hidden || CONFIGURATION.quiet {
         ProgressStyle::default_bar().template("")
+    } else if hide_per_sec {
+        ProgressStyle::default_bar()
+            .template(&format!(
+                "[{{bar:.cyan/blue}}] - {{elapsed:<4}} {{pos:>7}}/{{len:7}} {:7} {{prefix}}",
+                "-"
+            ))
+            .progress_chars("#>-")
     } else {
         ProgressStyle::default_bar()
             .template("[{bar:.cyan/blue}] - {elapsed:<4} {pos:>7}/{len:7} {per_sec:7} {prefix}")
@@ -20,3 +27,24 @@ pub fn add_bar(prefix: &str, length: u64, hidden: bool) -> ProgressBar {
 
     progress_bar
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    /// hit all code branches for add_bar
+    fn add_bar_with_all_configurations() {
+        let p1 = add_bar("prefix", 2, true, false); // hidden
+        let p2 = add_bar("prefix", 2, false, true); // no per second field
+        let p3 = add_bar("prefix", 2, false, false); // normal bar
+
+        p1.finish();
+        p2.finish();
+        p3.finish();
+
+        assert!(p1.is_finished());
+        assert!(p2.is_finished());
+        assert!(p3.is_finished());
+    }
+}

src/reporter.rs

@@ -1,6 +1,9 @@
-use crate::config::{CONFIGURATION, PROGRESS_PRINTER};
-use crate::utils::{create_report_string, ferox_print, make_request};
-use crate::{FeroxChannel, FeroxResponse};
+use crate::{
+    config::{CONFIGURATION, PROGRESS_PRINTER},
+    scanner::RESPONSES,
+    utils::{ferox_print, make_request, open_file},
+    FeroxChannel, FeroxResponse, FeroxSerialize,
+};
 use console::strip_ansi_codes;
 use std::io::Write;
 use std::sync::{Arc, Once, RwLock};
@@ -41,14 +44,14 @@ pub fn initialize(
     save_output: bool,
 ) -> (
     UnboundedSender<FeroxResponse>,
-    UnboundedSender<String>,
+    UnboundedSender<FeroxResponse>,
     JoinHandle<()>,
     Option<JoinHandle<()>>,
 ) {
     log::trace!("enter: initialize({}, {})", output_file, save_output);
 
     let (tx_rpt, rx_rpt): FeroxChannel<FeroxResponse> = mpsc::unbounded_channel();
-    let (tx_file, rx_file): FeroxChannel<String> = mpsc::unbounded_channel();
+    let (tx_file, rx_file): FeroxChannel<FeroxResponse> = mpsc::unbounded_channel();
 
     let file_clone = tx_file.clone();
 
@@ -81,7 +84,7 @@ pub fn initialize(
 /// reporting criteria
 async fn spawn_terminal_reporter(
     mut resp_chan: UnboundedReceiver<FeroxResponse>,
-    file_chan: UnboundedSender<String>,
+    file_chan: UnboundedSender<FeroxResponse>,
     save_output: bool,
 ) {
     log::trace!(
@@ -91,24 +94,20 @@ async fn spawn_terminal_reporter(
         save_output
     );
 
-    while let Some(resp) = resp_chan.recv().await {
+    while let Some(mut resp) = resp_chan.recv().await {
         log::trace!("received {} on reporting channel", resp.url());
 
-        if CONFIGURATION.status_codes.contains(&resp.status().as_u16()) {
-            let report = create_report_string(
-                resp.status().as_str(),
-                &resp.line_count().to_string(),
-                &resp.word_count().to_string(),
-                &resp.content_length().to_string(),
-                &resp.url().to_string(),
-            );
+        let contains_sentry = CONFIGURATION.status_codes.contains(&resp.status().as_u16());
+        let unknown_sentry = !RESPONSES.contains(&resp); // !contains == unknown
+        let should_process_response = contains_sentry && unknown_sentry;
 
+        if should_process_response {
             // print to stdout
-            ferox_print(&report, &PROGRESS_PRINTER);
+            ferox_print(&resp.as_str(), &PROGRESS_PRINTER);
 
             if save_output {
                 // -o used, need to send the report to be written out to disk
-                match file_chan.send(report.to_string()) {
+                match file_chan.send(resp.clone()) {
                     Ok(_) => {
                         log::debug!("Sent {} to file handler", resp.url());
                     }
@@ -120,9 +119,7 @@ async fn spawn_terminal_reporter(
         }
         log::trace!("report complete: {}", resp.url());
 
-        if CONFIGURATION.replay_client.is_some()
-            && CONFIGURATION.replay_codes.contains(&resp.status().as_u16())
-        {
+        if CONFIGURATION.replay_client.is_some() && should_process_response {
             // replay proxy specified/client created and this response's status code is one that
             // should be replayed
             match make_request(CONFIGURATION.replay_client.as_ref().unwrap(), &resp.url()).await {
@@ -132,6 +129,18 @@ async fn spawn_terminal_reporter(
                 }
             }
         }
+
+        if should_process_response {
+            // add response to RESPONSES for serialization in case of ctrl+c
+            // placed all by its lonesome like this so that RESPONSES can take ownership
+            // of the FeroxResponse
+
+            // before ownership is transferred, there's no real reason to keep the body anymore
+            // so we can free that piece of data, reducing memory usage
+            resp.text = String::new();
+
+            RESPONSES.insert(resp);
+        }
     }
     log::trace!("exit: spawn_terminal_reporter");
 }
@@ -140,7 +149,10 @@ async fn spawn_terminal_reporter(
 ///
 /// The consumer simply receives responses and writes them to the given output file if they meet
 /// the given reporting criteria
-async fn spawn_file_reporter(mut report_channel: UnboundedReceiver<String>, output_file: &str) {
+async fn spawn_file_reporter(
+    mut report_channel: UnboundedReceiver<FeroxResponse>,
+    output_file: &str,
+) {
     let buffered_file = match get_cached_file_handle(&CONFIGURATION.output) {
         Some(file) => file,
         None => {
@@ -157,47 +169,33 @@ async fn spawn_file_reporter(mut report_channel: UnboundedReceiver<String>, outp
 
     log::info!("Writing scan results to {}", output_file);
 
-    while let Some(report) = report_channel.recv().await {
-        safe_file_write(&report, buffered_file.clone());
+    while let Some(response) = report_channel.recv().await {
+        safe_file_write(&response, buffered_file.clone(), CONFIGURATION.json);
     }
 
     log::trace!("exit: spawn_file_reporter");
 }
 
-/// Given the path to a file, open the file in append mode (create it if it doesn't exist) and
-/// return a reference to the file that is buffered and locked
-fn open_file(filename: &str) -> Option<Arc<RwLock<io::BufWriter<fs::File>>>> {
-    log::trace!("enter: open_file({})", filename);
-
-    match fs::OpenOptions::new() // std fs
-        .create(true)
-        .append(true)
-        .open(filename)
-    {
-        Ok(file) => {
-            let writer = io::BufWriter::new(file); // std io
-
-            let locked_file = Some(Arc::new(RwLock::new(writer)));
-
-            log::trace!("exit: open_file -> {:?}", locked_file);
-            locked_file
-        }
-        Err(e) => {
-            log::error!("{}", e);
-            log::trace!("exit: open_file -> None");
-            None
-        }
-    }
-}
-
 /// Given a string and a reference to a locked buffered file, write the contents and flush
 /// the buffer to disk.
-pub fn safe_file_write(contents: &str, locked_file: Arc<RwLock<io::BufWriter<fs::File>>>) {
+pub fn safe_file_write<T>(
+    value: &T,
+    locked_file: Arc<RwLock<io::BufWriter<fs::File>>>,
+    convert_to_json: bool,
+) where
+    T: FeroxSerialize,
+{
     // note to future self: adding logging of anything other than error to this function
     // is a bad idea. we call this function while processing records generated by the logger.
     // If we then call log::... while already processing some logging output, it results in
     // the second log entry being injected into the first.
 
+    let contents = if convert_to_json {
+        value.as_json()
+    } else {
+        value.as_str()
+    };
+
     let contents = strip_ansi_codes(&contents);
 
     if let Ok(mut handle) = locked_file.write() {

src/scan_manager.rs

@@ -1,11 +1,29 @@
-use crate::{config::PROGRESS_PRINTER, progress, scanner::NUMBER_OF_REQUESTS, SLEEP_DURATION};
+use crate::config::Configuration;
+use crate::reporter::safe_file_write;
+use crate::utils::open_file;
+use crate::{
+    config::{CONFIGURATION, PROGRESS_PRINTER},
+    parser::TIMESPEC_REGEX,
+    progress,
+    scanner::{NUMBER_OF_REQUESTS, RESPONSES, SCANNED_URLS},
+    FeroxResponse, FeroxSerialize, SLEEP_DURATION,
+};
 use console::style;
 use indicatif::{ProgressBar, ProgressStyle};
 use lazy_static::lazy_static;
+use serde::{
+    ser::{SerializeSeq, SerializeStruct},
+    Deserialize, Deserializer, Serialize, Serializer,
+};
+use serde_json::Value;
+use std::collections::HashMap;
 use std::{
     cmp::PartialEq,
     fmt,
+    fs::File,
+    io::BufReader,
     sync::{Arc, Mutex, RwLock},
+    time::{SystemTime, UNIX_EPOCH},
 };
 use std::{
     io::{stderr, Write},
@@ -28,12 +46,20 @@ static INTERACTIVE_BARRIER: AtomicUsize = AtomicUsize::new(0);
 pub static PAUSE_SCAN: AtomicBool = AtomicBool::new(false);
 
 /// Simple enum used to flag a `FeroxScan` as likely a directory or file
-#[derive(Debug)]
+#[derive(Debug, Serialize, Deserialize)]
 pub enum ScanType {
     File,
     Directory,
 }
 
+/// Default implementation for ScanType
+impl Default for ScanType {
+    /// Return ScanType::File as default
+    fn default() -> Self {
+        Self::File
+    }
+}
+
 /// Struct to hold scan-related state
 ///
 /// The purpose of this container is to open up the pathway to aborting currently running tasks and
@@ -59,17 +85,8 @@ pub struct FeroxScan {
     pub progress_bar: Option<ProgressBar>,
 }
 
-/// Implementation of FeroxScan
-impl FeroxScan {
-    /// Stop a currently running scan
-    pub fn abort(&self) {
-        self.stop_progress_bar();
-
-        if let Some(_task) = &self.task {
-            // task.abort();  todo uncomment once upgraded to tokio 0.3
-        }
-    }
-
+/// Default implementation for FeroxScan
+impl Default for FeroxScan {
     /// Create a default FeroxScan, populates ID with a new UUID
     fn default() -> Self {
         let new_id = Uuid::new_v4().to_simple().to_string();
@@ -83,6 +100,18 @@ impl FeroxScan {
             scan_type: ScanType::File,
         }
     }
+}
+
+/// Implementation of FeroxScan
+impl FeroxScan {
+    /// Stop a currently running scan
+    pub fn abort(&self) {
+        self.stop_progress_bar();
+
+        if let Some(_task) = &self.task {
+            // task.abort();  todo uncomment once upgraded to tokio 0.3 (issue #107)
+        }
+    }
 
     /// Simple helper to call .finish on the scan's progress bar
     fn stop_progress_bar(&self) {
@@ -97,7 +126,7 @@ impl FeroxScan {
             pb.clone()
         } else {
             let num_requests = NUMBER_OF_REQUESTS.load(Ordering::Relaxed);
-            let pb = progress::add_bar(&self.url, num_requests, false);
+            let pb = progress::add_bar(&self.url, num_requests, false, false);
 
             pb.reset_elapsed();
 
@@ -145,6 +174,69 @@ impl PartialEq for FeroxScan {
     }
 }
 
+/// Serialize implementation for FeroxScan
+impl Serialize for FeroxScan {
+    /// Function that handles serialization of a FeroxScan
+    fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
+    where
+        S: Serializer,
+    {
+        let mut state = serializer.serialize_struct("FeroxScan", 4)?;
+
+        state.serialize_field("id", &self.id)?;
+        state.serialize_field("url", &self.url)?;
+        state.serialize_field("scan_type", &self.scan_type)?;
+        state.serialize_field("complete", &self.complete)?;
+
+        state.end()
+    }
+}
+
+/// Deserialize implementation for FeroxScan
+impl<'de> Deserialize<'de> for FeroxScan {
+    /// Deserialize a FeroxScan from a serde_json::Value
+    fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
+    where
+        D: Deserializer<'de>,
+    {
+        let mut scan = Self::default();
+
+        let map: HashMap<String, Value> = HashMap::deserialize(deserializer)?;
+
+        for (key, value) in &map {
+            match key.as_str() {
+                "id" => {
+                    if let Some(id) = value.as_str() {
+                        scan.id = id.to_string();
+                    }
+                }
+                "scan_type" => {
+                    if let Some(scan_type) = value.as_str() {
+                        scan.scan_type = match scan_type {
+                            "File" => ScanType::File,
+                            "Directory" => ScanType::Directory,
+                            _ => ScanType::File,
+                        }
+                    }
+                }
+                "complete" => {
+                    if let Some(complete) = value.as_bool() {
+                        scan.complete = complete;
+                    }
+                }
+                "url" => {
+                    if let Some(url) = value.as_str() {
+                        scan.url = url.to_string();
+                    }
+                }
+                _ => {}
+            }
+        }
+
+        Ok(scan)
+    }
+}
+
 /// Container around a locked hashset of `FeroxScan`s, adds wrappers for insertion and searching
 #[derive(Debug, Default)]
 pub struct FeroxScans {
@@ -152,6 +244,31 @@ pub struct FeroxScans {
     pub scans: Mutex<Vec<Arc<Mutex<FeroxScan>>>>,
 }
 
+/// Serialize implementation for FeroxScans
+impl Serialize for FeroxScans {
+    /// Function that handles serialization of FeroxScans
+    fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
+    where
+        S: Serializer,
+    {
+        if let Ok(scans) = self.scans.lock() {
+            let mut seq = serializer.serialize_seq(Some(scans.len()))?;
+
+            for scan in scans.iter() {
+                if let Ok(unlocked) = scan.lock() {
+                    seq.serialize_element(&*unlocked)?;
+                }
+            }
+
+            seq.end()
+        } else {
+            // if for some reason we can't unlock the mutex, just write an empty list
+            let seq = serializer.serialize_seq(Some(0))?;
+            seq.end()
+        }
+    }
+}
+
 /// Implementation of `FeroxScans`
 impl FeroxScans {
     /// Add a `FeroxScan` to the internal container
@@ -271,8 +388,8 @@ impl FeroxScans {
 
                 let mut user_input = String::new();
                 std::io::stdin().read_line(&mut user_input).unwrap();
-                // todo actual logic for parsing user input in a way that allows for
-                // calling .abort on the scan retrieved based on the input (issue #107)
+                // todo (issue #107) actual logic for parsing user input in a way that allows for
+                // calling .abort on the scan retrieved based on the input
             }
         }
 
@@ -324,8 +441,12 @@ impl FeroxScans {
     fn add_scan(&self, url: &str, scan_type: ScanType) -> (bool, Arc<Mutex<FeroxScan>>) {
         let bar = match scan_type {
             ScanType::Directory => {
-                let progress_bar =
-                    progress::add_bar(&url, NUMBER_OF_REQUESTS.load(Ordering::Relaxed), false);
+                let progress_bar = progress::add_bar(
+                    &url,
+                    NUMBER_OF_REQUESTS.load(Ordering::Relaxed),
+                    false,
+                    false,
+                );
 
                 progress_bar.reset_elapsed();
 
@@ -382,9 +503,263 @@ fn get_single_spinner() -> ProgressBar {
     spinner
 }
 
+/// Container around a locked vector of `FeroxResponse`s, adds wrappers for insertion and search
+#[derive(Debug, Default)]
+pub struct FeroxResponses {
+    /// Internal structure: locked hashset of `FeroxScan`s
+    pub responses: Arc<RwLock<Vec<FeroxResponse>>>,
+}
+
+/// Serialize implementation for FeroxResponses
+impl Serialize for FeroxResponses {
+    /// Function that handles serialization of FeroxResponses
+    fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
+    where
+        S: Serializer,
+    {
+        if let Ok(responses) = self.responses.read() {
+            let mut seq = serializer.serialize_seq(Some(responses.len()))?;
+
+            for response in responses.iter() {
+                seq.serialize_element(response)?;
+            }
+
+            seq.end()
+        } else {
+            // if for some reason we can't unlock the mutex, just write an empty list
+            let seq = serializer.serialize_seq(Some(0))?;
+            seq.end()
+        }
+    }
+}
+
+/// Implementation of `FeroxResponses`
+impl FeroxResponses {
+    /// Add a `FeroxResponse` to the internal container
+    pub fn insert(&self, response: FeroxResponse) {
+        match self.responses.write() {
+            Ok(mut responses) => {
+                responses.push(response);
+            }
+            Err(e) => {
+                log::error!("FeroxResponses' container's mutex is poisoned: {}", e);
+            }
+        }
+    }
+
+    /// Simple check for whether or not a FeroxResponse is contained within the inner container
+    pub fn contains(&self, other: &FeroxResponse) -> bool {
+        match self.responses.read() {
+            Ok(responses) => {
+                for response in responses.iter() {
+                    if response.url == other.url {
+                        return true;
+                    }
+                }
+            }
+            Err(e) => {
+                log::error!("FeroxResponses' container's mutex is poisoned: {}", e);
+            }
+        }
+        false
+    }
+}
+/// Data container for (de)?serialization of multiple items
+#[derive(Serialize, Debug)]
+pub struct FeroxState {
+    /// Known scans
+    scans: &'static FeroxScans,
+
+    /// Current running config
+    config: &'static Configuration,
+
+    /// Known responses
+    responses: &'static FeroxResponses,
+}
+
+/// FeroxSerialize implementation for FeroxState
+impl FeroxSerialize for FeroxState {
+    /// Simply return debug format of FeroxState to satisfy as_str
+    fn as_str(&self) -> String {
+        format!("{:?}", self)
+    }
+
+    /// Simple call to produce a JSON string using the given FeroxState
+    fn as_json(&self) -> String {
+        serde_json::to_string(&self).unwrap_or_default()
+    }
+}
+
+/// Given a string representing some number of seconds, minutes, hours, or days, convert
+/// that representation to seconds and then wait for those seconds to elapse.  Once that period
+/// of time has elapsed, kill all currently running scans and dump a state file to disk that can
+/// be used to resume any unfinished scan.
+pub async fn start_max_time_thread(time_spec: &str) {
+    log::trace!("enter: start_max_time_thread({})", time_spec);
+
+    // as this function has already made it through the parser, which calls is_match on
+    // the value passed to --time-limit using TIMESPEC_REGEX; we can safely assume that
+    // the capture groups are populated; can expect something like 10m, 30s, 1h, etc...
+    let captures = TIMESPEC_REGEX.captures(&time_spec).unwrap();
+    let length_match = captures.get(1).unwrap();
+    let measurement_match = captures.get(2).unwrap();
+
+    if let Ok(length) = length_match.as_str().parse::<u64>() {
+        let length_in_secs = match measurement_match.as_str().to_ascii_lowercase().as_str() {
+            "s" => length,
+            "m" => length * 60,           // minutes
+            "h" => length * 60 * 60,      // hours
+            "d" => length * 60 * 60 * 24, // days
+            _ => length,
+        };
+
+        log::debug!(
+            "max time limit as string: {} and as seconds: {}",
+            time_spec,
+            length_in_secs
+        );
+
+        time::delay_for(time::Duration::new(length_in_secs, 0)).await;
+
+        log::trace!("exit: start_max_time_thread");
+
+        #[cfg(test)]
+        panic!();
+        #[cfg(not(test))]
+        sigint_handler();
+    }
+
+    log::error!(
+        "Could not parse the value provided ({}), can't enforce time limit",
+        length_match.as_str()
+    );
+}
+
+/// Writes the current state of the program to disk (if save_state is true) and then exits
+fn sigint_handler() {
+    log::trace!("enter: sigint_handler");
+
+    let ts = SystemTime::now()
+        .duration_since(UNIX_EPOCH)
+        .unwrap()
+        .as_secs();
+
+    let slug = if !CONFIGURATION.target_url.is_empty() {
+        // target url populated
+        CONFIGURATION
+            .target_url
+            .replace("://", "_")
+            .replace("/", "_")
+            .replace(".", "_")
+    } else {
+        // stdin used
+        "stdin".to_string()
+    };
+
+    let filename = format!("ferox-{}-{}.state", slug, ts);
+    let warning = format!(
+        "🚨 Caught {} 🚨 saving scan state to {} ...",
+        style("ctrl+c").yellow(),
+        filename
+    );
+
+    PROGRESS_PRINTER.println(warning);
+
+    let state = FeroxState {
+        config: &CONFIGURATION,
+        scans: &SCANNED_URLS,
+        responses: &RESPONSES,
+    };
+
+    let state_file = open_file(&filename);
+
+    if let Some(buffered_file) = state_file {
+        safe_file_write(&state, buffered_file, true);
+    }
+
+    log::trace!("exit: sigint_handler (end of program)");
+    std::process::exit(1);
+}
+
+/// Initialize the ctrl+c handler that saves scan state to disk
+pub fn initialize() {
+    log::trace!("enter: initialize");
+
+    let result = ctrlc::set_handler(sigint_handler);
+
+    if result.is_err() {
+        log::error!("Could not set Ctrl+c handler");
+        std::process::exit(1);
+    }
+
+    log::trace!("exit: initialize");
+}
+
+/// Primary logic used to load a Configuration from disk and populate the appropriate data
+/// structures
+pub fn resume_scan(filename: &str) -> Configuration {
+    log::trace!("enter: resume_scan({})", filename);
+
+    let file = File::open(filename).unwrap_or_else(|e| {
+        log::error!("{}", e);
+        log::error!("Could not open state file, exiting");
+        std::process::exit(1);
+    });
+
+    let reader = BufReader::new(file);
+    let state: serde_json::Value = serde_json::from_reader(reader).unwrap();
+
+    let conf = state.get("config").unwrap_or_else(|| {
+        log::error!("Could not load configuration from state file, exiting");
+        std::process::exit(1);
+    });
+
+    let config = serde_json::from_value(conf.clone()).unwrap_or_else(|e| {
+        log::error!("{}", e);
+        log::error!("Could not deserialize configuration found in state file, exiting");
+        std::process::exit(1);
+    });
+
+    if let Some(responses) = state.get("responses") {
+        if let Some(arr_responses) = responses.as_array() {
+            for response in arr_responses {
+                if let Ok(deser_resp) = serde_json::from_value(response.clone()) {
+                    RESPONSES.insert(deser_resp);
+                }
+            }
+        }
+    }
+
+    if let Some(scans) = state.get("scans") {
+        if let Some(arr_scans) = scans.as_array() {
+            for scan in arr_scans {
+                let deser_scan: FeroxScan =
+                    serde_json::from_value(scan.clone()).unwrap_or_default();
+                // need to determine if it's complete and based on that create a progress bar
+                // populate it accordingly based on completion
+                SCANNED_URLS.insert(Arc::new(Mutex::new(deser_scan)));
+            }
+        }
+    }
+
+    log::trace!("exit: resume_scan -> {:?}", config);
+    config
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::VERSION;
+    use predicates::prelude::*;
+
+    #[test]
+    /// test that ScanType's default is File
+    fn default_scantype_is_file() {
+        match ScanType::default() {
+            ScanType::File => {}
+            ScanType::Directory => panic!(),
+        }
+    }
 
     #[test]
     /// test that get_single_spinner returns the correct spinner
@@ -528,4 +903,168 @@ mod tests {
         assert!(scan.progress_bar.is_some()); // new pb created
         assert!(!pb.is_finished()) // not finished
     }
+
+    #[test]
+    /// given a JSON entry representing a FeroxScan, test that it deserializes into the proper type
+    /// with the right attributes
+    fn ferox_scan_deserialize() {
+        let fs_json = r#"{"id":"057016a14769414aac9a7a62707598cb","url":"https://spiritanimal.com","scan_type":"Directory","complete":true}"#;
+        let fs_json_two = r#"{"id":"057016a14769414aac9a7a62707598cb","url":"https://spiritanimal.com","scan_type":"Not Correct","complete":true}"#;
+
+        let fs: FeroxScan = serde_json::from_str(fs_json).unwrap();
+        let fs_two: FeroxScan = serde_json::from_str(fs_json_two).unwrap();
+        assert_eq!(fs.url, "https://spiritanimal.com");
+
+        match fs.scan_type {
+            ScanType::Directory => {}
+            ScanType::File => {
+                panic!();
+            }
+        }
+        match fs_two.scan_type {
+            ScanType::Directory => {
+                panic!();
+            }
+            ScanType::File => {}
+        }
+
+        match fs.progress_bar {
+            None => {}
+            Some(_) => {
+                panic!();
+            }
+        }
+        assert_eq!(fs.complete, true);
+        assert_eq!(fs.id, "057016a14769414aac9a7a62707598cb");
+    }
+
+    #[test]
+    /// given a FeroxScan, test that it serializes into the proper JSON entry
+    fn ferox_scan_serialize() {
+        let fs = FeroxScan::new("https://spiritanimal.com", ScanType::Directory, None);
+        let fs_json = format!(
+            r#"{{"id":"{}","url":"https://spiritanimal.com","scan_type":"Directory","complete":false}}"#,
+            fs.lock().unwrap().id
+        );
+        assert_eq!(
+            fs_json,
+            serde_json::to_string(&*fs.lock().unwrap()).unwrap()
+        );
+    }
+
+    #[test]
+    /// given a FeroxScans, test that it serializes into the proper JSON entry
+    fn ferox_scans_serialize() {
+        let ferox_scan = FeroxScan::new("https://spiritanimal.com", ScanType::Directory, None);
+        let ferox_scans = FeroxScans::default();
+        let ferox_scans_json = format!(
+            r#"[{{"id":"{}","url":"https://spiritanimal.com","scan_type":"Directory","complete":false}}]"#,
+            ferox_scan.lock().unwrap().id
+        );
+        ferox_scans.scans.lock().unwrap().push(ferox_scan);
+        assert_eq!(
+            ferox_scans_json,
+            serde_json::to_string(&ferox_scans).unwrap()
+        );
+    }
+
+    #[test]
+    /// given a FeroxResponses, test that it serializes into the proper JSON entry
+    fn ferox_responses_serialize() {
+        let json_response = r#"{"type":"response","url":"https://nerdcore.com/css","path":"/css","wildcard":true,"status":301,"content_length":173,"line_count":10,"word_count":16,"headers":{"server":"nginx/1.16.1"}}"#;
+        let response: FeroxResponse = serde_json::from_str(json_response).unwrap();
+
+        let responses = FeroxResponses::default();
+        responses.insert(response);
+        // responses has a response now
+
+        // serialized should be a list of responses
+        let expected = format!("[{}]", json_response);
+
+        let serialized = serde_json::to_string(&responses).unwrap();
+        assert_eq!(expected, serialized);
+    }
+
+    #[test]
+    /// given a FeroxResponse, test that it serializes into the proper JSON entry
+    fn ferox_response_serialize_and_deserialize() {
+        // deserialize
+        let json_response = r#"{"type":"response","url":"https://nerdcore.com/css","path":"/css","wildcard":true,"status":301,"content_length":173,"line_count":10,"word_count":16,"headers":{"server":"nginx/1.16.1"}}"#;
+        let response: FeroxResponse = serde_json::from_str(json_response).unwrap();
+
+        assert_eq!(response.url.as_str(), "https://nerdcore.com/css");
+        assert_eq!(response.url.path(), "/css");
+        assert_eq!(response.wildcard, true);
+        assert_eq!(response.status.as_u16(), 301);
+        assert_eq!(response.content_length, 173);
+        assert_eq!(response.line_count, 10);
+        assert_eq!(response.word_count, 16);
+        assert_eq!(response.headers.get("server").unwrap(), "nginx/1.16.1");
+
+        // serialize, however, this can fail when headers are out of order
+        let new_json = serde_json::to_string(&response).unwrap();
+        assert_eq!(json_response, new_json);
+    }
+
+    #[test]
+    /// test FeroxSerialize implementation of FeroxState
+    fn feroxstates_feroxserialize_implementation() {
+        let ferox_scan = FeroxScan::new("https://spiritanimal.com", ScanType::Directory, None);
+        let saved_id = ferox_scan.lock().unwrap().id.clone();
+        SCANNED_URLS.insert(ferox_scan);
+
+        let json_response = r#"{"type":"response","url":"https://nerdcore.com/css","path":"/css","wildcard":true,"status":301,"content_length":173,"line_count":10,"word_count":16,"headers":{"server":"nginx/1.16.1"}}"#;
+        let response: FeroxResponse = serde_json::from_str(json_response).unwrap();
+        RESPONSES.insert(response);
+
+        let ferox_state = FeroxState {
+            scans: &SCANNED_URLS,
+            responses: &RESPONSES,
+            config: &CONFIGURATION,
+        };
+
+        let expected_strs = predicates::str::contains("scans: FeroxScans").and(
+            predicate::str::contains("config: Configuration")
+                .and(predicate::str::contains("responses: FeroxResponses"))
+                .and(predicate::str::contains("nerdcore.com"))
+                .and(predicate::str::contains("/css"))
+                .and(predicate::str::contains("https://spiritanimal.com")),
+        );
+
+        assert!(expected_strs.eval(&ferox_state.as_str()));
+
+        let json_state = ferox_state.as_json();
+        let expected = format!(
+            r#"{{"scans":[{{"id":"{}","url":"https://spiritanimal.com","scan_type":"Directory","complete":false}}],"config":{{"type":"configuration","wordlist":"/usr/share/seclists/Discovery/Web-Content/raft-medium-directories.txt","config":"","proxy":"","replay_proxy":"","target_url":"","status_codes":[200,204,301,302,307,308,401,403,405],"replay_codes":[200,204,301,302,307,308,401,403,405],"filter_status":[],"threads":50,"timeout":7,"verbosity":0,"quiet":false,"json":false,"output":"","debug_log":"","user_agent":"feroxbuster/{}","redirects":false,"insecure":false,"extensions":[],"headers":{{}},"queries":[],"no_recursion":false,"extract_links":false,"add_slash":false,"stdin":false,"depth":4,"scan_limit":0,"filter_size":[],"filter_line_count":[],"filter_word_count":[],"filter_regex":[],"dont_filter":false,"resumed":false,"save_state":false,"time_limit":"","filter_similar":[]}},"responses":[{{"type":"response","url":"https://nerdcore.com/css","path":"/css","wildcard":true,"status":301,"content_length":173,"line_count":10,"word_count":16,"headers":{{"server":"nginx/1.16.1"}}}}]}}"#,
+            saved_id, VERSION
+        );
+        println!("{}\n{}", expected, json_state);
+        assert!(predicates::str::similar(expected).eval(&json_state));
+    }
+
+    #[should_panic]
+    #[tokio::test(core_threads = 1)]
+    /// call start_max_time_thread with a valid timespec, expect a panic, but only after a certain
+    /// number of seconds
+    async fn start_max_time_thread_panics_after_delay() {
+        let now = time::Instant::now();
+        let delay = time::Duration::new(3, 0);
+
+        start_max_time_thread("3s").await;
+
+        assert!(now.elapsed() > delay);
+    }
+
+    #[tokio::test(core_threads = 1)]
+    /// call start_max_time_thread with a timespec that's too large to be parsed correctly, expect
+    /// immediate return and no panic, as the sigint handler is never called
+    async fn start_max_time_thread_returns_immediately_with_too_large_input() {
+        let now = time::Instant::now();
+        let delay = time::Duration::new(1, 0);
+
+        // pub const MAX: usize = usize::MAX; // 18_446_744_073_709_551_615usize
+        start_max_time_thread("18446744073709551616m").await; // can't fit in dest u64
+
+        assert!(now.elapsed() < delay); // assuming function call will take less than 1second
+    }
 }

src/scanner.rs

@@ -1,20 +1,25 @@
 use crate::{
-    config::CONFIGURATION,
-    extractor::get_links,
+    config::{Configuration, CONFIGURATION},
+    extractor::{get_links, request_feroxresponse_from_new_link},
     filters::{
-        FeroxFilter, LinesFilter, SizeFilter, StatusCodeFilter, WildcardFilter, WordsFilter,
+        FeroxFilter, LinesFilter, RegexFilter, SimilarityFilter, SizeFilter, StatusCodeFilter,
+        WildcardFilter, WordsFilter,
     },
     heuristics,
-    scan_manager::{FeroxScans, PAUSE_SCAN},
+    scan_manager::{FeroxResponses, FeroxScans, PAUSE_SCAN},
     utils::{format_url, get_current_depth, make_request},
-    FeroxChannel, FeroxResponse,
+    FeroxChannel, FeroxResponse, SIMILARITY_THRESHOLD,
 };
 use futures::{
     future::{BoxFuture, FutureExt},
     stream, StreamExt,
 };
+use fuzzyhash::FuzzyHash;
 use lazy_static::lazy_static;
+use regex::Regex;
 use reqwest::Url;
+#[cfg(not(test))]
+use std::process::exit;
 use std::{
     collections::HashSet,
     convert::TryInto,
@@ -43,6 +48,9 @@ lazy_static! {
     /// Vector of implementors of the FeroxFilter trait
     static ref FILTERS: Arc<RwLock<Vec<Box<dyn FeroxFilter>>>> = Arc::new(RwLock::new(Vec::<Box<dyn FeroxFilter>>::new()));
 
+    /// Vector of FeroxResponse objects
+    pub static ref RESPONSES: FeroxResponses = FeroxResponses::default();
+
     /// Bounded semaphore used as a barrier to limit concurrent scans
     static ref SCAN_LIMITER: Semaphore = Semaphore::new(CONFIGURATION.scan_limit);
 }
@@ -90,14 +98,16 @@ fn spawn_recursion_handler(
     mut recursion_channel: UnboundedReceiver<String>,
     wordlist: Arc<HashSet<String>>,
     base_depth: usize,
+    num_targets: usize,
     tx_term: UnboundedSender<FeroxResponse>,
-    tx_file: UnboundedSender<String>,
+    tx_file: UnboundedSender<FeroxResponse>,
 ) -> BoxFuture<'static, Vec<JoinHandle<()>>> {
     log::trace!(
-        "enter: spawn_recursion_handler({:?}, wordlist[{} words...], {}, {:?}, {:?})",
+        "enter: spawn_recursion_handler({:?}, wordlist[{} words...], {}, {}, {:?}, {:?})",
         recursion_channel,
         wordlist.len(),
         base_depth,
+        num_targets,
         tx_term,
         tx_file
     );
@@ -125,6 +135,7 @@ fn spawn_recursion_handler(
                     resp_clone.to_owned().as_str(),
                     list_clone,
                     base_depth,
+                    num_targets,
                     term_clone,
                     file_clone,
                 )
@@ -378,30 +389,11 @@ async fn make_requests(
                 let new_links = get_links(&ferox_response).await;
 
                 for new_link in new_links {
-                    // create a url based on the given command line options, continue on error
-                    let new_url = match format_url(
-                        &new_link,
-                        &"",
-                        CONFIGURATION.add_slash,
-                        &CONFIGURATION.queries,
-                        None,
-                    ) {
-                        Ok(url) => url,
-                        Err(_) => continue,
-                    };
-
-                    if SCANNED_URLS.get_scan_by_url(&new_url.to_string()).is_some() {
-                        //we've seen the url before and don't need to scan again
-                        continue;
-                    }
-
-                    // make the request and store the response
-                    let new_response = match make_request(&CONFIGURATION.client, &new_url).await {
-                        Ok(resp) => resp,
-                        Err(_) => continue,
-                    };
-
-                    let mut new_ferox_response = FeroxResponse::from(new_response, true).await;
+                    let mut new_ferox_response =
+                        match request_feroxresponse_from_new_link(&new_link).await {
+                            Some(resp) => resp,
+                            None => continue,
+                        };
 
                     // filter if necessary
                     if should_filter_response(&new_ferox_response) {
@@ -412,7 +404,7 @@ async fn make_requests(
                         // very likely a file, simply request and report
                         log::debug!("Singular extraction: {}", new_ferox_response);
 
-                        SCANNED_URLS.add_file_scan(&new_url.to_string());
+                        SCANNED_URLS.add_file_scan(&new_ferox_response.url().to_string());
 
                         send_report(report_chan.clone(), new_ferox_response);
 
@@ -445,7 +437,7 @@ async fn make_requests(
 }
 
 /// Simple helper to send a `FeroxResponse` over the tx side of an `mpsc::unbounded_channel`
-fn send_report(report_sender: UnboundedSender<FeroxResponse>, response: FeroxResponse) {
+pub fn send_report(report_sender: UnboundedSender<FeroxResponse>, response: FeroxResponse) {
     log::trace!("enter: send_report({:?}, {}", report_sender, response);
 
     match report_sender.send(response) {
@@ -465,14 +457,16 @@ pub async fn scan_url(
     target_url: &str,
     wordlist: Arc<HashSet<String>>,
     base_depth: usize,
+    num_targets: usize,
     tx_term: UnboundedSender<FeroxResponse>,
-    tx_file: UnboundedSender<String>,
+    tx_file: UnboundedSender<FeroxResponse>,
 ) {
     log::trace!(
-        "enter: scan_url({:?}, wordlist[{} words...], {}, {:?}, {:?})",
+        "enter: scan_url({:?}, wordlist[{} words...], {}, {}, {:?}, {:?})",
         target_url,
         wordlist.len(),
         base_depth,
+        num_targets,
         tx_term,
         tx_file
     );
@@ -481,7 +475,7 @@ pub async fn scan_url(
 
     let (tx_dir, rx_dir): FeroxChannel<String> = mpsc::unbounded_channel();
 
-    if CALL_COUNT.load(Ordering::Relaxed) == 0 {
+    if CALL_COUNT.load(Ordering::Relaxed) < num_targets {
         CALL_COUNT.fetch_add(1, Ordering::Relaxed);
 
         // this protection allows us to add the first scanned url to SCANNED_URLS
@@ -516,7 +510,7 @@ pub async fn scan_url(
 
     // Arc clones to be passed around to the various scans
     let wildcard_bar = progress_bar.clone();
-    let heuristics_file_clone = tx_file.clone();
+    let heuristics_term_clone = tx_term.clone();
     let recurser_term_clone = tx_term.clone();
     let recurser_file_clone = tx_file.clone();
     let recurser_words = wordlist.clone();
@@ -527,6 +521,7 @@ pub async fn scan_url(
             rx_dir,
             recurser_words,
             base_depth,
+            num_targets,
             recurser_term_clone,
             recurser_file_clone,
         )
@@ -535,7 +530,7 @@ pub async fn scan_url(
 
     // add any wildcard filters to `FILTERS`
     let filter =
-        match heuristics::wildcard_test(&target_url, wildcard_bar, heuristics_file_clone).await {
+        match heuristics::wildcard_test(&target_url, wildcard_bar, heuristics_term_clone).await {
             Some(f) => Box::new(f),
             None => Box::new(WildcardFilter::default()),
         };
@@ -601,38 +596,21 @@ pub async fn scan_url(
 
 /// Perform steps necessary to run scans that only need to be performed once (warming up the
 /// engine, as it were)
-pub fn initialize(
-    num_words: usize,
-    scan_limit: usize,
-    extensions: &[String],
-    status_code_filters: &[u16],
-    lines_filters: &[usize],
-    words_filters: &[usize],
-    size_filters: &[u64],
-) {
-    log::trace!(
-        "enter: initialize({}, {}, {:?}, {:?}, {:?}, {:?}, {:?})",
-        num_words,
-        scan_limit,
-        extensions,
-        status_code_filters,
-        lines_filters,
-        words_filters,
-        size_filters,
-    );
+pub async fn initialize(num_words: usize, config: &Configuration) {
+    log::trace!("enter: initialize({}, {:?})", num_words, config,);
 
     // number of requests only needs to be calculated once, and then can be reused
-    let num_reqs_expected: u64 = if extensions.is_empty() {
+    let num_reqs_expected: u64 = if config.extensions.is_empty() {
         num_words.try_into().unwrap()
     } else {
-        let total = num_words * (extensions.len() + 1);
+        let total = num_words * (config.extensions.len() + 1);
         total.try_into().unwrap()
     };
 
     NUMBER_OF_REQUESTS.store(num_reqs_expected, Ordering::Relaxed);
 
     // add any status code filters to `FILTERS` (-C|--filter-status)
-    for code_filter in status_code_filters {
+    for code_filter in &config.filter_status {
         let filter = StatusCodeFilter {
             filter_code: *code_filter,
         };
@@ -641,7 +619,7 @@ pub fn initialize(
     }
 
     // add any line count filters to `FILTERS` (-N|--filter-lines)
-    for lines_filter in lines_filters {
+    for lines_filter in &config.filter_line_count {
         let filter = LinesFilter {
             line_count: *lines_filter,
         };
@@ -650,7 +628,7 @@ pub fn initialize(
     }
 
     // add any line count filters to `FILTERS` (-W|--filter-words)
-    for words_filter in words_filters {
+    for words_filter in &config.filter_word_count {
         let filter = WordsFilter {
             word_count: *words_filter,
         };
@@ -659,7 +637,7 @@ pub fn initialize(
     }
 
     // add any line count filters to `FILTERS` (-S|--filter-size)
-    for size_filter in size_filters {
+    for size_filter in &config.filter_size {
         let filter = SizeFilter {
             content_length: *size_filter,
         };
@@ -667,7 +645,52 @@ pub fn initialize(
         add_filter_to_list_of_ferox_filters(boxed_filter, FILTERS.clone());
     }
 
-    if scan_limit == 0 {
+    // add any regex filters to `FILTERS` (-X|--filter-regex)
+    for regex_filter in &config.filter_regex {
+        let raw = regex_filter;
+        let compiled = match Regex::new(&raw) {
+            Ok(regex) => regex,
+            Err(e) => {
+                log::error!("Invalid regular expression: {}", e);
+                #[cfg(test)]
+                panic!();
+                #[cfg(not(test))]
+                exit(1);
+            }
+        };
+
+        let filter = RegexFilter {
+            raw_string: raw.to_owned(),
+            compiled,
+        };
+        let boxed_filter = Box::new(filter);
+        add_filter_to_list_of_ferox_filters(boxed_filter, FILTERS.clone());
+    }
+
+    // add any similarity filters to `FILTERS` (--filter-similar-to)
+    for similarity_filter in &config.filter_similar {
+        // url as-is based on input, ignores user-specified url manipulation options (add-slash etc)
+        if let Ok(url) = format_url(&similarity_filter, &"", false, &Vec::new(), None) {
+            // attempt to request the given url
+            if let Ok(resp) = make_request(&CONFIGURATION.client, &url).await {
+                // if successful, create a filter based on the response's body
+                let fr = FeroxResponse::from(resp, true).await;
+
+                // hash the response body and store the resulting hash in the filter object
+                let hash = FuzzyHash::new(&fr.text()).to_string();
+
+                let filter = SimilarityFilter {
+                    text: hash,
+                    threshold: SIMILARITY_THRESHOLD,
+                };
+
+                let boxed_filter = Box::new(filter);
+                add_filter_to_list_of_ferox_filters(boxed_filter, FILTERS.clone());
+            }
+        }
+    }
+
+    if config.scan_limit == 0 {
         // scan_limit == 0 means no limit should be imposed... however, scoping the Semaphore
         // permit is tricky, so as a workaround, we'll add a ridiculous number of permits to
         // the semaphore (1,152,921,504,606,846,975 to be exact) and call that 'unlimited'
@@ -774,4 +797,13 @@ mod tests {
         let result = reached_max_depth(&url, 0, 2);
         assert!(result);
     }
+
+    #[tokio::test(core_threads = 1)]
+    #[should_panic]
+    /// call initialize with a bad regex, triggering a panic
+    async fn initialize_panics_on_bad_regex() {
+        let mut config = Configuration::default();
+        config.filter_regex = vec![r"(".to_string()];
+        initialize(1, &config).await;
+    }
 }

src/utils.rs

@@ -8,6 +8,34 @@ use reqwest::{Client, Response, Url};
 #[cfg(not(target_os = "windows"))]
 use rlimit::{getrlimit, setrlimit, Resource, Rlim};
 use std::convert::TryInto;
+use std::sync::{Arc, RwLock};
+use std::{fs, io};
+
+/// Given the path to a file, open the file in append mode (create it if it doesn't exist) and
+/// return a reference to the file that is buffered and locked
+pub fn open_file(filename: &str) -> Option<Arc<RwLock<io::BufWriter<fs::File>>>> {
+    log::trace!("enter: open_file({})", filename);
+
+    match fs::OpenOptions::new() // std fs
+        .create(true)
+        .append(true)
+        .open(filename)
+    {
+        Ok(file) => {
+            let writer = io::BufWriter::new(file); // std io
+
+            let locked_file = Some(Arc::new(RwLock::new(writer)));
+
+            log::trace!("exit: open_file -> {:?}", locked_file);
+            locked_file
+        }
+        Err(e) => {
+            log::error!("{}", e);
+            log::trace!("exit: open_file -> None");
+            None
+        }
+    }
+}
 
 /// Helper function that determines the current depth of a given url
 ///

tests/test_banner.rs

@@ -701,3 +701,139 @@ fn banner_prints_filter_status() -> Result<(), Box<dyn std::error::Error>> {
         );
     Ok(())
 }
+
+#[test]
+/// test allows non-existent wordlist to trigger the banner printing to stderr
+/// expect to see all mandatory prints + json
+fn banner_prints_json() {
+    Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg("http://localhost")
+        .arg("--json")
+        .arg("--output")
+        .arg("/dev/null")
+        .assert()
+        .success()
+        .stderr(
+            predicate::str::contains("─┬─")
+                .and(predicate::str::contains("Target Url"))
+                .and(predicate::str::contains("http://localhost"))
+                .and(predicate::str::contains("Threads"))
+                .and(predicate::str::contains("Wordlist"))
+                .and(predicate::str::contains("Status Codes"))
+                .and(predicate::str::contains("Timeout (secs)"))
+                .and(predicate::str::contains("User-Agent"))
+                .and(predicate::str::contains("JSON Output"))
+                .and(predicate::str::contains("│ true"))
+                .and(predicate::str::contains("─┴─")),
+        );
+}
+
+#[test]
+/// test allows non-existent wordlist to trigger the banner printing to stderr
+/// expect to see all mandatory prints + json
+fn banner_prints_debug_log() {
+    Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg("http://localhost")
+        .arg("--debug-log")
+        .arg("/dev/null")
+        .assert()
+        .success()
+        .stderr(
+            predicate::str::contains("─┬─")
+                .and(predicate::str::contains("Target Url"))
+                .and(predicate::str::contains("http://localhost"))
+                .and(predicate::str::contains("Threads"))
+                .and(predicate::str::contains("Wordlist"))
+                .and(predicate::str::contains("Status Codes"))
+                .and(predicate::str::contains("Timeout (secs)"))
+                .and(predicate::str::contains("User-Agent"))
+                .and(predicate::str::contains("Debugging Log"))
+                .and(predicate::str::contains("│ /dev/null"))
+                .and(predicate::str::contains("─┴─")),
+        );
+}
+
+#[test]
+/// test allows non-existent wordlist to trigger the banner printing to stderr
+/// expect to see all mandatory prints + regex filters
+fn banner_prints_filter_regex() {
+    Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg("http://localhost")
+        .arg("--filter-regex")
+        .arg("^ignore me$")
+        .assert()
+        .success()
+        .stderr(
+            predicate::str::contains("─┬─")
+                .and(predicate::str::contains("Target Url"))
+                .and(predicate::str::contains("http://localhost"))
+                .and(predicate::str::contains("Threads"))
+                .and(predicate::str::contains("Wordlist"))
+                .and(predicate::str::contains("Status Codes"))
+                .and(predicate::str::contains("Timeout (secs)"))
+                .and(predicate::str::contains("User-Agent"))
+                .and(predicate::str::contains("Regex Filter"))
+                .and(predicate::str::contains("│ ^ignore me$"))
+                .and(predicate::str::contains("─┴─")),
+        );
+}
+
+#[test]
+/// test allows non-existent wordlist to trigger the banner printing to stderr
+/// expect to see all mandatory prints + time limit
+fn banner_prints_time_limit() {
+    Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg("http://localhost")
+        .arg("--time-limit")
+        .arg("10m")
+        .assert()
+        .success()
+        .stderr(
+            predicate::str::contains("─┬─")
+                .and(predicate::str::contains("Target Url"))
+                .and(predicate::str::contains("http://localhost"))
+                .and(predicate::str::contains("Threads"))
+                .and(predicate::str::contains("Wordlist"))
+                .and(predicate::str::contains("Status Codes"))
+                .and(predicate::str::contains("Timeout (secs)"))
+                .and(predicate::str::contains("User-Agent"))
+                .and(predicate::str::contains("Time Limit"))
+                .and(predicate::str::contains("│ 10m"))
+                .and(predicate::str::contains("─┴─")),
+        );
+}
+
+#[test]
+/// test allows non-existent wordlist to trigger the banner printing to stderr
+/// expect to see all mandatory prints + similarity filter
+fn banner_prints_similarity_filter() {
+    Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg("http://localhost")
+        .arg("--filter-similar-to")
+        .arg("https://somesite.com")
+        .assert()
+        .success()
+        .stderr(
+            predicate::str::contains("─┬─")
+                .and(predicate::str::contains("Target Url"))
+                .and(predicate::str::contains("http://localhost"))
+                .and(predicate::str::contains("Threads"))
+                .and(predicate::str::contains("Wordlist"))
+                .and(predicate::str::contains("Status Codes"))
+                .and(predicate::str::contains("Timeout (secs)"))
+                .and(predicate::str::contains("User-Agent"))
+                .and(predicate::str::contains("Similarity Filter"))
+                .and(predicate::str::contains("│ https://somesite.com"))
+                .and(predicate::str::contains("─┴─")),
+        );
+}

tests/test_extractor.rs

@@ -1,7 +1,7 @@
 mod utils;
 use assert_cmd::prelude::*;
 use httpmock::Method::GET;
-use httpmock::{Mock, MockServer};
+use httpmock::MockServer;
 use predicates::prelude::*;
 use std::process::Command;
 use utils::{setup_tmp_directory, teardown_tmp_directory};
@@ -13,18 +13,17 @@ fn extractor_finds_absolute_url() -> Result<(), Box<dyn std::error::Error>> {
     let srv = MockServer::start();
     let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_status(200)
-        .return_body(&srv.url("'/homepage/assets/img/icons/handshake.svg'"))
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200)
+            .body(&srv.url("'/homepage/assets/img/icons/handshake.svg'"));
+    });
 
-    let mock_two = Mock::new()
-        .expect_method(GET)
-        .expect_path("/homepage/assets/img/icons/handshake.svg")
-        .return_status(200)
-        .create_on(&srv);
+    let mock_two = srv.mock(|when, then| {
+        when.method(GET)
+            .path("/homepage/assets/img/icons/handshake.svg");
+        then.status(200);
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -43,8 +42,8 @@ fn extractor_finds_absolute_url() -> Result<(), Box<dyn std::error::Error>> {
             )),
     );
 
-    assert_eq!(mock.times_called(), 1);
-    assert_eq!(mock_two.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(mock_two.hits(), 1);
     teardown_tmp_directory(tmp_dir);
     Ok(())
 }
@@ -56,12 +55,11 @@ fn extractor_finds_absolute_url_to_different_domain() -> Result<(), Box<dyn std:
     let srv = MockServer::start();
     let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_status(200)
-        .return_body("\"http://localhost/homepage/assets/img/icons/handshake.svg\"")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200)
+            .body("\"http://localhost/homepage/assets/img/icons/handshake.svg\"");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -81,7 +79,7 @@ fn extractor_finds_absolute_url_to_different_domain() -> Result<(), Box<dyn std:
             .not(),
     );
 
-    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
     teardown_tmp_directory(tmp_dir);
     Ok(())
 }
@@ -92,18 +90,17 @@ fn extractor_finds_relative_url() -> Result<(), Box<dyn std::error::Error>> {
     let srv = MockServer::start();
     let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_status(200)
-        .return_body("\"/homepage/assets/img/icons/handshake.svg\"")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200)
+            .body("\"/homepage/assets/img/icons/handshake.svg\"");
+    });
 
-    let mock_two = Mock::new()
-        .expect_method(GET)
-        .expect_path("/homepage/assets/img/icons/handshake.svg")
-        .return_status(200)
-        .create_on(&srv);
+    let mock_two = srv.mock(|when, then| {
+        when.method(GET)
+            .path("/homepage/assets/img/icons/handshake.svg");
+        then.status(200);
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -122,8 +119,8 @@ fn extractor_finds_relative_url() -> Result<(), Box<dyn std::error::Error>> {
             )),
     );
 
-    assert_eq!(mock.times_called(), 1);
-    assert_eq!(mock_two.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(mock_two.hits(), 1);
     teardown_tmp_directory(tmp_dir);
     Ok(())
 }
@@ -131,30 +128,28 @@ fn extractor_finds_relative_url() -> Result<(), Box<dyn std::error::Error>> {
 #[test]
 /// send a request to a page that contains an relative link, follow it, and find the same link again
 /// should follow then filter
-fn extractor_finds_same_relative_url_twice() -> Result<(), Box<dyn std::error::Error>> {
+fn extractor_finds_same_relative_url_twice() {
     let srv = MockServer::start();
     let (tmp_dir, file) =
-        setup_tmp_directory(&["LICENSE".to_string(), "README".to_string()], "wordlist")?;
+        setup_tmp_directory(&["LICENSE".to_string(), "README".to_string()], "wordlist").unwrap();
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_status(200)
-        .return_body(&srv.url("\"/homepage/assets/img/icons/handshake.svg\""))
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200)
+            .body(&srv.url("\"/homepage/assets/img/icons/handshake.svg\""));
+    });
 
-    let mock_two = Mock::new()
-        .expect_method(GET)
-        .expect_path("/README")
-        .return_body(&srv.url("\"/homepage/assets/img/icons/handshake.svg\""))
-        .return_status(200)
-        .create_on(&srv);
+    let mock_two = srv.mock(|when, then| {
+        when.method(GET).path("/README");
+        then.status(200)
+            .body(&srv.url("\"/homepage/assets/img/icons/handshake.svg\""));
+    });
 
-    let mock_three = Mock::new()
-        .expect_method(GET)
-        .expect_path("/homepage/assets/img/icons/handshake.svg")
-        .return_status(200)
-        .create_on(&srv);
+    let mock_three = srv.mock(|when, then| {
+        when.method(GET)
+            .path("/homepage/assets/img/icons/handshake.svg");
+        then.status(200);
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -168,16 +163,15 @@ fn extractor_finds_same_relative_url_twice() -> Result<(), Box<dyn std::error::E
     cmd.assert().success().stdout(
         predicate::str::contains("/LICENSE")
             .and(predicate::str::contains("200"))
-            .and(predicate::str::contains(
-                "/homepage/assets/img/icons/handshake.svg",
-            )),
+            // .count(1) asserts that we only see the endpoint reported once, even though there
+            // is the potential to request the same url twice
+            .and(predicate::str::contains("/homepage/assets/img/icons/handshake.svg").count(1)),
     );
 
-    assert_eq!(mock.times_called(), 1);
-    assert_eq!(mock_two.times_called(), 1);
-    assert_eq!(mock_three.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(mock_two.hits(), 1);
+    assert!(mock_three.hits() <= 2);
     teardown_tmp_directory(tmp_dir);
-    Ok(())
 }
 
 #[test]
@@ -188,19 +182,17 @@ fn extractor_finds_filtered_content() -> Result<(), Box<dyn std::error::Error>>
     let (tmp_dir, file) =
         setup_tmp_directory(&["LICENSE".to_string(), "README".to_string()], "wordlist")?;
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_status(200)
-        .return_body(&srv.url("\"/homepage/assets/img/icons/handshake.svg\""))
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200)
+            .body(&srv.url("\"/homepage/assets/img/icons/handshake.svg\""));
+    });
 
-    let mock_two = Mock::new()
-        .expect_method(GET)
-        .expect_path("/homepage/assets/img/icons/handshake.svg")
-        .return_body("im a little teapot")
-        .return_status(200)
-        .create_on(&srv);
+    let mock_two = srv.mock(|when, then| {
+        when.method(GET)
+            .path("/homepage/assets/img/icons/handshake.svg");
+        then.status(200).body("im a little teapot");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -222,8 +214,72 @@ fn extractor_finds_filtered_content() -> Result<(), Box<dyn std::error::Error>>
             .not(),
     );
 
-    assert_eq!(mock.times_called(), 1);
-    assert_eq!(mock_two.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(mock_two.hits(), 1);
     teardown_tmp_directory(tmp_dir);
     Ok(())
 }
+
+#[test]
+/// serve a robots.txt with a file and and a folder link contained within it. ferox should
+/// find both links and request each one. Additionally, a scan should start with the directory
+/// link found, meaning the wordlist will be thrown at the sub directory
+fn extractor_finds_robots_txt_links_and_displays_files_or_scans_directories() {
+    let srv = MockServer::start();
+    let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist").unwrap();
+
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200).body("im a little teapot"); // 18
+    });
+
+    let mock_two = srv.mock(|when, then| {
+        when.method(GET).path("/robots.txt");
+        then.status(200).body(
+            r#"
+            User-agent: *
+            Crawl-delay: 10
+            # CSS, JS, Images
+            Allow: /misc/*.css$
+            Disallow: /misc/stupidfile.php
+               Disallow: /disallowed-subdir/
+            "#,
+        );
+    });
+
+    let mock_file = srv.mock(|when, then| {
+        when.method(GET).path("/misc/stupidfile.php");
+        then.status(200).body("im a little teapot too"); // 22
+    });
+
+    let mock_dir = srv.mock(|when, then| {
+        when.method(GET).path("/disallowed-subdir/LICENSE");
+        then.status(200).body("i too, am a container for tea"); // 29
+    });
+
+    let cmd = Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg(srv.url("/"))
+        .arg("--wordlist")
+        .arg(file.as_os_str())
+        .arg("--extract-links")
+        .unwrap();
+
+    cmd.assert().success().stdout(
+        predicate::str::contains("/LICENSE") // 2 directories contain LICENSE
+            .count(2)
+            .and(predicate::str::contains("18c"))
+            .and(predicate::str::contains("/misc/stupidfile.php"))
+            .and(predicate::str::contains("22c"))
+            .and(predicate::str::contains("/disallowed-subdir/LICENSE"))
+            .and(predicate::str::contains("29c"))
+            .and(predicate::str::contains("200").count(3)),
+    );
+
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(mock_dir.hits(), 1);
+    assert_eq!(mock_two.hits(), 1);
+    assert_eq!(mock_file.hits(), 1);
+    teardown_tmp_directory(tmp_dir);
+}

tests/test_filters.rs

@@ -1,7 +1,7 @@
 mod utils;
 use assert_cmd::prelude::*;
 use httpmock::Method::GET;
-use httpmock::{Mock, MockServer};
+use httpmock::MockServer;
 use predicates::prelude::*;
 use std::process::Command;
 use utils::{setup_tmp_directory, teardown_tmp_directory};
@@ -14,19 +14,15 @@ fn filters_status_code_should_filter_response() {
     let (tmp_dir, file) =
         setup_tmp_directory(&["LICENSE".to_string(), "file.js".to_string()], "wordlist").unwrap();
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_status(302)
-        .return_body("this is a test")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(302).body("this is a test");
+    });
 
-    let mock_two = Mock::new()
-        .expect_method(GET)
-        .expect_path("/file.js")
-        .return_status(200)
-        .return_body("this is also a test of some import")
-        .create_on(&srv);
+    let mock_two = srv.mock(|when, then| {
+        when.method(GET).path("/file.js");
+        then.status(200).body("this is also a test of some import");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -44,15 +40,15 @@ fn filters_status_code_should_filter_response() {
             .not()
             .and(predicate::str::contains("302"))
             .not()
-            .and(predicate::str::contains("14"))
+            .and(predicate::str::contains("14c"))
             .not()
             .and(predicate::str::contains("/file.js"))
             .and(predicate::str::contains("200"))
-            .and(predicate::str::contains("34")),
+            .and(predicate::str::contains("34c")),
     );
 
-    assert_eq!(mock.times_called(), 1);
-    assert_eq!(mock_two.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(mock_two.hits(), 1);
     teardown_tmp_directory(tmp_dir);
 }
 
@@ -64,19 +60,16 @@ fn filters_lines_should_filter_response() {
     let (tmp_dir, file) =
         setup_tmp_directory(&["LICENSE".to_string(), "file.js".to_string()], "wordlist").unwrap();
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_status(302)
-        .return_body("this is a test")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(302).body("this is a test");
+    });
 
-    let mock_two = Mock::new()
-        .expect_method(GET)
-        .expect_path("/file.js")
-        .return_status(200)
-        .return_body("this is also a test of some import\nwith 2 lines, no less")
-        .create_on(&srv);
+    let mock_two = srv.mock(|when, then| {
+        when.method(GET).path("/file.js");
+        then.status(200)
+            .body("this is also a test of some import\nwith 2 lines, no less");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -100,8 +93,8 @@ fn filters_lines_should_filter_response() {
             .not(),
     );
 
-    assert_eq!(mock.times_called(), 1);
-    assert_eq!(mock_two.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(mock_two.hits(), 1);
     teardown_tmp_directory(tmp_dir);
 }
 
@@ -113,19 +106,16 @@ fn filters_words_should_filter_response() {
     let (tmp_dir, file) =
         setup_tmp_directory(&["LICENSE".to_string(), "file.js".to_string()], "wordlist").unwrap();
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_status(302)
-        .return_body("this is a test")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(302).body("this is a test");
+    });
 
-    let mock_two = Mock::new()
-        .expect_method(GET)
-        .expect_path("/file.js")
-        .return_status(200)
-        .return_body("this is also a test of some import\nwith 2 lines, no less")
-        .create_on(&srv);
+    let mock_two = srv.mock(|when, then| {
+        when.method(GET).path("/file.js");
+        then.status(200)
+            .body("this is also a test of some import\nwith 2 lines, no less");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -149,8 +139,8 @@ fn filters_words_should_filter_response() {
             .not(),
     );
 
-    assert_eq!(mock.times_called(), 1);
-    assert_eq!(mock_two.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(mock_two.hits(), 1);
     teardown_tmp_directory(tmp_dir);
 }
 
@@ -162,19 +152,16 @@ fn filters_size_should_filter_response() {
     let (tmp_dir, file) =
         setup_tmp_directory(&["LICENSE".to_string(), "file.js".to_string()], "wordlist").unwrap();
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_status(302)
-        .return_body("this is a test")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(302).body("this is a test");
+    });
 
-    let mock_two = Mock::new()
-        .expect_method(GET)
-        .expect_path("/file.js")
-        .return_status(200)
-        .return_body("this is also a test of some import\nwith 2 lines, no less")
-        .create_on(&srv);
+    let mock_two = srv.mock(|when, then| {
+        when.method(GET).path("/file.js");
+        then.status(200)
+            .body("this is also a test of some import\nwith 2 lines, no less");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -198,7 +185,65 @@ fn filters_size_should_filter_response() {
             .not(),
     );
 
-    assert_eq!(mock.times_called(), 1);
-    assert_eq!(mock_two.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(mock_two.hits(), 1);
+    teardown_tmp_directory(tmp_dir);
+}
+
+#[test]
+/// create a FeroxResponse that should elicit a true from
+/// SimilarityFilter::should_filter_response
+fn filter_similar_should_filter_response() {
+    let srv = MockServer::start();
+    let (tmp_dir, file) = setup_tmp_directory(
+        &["not-similar".to_string(), "similar".to_string()],
+        "wordlist",
+    )
+    .unwrap();
+
+    // ''.join(random.choices(string.ascii_letters + string.digits + string.whitespace, k=4096))
+    let content = "VCiYFr0HKsEIK6r\r1hJLYnOr90Aji\rDWAjQA3LVAzrluN48FuSPrRpm\n \tV\x0cx\nSCc5sX\nTB\x0c6Of7ns\t2HDwQCduKTqG8gG\x0beszazwljW01H60HMOLziOKwQwEYV7CbrLWQiLeCWKVxX\rvag\nAAEOhjER7gURuGXw\nMyY\t8mSw\x0b\x0bK0Z9G0Pt\x0bJZItAIqAq FxeaoOeLqWVFvxtDFfko0YVYt1I\rNmSXZ4lnOoiBCLbu6TLb80lClhY\tPN7Lp36F786I\nglwRK2oD45EtN SWW IF6uqKdf\x0czAcVycf\x0cBzHYnn1HAkU2Jluos0qwMGJ2m74z\nLd3\x0cIUVZmnRmHHWQGd1u2xmsZR\x0bfnml10ur6J\x0ba8xOZatiY 15Aq3KOGWdD3xQwqo\r5SKnnxH5tqU\rO\rZpJ\n7t7UUgfE\niWFgqWDpMeOG 1248M I\ro5B9Yed\r2aq2\tXxLn31s3hCV WEfQd60DKp6eFhUeUSeXDq6qjgTnWigoCZQERf\rXp7s2L37 iOEMl3\r41\nBShOjLfD8Kj0\rbu0ENreRjP\nY77jsrsaYgOsUrEzw\x0bw3OLi\n8fkddcaOvJeutTy B\rsDMkK\x0cnx2S0N\x0cDaY\x0c9iyo6p4IL\tOC1qgNlWP4VLg\tWmPG46ZMCirth5h4FwkS\nD2WsiEA2Z\n0xbLd7Uww hUQC6 3V\r1SsWem4UcQxG\rfuVvWl\nD9\nDpZQFFgiqhQiq1I0LMAR\r\rKBmj4iurrxaoMHTl9oj\x0b0N3AfD17gyqZiJ67bgizvecsRGeB1f\x0c\nYRvieJqIVHDKOOR\ruhqnVZz4BQ5FFBusz\x0cZl5\x0bt\tbdOUhAAAKyA6Jwl 7OjzojiRHGD6dl ncsgndsKURhFv4\tV5d\n73iPzbT\t8v6IrJtnq\nJuFl7A\x0b\rVnnsjTW0Y4QB1BgCy3B\x0cma7\tpPt5jmcJH7v5J\tYKEXh UqRChBFY5nbFbmXjJYxevPYJmSHC\rDQ4j9de\rTMZ\rtWaPAzkJjH\x0c\nyrEuf9WaMM\trFlKo9r9w\r\nQkQqIEu8Gfr\t aRzvN\r2oZhCyB4fa\np37\tXQi4Wa\no7gHUDQLoRvkK1dy2K3ydrI0O6\rFTGS7oHA\x0bajFOd\rcS5W25tFGhocwxM0\nuugNGDLjBQ\tWGdJV0\x0c\r7bNLs\x0cr deAWt35A4co\x0bPCuYmQ ExxtK\rvpckCyJxLrK5xULK\x0cvqtiGyovHQW8aDjV3rhXhR\nmQvmK\x0czLx\x0cECSYSF5jP35zN VkaRzQ lZ4 l06X4HHpsVn 8y8fGbIP\tRWFUAeFI24\rqN\x0cBW7u7WPMv36BmkgzQ\x0c2\x0cyLf\tYo8iRjE7zMsceym4ZnWg7EsOedh2cES\rz2n\x0cJi52uIPfSkAPzW\rEekjgWdb8y 285F4xae8\n8AiIkT4l3AOy\rT4yeXgaRMCI4t3PkHeFZ\rEb6R4FNCE \nbVil\x0c6qxSVPnU\nh\ttFMNE4\x0c\rwF\t\x0cW5vebbRWG\x0biVZLP\x0ct\x0c5gQ4CJ9KJl\x0cwyIfSIYaCvi4m1r\tJbYqmI0NVO36A\t8BSPNlaKbR73l9mxZxoqD4yca\n5h\r7a0z\tVm34aTy\tnLj5nSrh8er5lN0J7hcjmUk2DL\nyWEVNXTF8RWfC\x0bpcgBQXOQzidyYO\x0bh76UyUPAjELmNoECgGq06hiFGDI LiPZcofhcm\r62fEixIoyG\tmI\x0cYLQvBCbCluGgbm\x0c7GI6\n19il8PdPqss2uQqA5KgkHMIb hh211YuqV9kdmVnwyD63pz3p t58q6kHX\r\teYBrg6eDh\x0bx8\x0cI1SOV3Gt5qubmixHR\rApbgkTQJQ\tX0t11IP55hys2d\x0bF dh7j7G0Ac\x0bQMNvkSU9AV\x0b8mcIPHy9d\x0cyINf5qu\x0cdiBFrhiNRmCZ4r\tSx4N5VOm6KCp2T8bOVEjOR6otPAN5e\n\x0csyJ3giBjkgg 9dYQKq5P75AG5\x0bfD6zZO4DxQ44uX7Kz50dv4ncXQA\rqgHT\rLRcsRl\rW\t7We\tpAEJHMChxwVK\x0cprVvINvolf7hj\tUrob\rW3pXlqKIEQT8t7\x0bGODJanb328OiQCxE\rPfW4j\rl3p\x0cRXDB55u0MN7isBL\ty3UvE1 7I\nfuoZVPzk7az1\rMzA2FROXu0k\rFq pby6pHMqfTQT7iTw izlk0CUpyoUaq5w3UPFK7\rMOPw2cZ6FsVITbCoPhT\rIvuImCFGqmYpE hNevWkPCtwwnx2sX\x0c7oKzBExp32ZpdY\tstuDjSzfalsO1M\x0bNMUegnBDr3Liv3Lv\x0b\n37VZT2LEJ9fNYDi9r\t\x0bYC\rHSt0oJbk\x0b\x0bUdS8eB\nMXBPDEppZjHR7vGZYqX7yFm t1i682AXWf VPTzYTvm6mhOre8\x0bk0spJNYuI\tk\tC1B1N0 AYYDWH\t\tX1TjinXdkXcbFTlIiBLzx\rmUoyx9b7paJSVMX\tfLo8hU1Dmuluyk8R8\x0c4\x0cBe\nCrIMlyek4i\x0bFwuE9\nXUqpVxikH0PZspopUwPM9Kcue\rBh2Mf\rme3h4qelC\x0bEH\x0bkkxi6U\x0cE\x0ctqBgN93 V4ovmocLrK6\ngCQlf\x0cshRVvrPq\x0cOjgbjhSEK8PIx8OYqjjDDkJ0AgLhfbdGw2\nLMv2M0E08PGXnqUyVsjN\t C 4\n80 Fia g\x0b5dEFvyl5Y80U6sMAdHgk2nzC5ElDBhgcBprXC\x0bIMKXyt\x0ce5SkYcRartfblLqD1 A5\nre\x0bj67lJYCs\t8b50xA69eMHqGDLLP8sJceN19kkonjLj\t\rS\tk9sMOeewQHbT \x0cp53aMX9\x0bDYCZWAtdA6h\rAFHDEYFBE1MzdOxMO\x0cvDE7QfLb3jq4s\tI3aVTmDDOQAnuvWb2AGUUP\rf2HinUAiF13LKEfpqcD06S8aQC0Kyl729L7a6CbuoB0GRlJx tD yuTVqD62HuXpfKrDsbejEdp3\rxjc\x0bn4lLNaViizec\rWR\x0cTT5aZ\ny9\rO1qB1XGQPnES\nUhJtU Ll7t3Zglj1IAEx 8Rh3V\x0bfmUSC4\x0bVR9l33LS3bPAJpLbH3Q2\nv2fqMeIt3nGR\x0cgCixM4qzVSx7Yb192a1HWx8nnuWQIEK7QHL6p\x0cD3d0Y1FoZqsmY2U\rspvt3gwKOHR6RaZlmhX\n3bmIEF6\x0b\x0bMXJKOnXPgjkdhun4aGDBw\x0cOEW\repDYTcc48oZ4lg7PukNq7TU\tWP0ZJbzVKK\rxAMaZujwTqQXsXODiE2DdwnstAa6CMYfzj7J\x0c2Q\tY2764IYCy 3Fqm0\x0ckbe7VvfqWUh0\tUlubxZ\rX59MfNSfCfcH8GFZIGIRPt\rZVXfra1 H7VI2yJ\x0cspGDCi\rcgHfZa8528CP9tilUx0ifWPGqskLVDPLJP\nciNxodMQSrJXp\ro\r9aBFHCV\x0cR\rrp\x0bmMfxg5rG\tSuWonbJQlmHQ\ri34w8S\x0cN9Ezj2k2OmLH\x0cEcVUDjXNZIFCtlA843I44p GZyhlOctwpd7 OZnUxk4uacN\r8NihNGO\n9eXy5l6gQe5srySxxvuX5jtCzuJ35xvCfEXYa\x0b2lTDBOAaSYpnl v9L\x0cY8RLg2oE7xeCUbD\tSHKZgeXHZIzYAmA7bsmiZUfzmo5ZZUhtBh4F\x0bTx1\x0bz zQov5mYwfpWJTR2Q\x0bLRXMuBzj\x0bZC\x0b pFNPj8ixWJQggQlr9eNW6SHLJk731nc\x0cBn\x0ckQxg2BdRT\x0bp6lf7G\x0bnIMDeY8w6fUf\x0cjGE1Pfsekv7EYEIHsOAsZb3lBfBPO9\tXpHPBMRmRtzMc5WoX6C5cc\x0cBuTPtPOgXnap1Y3xq7pcMcgu55xblsXEAJKsojjR7aDB\tU84kUKRNEj\n8mcqEyOmvq1WA\na6bhzYf9VQv2aj9KLfByVqUKNFVIc4Mkha\x0c0aCPQSKe0GGwPlSfbtNXhdhxAb3RLf1J\x0cshJzjQe4DCmlRmjt\tlB0BwzBpkg2hTYM\r S\x0cux\x0bj6IcEZ\n\ngQ\rKKgg \rrv4sUMy5sfY1aatjK1MmUyXR\rRHk\x0cqq\x0cD1fy4C0\n\x0byd4SFKOyKJqx2mzI74vPxLLo\x0c0OamjXuUu\nWGkiA70nuf0PGRfwLEBPCMeyneJI1HcIXH\nCTFEIMiAq6fT\rmJgC hXEU\rriAhCm3OzgbcDgvQgDSyUw5jl\x0cTaLOPuFseq\x0cj2npTd57itktTdWBY7sqlOGKNSc\x0ctx2mUoHi31EF3l5lvYPDeG6bIPFwIn7\tG6G \x0bgNkSn89flvqcvI73RA";
+    let mutated = "VCiYFr0HKsEIK6r\r1hJLYnOr90Aji\rDWAjQA3LVAzrluN484327FuSPrRpm\n \tV\x0cx\nSCc5sX\nTB\x0c6Of7ns\t2HDwQCduKTqG8gG\x0beszazwljW01H60HMOLziOKwQwEYV7CbrLWQiLeCWKVxX\rvag\nAAEOhjER7gURuGXw\nMyY\t8mSw\x0b\x0bK0Z9G0Pt\x0bJZItAIqAq FxeaoOeLqWVFvxtDFfko0YVYt1I\rNmSXZ4lnOoiBCLbu6TLb80lClhY\tPN7Lp36F786I\nglwRK2oD45EtN SWW IF6uqKdf\x0czAcVycf\x0cBzHYnn1HAkU2Jluos0qwMGJ2m74z\nLd3\x0cIUVZmnRmHHWQGd1u2xmsZR\x0bfnml10ur6J\x0ba8xOZatiY 15Aq3KOGWdD3xQwqo\r5SKnnxH5tqU\rO\rZpJ\n7t7UUgfE\niWFgqWDpMeOG 1248M I\ro5B9Yed\r2aq2\tXxLn31s3hCV WEfQd60DKp6eFhUeUSeXDq6qjgTnWigoCZQERf\rXp7s2L37 iOEMl3\r41\nBShOjLfD8Kj0\rbu0ENreRjP\nY77jsrsaYgOsUrEzw\x0bw3OLi\n8fkddcaOvJeutTy B\rsDMkK\x0cnx2S0N\x0cDaY\x0c9iyo6p4IL\tOC1qgNlWP4VLg\tWmPG46ZMCirth5h4FwkS\nD2WsiEA2Z\n0xbLd7Uww hUQC6 3V\r1SsWem4UcQxG\rfuVvWl\nD9\nDpZQFFgiqhQiq1I0LMAR\r\rKBmj4iurrxaoMHTl9oj\x0b0N3AfD17gyqZiJ67bgizvecsRGeB1f\x0c\nYRvieJqIVHDKOOR\ruhqnVZz4BQ5FFBusz\x0cZl5\x0bt\tbdOUhAAAKyA6Jwl 7OjzojiRHGD6dl ncsgndsKURhFv4\tV5d\n73iPzbT\t8v6IrJtnq\nJuFl7A\x0b\rVnnsjTW0Y4QB1BgCy3B\x0cma7\tpPt5jmcJH7v5J\tYKEXh UqRChBFY5nbFbmXjJYxevPYJmSHC\rDQ4j9de\rTMZ\rtWaPAzkJjH\x0c\nyrEuf9WaMM\trFlKo9r9w\r\nQkQqIEu8Gfr\t aRzvN\r2oZhCyB4fa\np37\tXQi4Wa\no7gHUDQLoRvkK1dy2K3ydrI0O6\rFTGS7oHA\x0bajFOd\rcS5W25tFGhocwxM0\nuugNGDLjBQ\tWGdJV0\x0c\r7bNLs\x0cr deAWt35A4co\x0bPCuYmQ ExxtK\rvpckCyJxLrK5xULK\x0cvqtiGyovHQW8aDjV3rhXhR\nmQvmK\x0czLx\x0cECSYSF5jP35zN VkaRzQ lZ4 l06X4HHpsVn 8y8fGbIP\tRWFUAeFI24\rqN\x0cBW7u7WPMv36BmkgzQ\x0c2\x0cyLf\tYo8iRjE7zMsceym4ZnWg7EsOedh2cES\rz2n\x0cJi52uIPfSkAPzW\rEekjgWdb8y 285F4xae8\n8AiIkT4l3AOy\rT4yeXgaRMCI4t3PkHeFZ\rEb6R4FNCE \nbVil\x0c6qxSVPnU\nh\ttFMNE4\x0c\rwF\t\x0cW5vebbRWG\x0biVZLP\x0ct\x0c5gQ4CJ9KJl\x0cwyIfSIYaCvi4m1r\tJbYqmI0NVO36A\t8BSPNlaKbR73l9mxZxoqD4yca\n5h\r7a0z\tVm34aTy\tnLj5nSrh8er5lN0J7hcjmUk2DL\nyWEVNXTF8RWfC\x0bpcgBQXOQzidyYO\x0bh76UyUPAjELmNoECgGq06hiFGDI LiPZcofhcm\r62fEixIoyG\tmI\x0cYLQvBCbCluGgbm\x0c7GI6\n19il8PdPqss2uQqA5KgkHMIb hh211YuqV9kdmVnwyD63pz3p t58q6kHX\r\teYBrg6eDh\x0bx8\x0cI1SOV3Gt5qubmixHR\rApbgkTQJQ\tX0t11IP55hys2d\x0bF dh7j7G0Ac\x0bQMNvkSU9AV\x0b8mcIPHy9d\x0cyINf5qu\x0cdiBFrhiNRmCZ4r\tSx4N5VOm6KCp2T8bOVEjOR6otPAN5e\n\x0csyJ3giBjkgg 9dYQKq5P75AG5\x0bfD6zZO4DxQ44uX7Kz50dv4ncXQA\rqgHT\rLRcsRl\rW\t7We\tpAEJHMChxwVK\x0cprVvINvolf7hj\tUrob\rW3pXlqKIEQT8t7\x0bGODJanb328OiQCxE\rPfW4j\rl3p\x0cRXDB55u0MN7isBL\ty3UvE1 7I\nfuoZVPzk7az1\rMzA2FROXu0k\rFq pby6pHMqfTQT7iTw izlk0CUpyoUaq5w3UPFK7\rMOPw2cZ6FsVITbCoPhT\rIvuImCFGqmYpE hNevWkPCtwwnx2sX\x0c7oKzBExp32ZpdY\tstuDjSzfalsO1M\x0bNMUegnBDr3Liv3Lv\x0b\n37VZT2LEJ9fNYDi9r\t\x0bYC\rHSt0oJbk\x0b\x0bUdS8eB\nMXBPDEppZjHR7vGZYqX7yFm t1i682AXWf VPTzYTvm6mhOre8\x0bk0spJNYuI\tk\tC1B1N0 AYYDWH\t\tX1TjinXdkXcbFTlIiBLzx\rmUoyx9b7paJSVMX\tfLo8hU1Dmuluyk8R8\x0c4\x0cBe\nCrIMlyek4i\x0bFwuE9\nXUqpVxikH0PZspopUwPM9Kcue\rBh2Mf\rme3h4qelC\x0bEH\x0bkkxi6U\x0cE\x0ctqBgN93 V4ovmocLrK6\ngCQlf\x0cshRVvrPq\x0cOjgbjhSEK8PIx8OYqjjDDkJ0AgLhfbdGw2\nLMv2M0E08PGXnqUyVsjN\t C 4\n80 Fia g\x0b5dEFvyl5Y80U6sMAdHgk2nzC5ElDBhgcBprXC\x0bIMKXyt\x0ce5SkYcRartfblLqD1 A5\nre\x0bj67lJYCs\t8b50xA69eMHqGDLLP8sJceN19kkonjLj\t\rS\tk9sMOeewQHbT \x0cp53aMX9\x0bDYCZWAtdA6h\rAFHDEYFBE1MzdOxMO\x0cvDE7QfLb3jq4s\tI3aVTmDDOQAnuvWb2AGUUP\rf2HinUAiF13LKEfpqcD06S8aQC0Kyl729L7a6CbuoB0GRlJx tD yuTVqD62HuXpfKrDsbejEdp3\rxjc\x0bn4lLNaViizec\rWR\x0cTT5aZ\ny9\rO1qB1XGQPnES\nUhJtU Ll7t3Zglj1IAEx 8Rh3V\x0bfmUSC4\x0bVR9l33LS3bPAJpLbH3Q2\nv2fqMeIt3nGR\x0cgCixM4qzVSx7Yb192a1HWx8nnuWQIEK7QHL6p\x0cD3d0Y1FoZqsmY2U\rspvt3gwKOHR6RaZlmhX\n3bmIEF6\x0b\x0bMXJKOnXPgjkdhun4aGDBw\x0cOEW\repDYTcc48oZ4lg7PukNq7TU\tWP0ZJbzVKK\rxAMaZujwTqQXsXODiE2DdwnstAa6CMYfzj7J\x0c2Q\tY2764IYCy 3Fqm0\x0ckbe7VvfqWUh0\tUlubxZ\rX59MfNSfCfcH8GFZIGIRPt\rZVXfra1 H7VI2yJ\x0cspGDCi\rcgHfZa8528CP9tilUx0ifWPGqskLVDPLJP\nciNxodMQSrJXp\ro\r9aBFHCV\x0cR\rrp\x0bmMfxg5rG\tSuWonbJQlmHQ\ri34w8S\x0cN9Ezj2k2OmLH\x0cEcVUDjXNZIFCtlA843I44p GZyhlOctwpd7 OZnUxk4uacN\r8NihNGO\n9eXy5l6gQe5srySxxvuX5jtCzuJ35xvCfEXYa\x0b2lTDBOAaSYpnl v9L\x0cY8RLg2oE7xeCUbD\tSHKZgeXHZIzYAmA7bsmiZUfzmo5ZZUhtBh4F\x0bTx1\x0bz zQov5mYwfpWJTR2Q\x0bLRXMuBzj\x0bZC\x0b pFNPj8ixWJQggQlr9eNW6SHLJk731nc\x0cBn\x0ckQxg2BdRT\x0bp6lf7G\x0bnIMDeY8w6fUf\x0cjGE1Pfsekv7EYEIHsOAsZb3lBfBPO9\tXpHPBMRmRtzMc5WoX6C5cc\x0cBuTPtPOgXnap1Y3xq7pcMcgu55xblsXEAJKsojjR7aDB\tU84kUKRNEj\n8mcqEyOmvq1WA\na6bhzYf9VQv2aj9KLfByVqUKNFVIc4Mkha\x0c0aCPQSKe0GGwPlSfbtNXhdhxAb3RLf1J\x0cshJzjQe4DCmlRmjt\tlB0BwzBpkg2hTYM\r S\x0cux\x0bj6IcEZ\n\ngQ\rKKgg \rrv4sUMy5sfY1aatjK1MmUyXR\rRHk\x0cqq\x0cD1fy4C0\n\x0byd4SFKOyKJqx2mzI74vPxLLo\x0c0OamjXuUu\nWGkiA70nuf0PGRfwLEBPCMeyneJI1HcIXH\nCTFEIMiAq6fT\rmJgC hXEU\rriAhCm3OzgbcDgvQgDSyUw5jl\x0cTaimauFseq\x0cj2npTd57itktTdWBY7sqlOGKNSc\x0ctx2mUoHi31EF3l5lvYPDeG6bIPFwIn7\tG6G \x0bgNkSn89flvqcvI73RA";
+
+    let canary = srv.mock(|when, then| {
+        when.method(GET).path("/canary");
+        then.status(200).body(content);
+    });
+
+    // not similar, should see results in output
+    let not_similar = srv.mock(|when, then| {
+        when.method(GET).path("/not-similar");
+        then.status(302).body("this is a test");
+    });
+
+    // similar, should not see results
+    let similar = srv.mock(|when, then| {
+        when.method(GET).path("/similar");
+        then.status(200).body(mutated);
+    });
+
+    let cmd = Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg(srv.url("/"))
+        .arg("--wordlist")
+        .arg(file.as_os_str())
+        .arg("--filter-similar-to")
+        .arg(srv.url("/canary"))
+        .unwrap();
+
+    cmd.assert().success().stdout(
+        predicate::str::contains("/LICfdafdsafdsafadsENSE")
+            .and(predicate::str::contains("302"))
+            .and(predicate::str::contains("14c"))
+            .and(predicate::str::contains("/similar"))
+            .not()
+            .and(predicate::str::contains("4100c"))
+            .not(),
+    );
+
+    assert_eq!(canary.hits(), 1);
+    assert_eq!(similar.hits(), 1);
+    assert_eq!(not_similar.hits(), 1);
     teardown_tmp_directory(tmp_dir);
 }

tests/test_heuristics.rs

@@ -2,7 +2,7 @@ mod utils;
 use assert_cmd::prelude::*;
 use assert_cmd::Command;
 use httpmock::Method::GET;
-use httpmock::{Mock, MockServer, Regex};
+use httpmock::{MockServer, Regex};
 use predicates::prelude::*;
 use utils::{setup_tmp_directory, teardown_tmp_directory};
 
@@ -65,12 +65,10 @@ fn test_one_good_and_one_bad_target_scan_succeeds() -> Result<(), Box<dyn std::e
     let urls = vec![not_real, srv.url("/"), String::from("LICENSE")];
     let (tmp_dir, file) = setup_tmp_directory(&urls, "wordlist")?;
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_status(200)
-        .return_body("this is a test")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200).body("this is a test");
+    });
 
     let mut cmd = Command::cargo_bin("feroxbuster").unwrap();
 
@@ -86,7 +84,51 @@ fn test_one_good_and_one_bad_target_scan_succeeds() -> Result<(), Box<dyn std::e
                 .and(predicate::str::contains("200"))
                 .and(predicate::str::contains("14")),
         );
-    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
+
+    teardown_tmp_directory(tmp_dir);
+    Ok(())
+}
+
+#[test]
+/// test pipes two good targets to the scanner, expected result is that both targets
+/// are scanned successfully and no error is reported (result of issue #169)
+fn test_two_good_targets_scan_succeeds() -> Result<(), Box<dyn std::error::Error>> {
+    let srv = MockServer::start();
+    let srv2 = MockServer::start();
+
+    let urls = vec![srv.url("/"), srv2.url("/"), String::from("LICENSE")];
+    let (tmp_dir, file) = setup_tmp_directory(&urls, "wordlist")?;
+
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200).body("this is a test");
+    });
+
+    let mock2 = srv2.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(403).body("this also is a test");
+    });
+
+    let mut cmd = Command::cargo_bin("feroxbuster").unwrap();
+
+    cmd.arg("--stdin")
+        .arg("--wordlist")
+        .arg(file.as_os_str())
+        .pipe_stdin(file)
+        .unwrap()
+        .assert()
+        .success()
+        .stdout(
+            predicate::str::contains("/LICENSE")
+                .and(predicate::str::contains("200"))
+                .and(predicate::str::contains("403"))
+                .and(predicate::str::contains("14c"))
+                .and(predicate::str::contains("19c")),
+        );
+
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(mock2.hits(), 1);
 
     teardown_tmp_directory(tmp_dir);
     Ok(())
@@ -98,12 +140,11 @@ fn test_static_wildcard_request_found() -> Result<(), Box<dyn std::error::Error>
     let srv = MockServer::start();
     let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path_matches(Regex::new("/[a-zA-Z0-9]{32}/").unwrap())
-        .return_status(200)
-        .return_body("this is a test")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET)
+            .path_matches(Regex::new("/[a-zA-Z0-9]{32}/").unwrap());
+        then.status(200).body("this is a test");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -123,30 +164,28 @@ fn test_static_wildcard_request_found() -> Result<(), Box<dyn std::error::Error>
             .and(predicate::str::contains("(url length: 32)")),
     );
 
-    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
     Ok(())
 }
 
 #[test]
 /// test finds a dynamic wildcard and reports as much to stdout and a file
-fn test_dynamic_wildcard_request_found() -> Result<(), Box<dyn std::error::Error>> {
+fn test_dynamic_wildcard_request_found() {
     let srv = MockServer::start();
-    let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
+    let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist").unwrap();
     let outfile = tmp_dir.path().join("outfile");
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path_matches(Regex::new("/[a-zA-Z0-9]{32}/").unwrap())
-        .return_status(200)
-        .return_body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET)
+            .path_matches(Regex::new("/[a-zA-Z0-9]{32}/").unwrap());
+        then.status(200)
+            .body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA");
+    });
 
-    let mock2 = Mock::new()
-        .expect_method(GET)
-        .expect_path_matches(Regex::new("/[a-zA-Z0-9]{96}/").unwrap())
-        .return_status(200)
-        .return_body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA")
-        .create_on(&srv);
+    let mock2 = srv.mock(|when, then| {
+        when.method(GET).path_matches(Regex::new("/[a-zA-Z0-9]{96}/").unwrap());
+        then.status(200).body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -166,31 +205,19 @@ fn test_dynamic_wildcard_request_found() -> Result<(), Box<dyn std::error::Error
     assert_eq!(contents.contains("WLD"), true);
     assert_eq!(contents.contains("Got"), true);
     assert_eq!(contents.contains("200"), true);
-    assert_eq!(contents.contains("auto-filtering"), true);
     assert_eq!(contents.contains("(url length: 32)"), true);
     assert_eq!(contents.contains("(url length: 96)"), true);
-    assert_eq!(contents.contains("Wildcard response is dynamic"), true);
-    assert_eq!(
-        contents.contains("(14 + url length) responses; toggle this behavior by using"),
-        true
-    );
 
     cmd.assert().success().stdout(
         predicate::str::contains("WLD")
             .and(predicate::str::contains("Got"))
             .and(predicate::str::contains("200"))
             .and(predicate::str::contains("(url length: 32)"))
-            .and(predicate::str::contains("(url length: 96)"))
-            .and(predicate::str::contains("Wildcard response is dynamic;"))
-            .and(predicate::str::contains("auto-filtering"))
-            .and(predicate::str::contains(
-                "(14 + url length) responses; toggle this behavior by using",
-            )),
+            .and(predicate::str::contains("(url length: 96)")),
     );
 
-    assert_eq!(mock.times_called(), 1);
-    assert_eq!(mock2.times_called(), 1);
-    Ok(())
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(mock2.hits(), 1);
 }
 
 #[test]
@@ -199,12 +226,11 @@ fn heuristics_static_wildcard_request_with_dont_filter() -> Result<(), Box<dyn s
     let srv = MockServer::start();
     let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path_matches(Regex::new("/[a-zA-Z0-9]{32}/").unwrap())
-        .return_status(200)
-        .return_body("this is a test")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET)
+            .path_matches(Regex::new("/[a-zA-Z0-9]{32}/").unwrap());
+        then.status(200).body("this is a test");
+    });
 
     Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -217,29 +243,29 @@ fn heuristics_static_wildcard_request_with_dont_filter() -> Result<(), Box<dyn s
 
     teardown_tmp_directory(tmp_dir);
 
-    assert_eq!(mock.times_called(), 0);
+    assert_eq!(mock.hits(), 0);
     Ok(())
 }
 
 #[test]
 /// test finds a static wildcard and reports as much to stdout
-fn heuristics_wildcard_test_with_two_static_wildcards() -> Result<(), Box<dyn std::error::Error>> {
+fn heuristics_wildcard_test_with_two_static_wildcards() {
     let srv = MockServer::start();
-    let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
+    let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist").unwrap();
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path_matches(Regex::new("/[a-zA-Z0-9]{32}/").unwrap())
-        .return_status(200)
-        .return_body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET)
+            .path_matches(Regex::new("/[a-zA-Z0-9]{32}/").unwrap());
+        then.status(200)
+            .body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA");
+    });
 
-    let mock2 = Mock::new()
-        .expect_method(GET)
-        .expect_path_matches(Regex::new("/[a-zA-Z0-9]{96}/").unwrap())
-        .return_status(200)
-        .return_body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA")
-        .create_on(&srv);
+    let mock2 = srv.mock(|when, then| {
+        when.method(GET)
+            .path_matches(Regex::new("/[a-zA-Z0-9]{96}/").unwrap());
+        then.status(200)
+            .body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -263,9 +289,8 @@ fn heuristics_wildcard_test_with_two_static_wildcards() -> Result<(), Box<dyn st
             )),
     );
 
-    assert_eq!(mock.times_called(), 1);
-    assert_eq!(mock2.times_called(), 1);
-    Ok(())
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(mock2.hits(), 1);
 }
 
 #[test]
@@ -275,19 +300,19 @@ fn heuristics_wildcard_test_with_two_static_wildcards_with_quiet_enabled(
     let srv = MockServer::start();
     let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path_matches(Regex::new("/[a-zA-Z0-9]{32}/").unwrap())
-        .return_status(200)
-        .return_body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET)
+            .path_matches(Regex::new("/[a-zA-Z0-9]{32}/").unwrap());
+        then.status(200)
+            .body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA");
+    });
 
-    let mock2 = Mock::new()
-        .expect_method(GET)
-        .expect_path_matches(Regex::new("/[a-zA-Z0-9]{96}/").unwrap())
-        .return_status(200)
-        .return_body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA")
-        .create_on(&srv);
+    let mock2 = srv.mock(|when, then| {
+        when.method(GET)
+            .path_matches(Regex::new("/[a-zA-Z0-9]{96}/").unwrap());
+        then.status(200)
+            .body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -303,32 +328,31 @@ fn heuristics_wildcard_test_with_two_static_wildcards_with_quiet_enabled(
 
     cmd.assert().success().stdout(predicate::str::is_empty());
 
-    assert_eq!(mock.times_called(), 1);
-    assert_eq!(mock2.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(mock2.hits(), 1);
     Ok(())
 }
 
 #[test]
 /// test finds a static wildcard and reports as much to stdout and a file
-fn heuristics_wildcard_test_with_two_static_wildcards_and_output_to_file(
-) -> Result<(), Box<dyn std::error::Error>> {
+fn heuristics_wildcard_test_with_two_static_wildcards_and_output_to_file() {
     let srv = MockServer::start();
-    let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
+    let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist").unwrap();
     let outfile = tmp_dir.path().join("outfile");
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path_matches(Regex::new("/[a-zA-Z0-9]{32}/").unwrap())
-        .return_status(200)
-        .return_body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET)
+            .path_matches(Regex::new("/[a-zA-Z0-9]{32}/").unwrap());
+        then.status(200)
+            .body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA");
+    });
 
-    let mock2 = Mock::new()
-        .expect_method(GET)
-        .expect_path_matches(Regex::new("/[a-zA-Z0-9]{96}/").unwrap())
-        .return_status(200)
-        .return_body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA")
-        .create_on(&srv);
+    let mock2 = srv.mock(|when, then| {
+        when.method(GET)
+            .path_matches(Regex::new("/[a-zA-Z0-9]{96}/").unwrap());
+        then.status(200)
+            .body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -350,10 +374,6 @@ fn heuristics_wildcard_test_with_two_static_wildcards_and_output_to_file(
     assert_eq!(contents.contains("200"), true);
     assert_eq!(contents.contains("(url length: 32)"), true);
     assert_eq!(contents.contains("(url length: 96)"), true);
-    assert_eq!(
-        contents.contains("Wildcard response is static; auto-filtering 46"),
-        true
-    );
 
     cmd.assert().success().stdout(
         predicate::str::contains("WLD")
@@ -366,10 +386,8 @@ fn heuristics_wildcard_test_with_two_static_wildcards_and_output_to_file(
             )),
     );
 
-    assert_eq!(mock.times_called(), 1);
-    assert_eq!(mock2.times_called(), 1);
-
-    Ok(())
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(mock2.hits(), 1);
 }
 
 #[test]
@@ -381,20 +399,20 @@ fn heuristics_wildcard_test_with_redirect_as_response_code(
     let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
     let outfile = tmp_dir.path().join("outfile");
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path_matches(Regex::new("/[a-zA-Z0-9]{32}/").unwrap())
-        .return_status(301)
-        .return_body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET)
+            .path_matches(Regex::new("/[a-zA-Z0-9]{32}/").unwrap());
+        then.status(301)
+            .body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA");
+    });
 
-    let mock2 = Mock::new()
-        .expect_method(GET)
-        .expect_path_matches(Regex::new("/[a-zA-Z0-9]{96}/").unwrap())
-        .return_status(301)
-        .return_header("Location", &srv.url("/some-redirect"))
-        .return_body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA")
-        .create_on(&srv);
+    let mock2 = srv.mock(|when, then| {
+        when.method(GET)
+            .path_matches(Regex::new("/[a-zA-Z0-9]{96}/").unwrap());
+        then.status(301)
+            .header("Location", &srv.url("/some-redirect"))
+            .body("this is a testAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -427,7 +445,7 @@ fn heuristics_wildcard_test_with_redirect_as_response_code(
             .and(predicate::str::contains("WLD")),
     );
 
-    assert_eq!(mock.times_called(), 1);
-    assert_eq!(mock2.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(mock2.hits(), 1);
     Ok(())
 }

tests/test_main.rs

@@ -1,7 +1,7 @@
 mod utils;
 use assert_cmd::Command;
 use httpmock::Method::GET;
-use httpmock::{Mock, MockServer};
+use httpmock::MockServer;
 use predicates::prelude::*;
 use utils::{setup_tmp_directory, teardown_tmp_directory};
 
@@ -10,12 +10,10 @@ use utils::{setup_tmp_directory, teardown_tmp_directory};
 fn main_use_root_owned_file_as_wordlist() -> Result<(), Box<dyn std::error::Error>> {
     let srv = MockServer::start();
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/")
-        .return_status(200)
-        .return_body("this is a test")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/");
+        then.status(200).body("this is a test");
+    });
 
     Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -29,7 +27,7 @@ fn main_use_root_owned_file_as_wordlist() -> Result<(), Box<dyn std::error::Erro
         .stdout(predicate::str::contains("Permission denied (os error 13)"));
 
     // connectivity test hits it once
-    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
     Ok(())
 }
 
@@ -39,12 +37,10 @@ fn main_use_empty_wordlist() -> Result<(), Box<dyn std::error::Error>> {
     let srv = MockServer::start();
     let (tmp_dir, file) = setup_tmp_directory(&[], "wordlist")?;
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/")
-        .return_status(200)
-        .return_body("this is a test")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/");
+        then.status(200).body("this is a test");
+    });
 
     Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -57,7 +53,7 @@ fn main_use_empty_wordlist() -> Result<(), Box<dyn std::error::Error>> {
         .failure()
         .stdout(predicate::str::contains("Did not find any words in"));
 
-    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
 
     teardown_tmp_directory(tmp_dir);
     Ok(())

tests/test_scan_manager.rs

@@ -0,0 +1,130 @@
+mod utils;
+use assert_cmd::Command;
+use httpmock::Method::GET;
+use httpmock::MockServer;
+use predicates::prelude::*;
+use std::fs::{read_to_string, write};
+use std::path::Path;
+use std::time;
+use utils::{setup_tmp_directory, teardown_tmp_directory};
+
+#[test]
+/// pass a known serialized scan with 1 scan complete and 1 not. expect the incomplete scan to
+/// start and the complete to not start. expect the responses, scans, and configuration structures
+/// to be populated based off the contents of the given state file
+fn resume_scan_works() {
+    let srv = MockServer::start();
+    let (tmp_dir, file) =
+        setup_tmp_directory(&["css".to_string(), "stuff".to_string()], "wordlist").unwrap();
+
+    // localhost:PORT/ <- complete
+    // localhost:PORT/js <- will get scanned with /css and /stuff
+    let complete_scan = format!(
+        r#"{{"id":"057016a14769414aac9a7a62707598cb","url":"{}","scan_type":"Directory","complete":true}}"#,
+        srv.url("/")
+    );
+    let incomplete_scan = format!(
+        r#"{{"id":"400b2323a16f43468a04ffcbbeba34c6","url":"{}","scan_type":"Directory","complete":false}}"#,
+        srv.url("/js")
+    );
+    let scans = format!(r#""scans":[{},{}]"#, complete_scan, incomplete_scan);
+
+    let config = format!(
+        r#""config": {{"type":"configuration","wordlist":"{}","config":"","proxy":"","replay_proxy":"","target_url":"{}","status_codes":[200,204,301,302,307,308,401,403,405],"replay_codes":[200,204,301,302,307,308,401,403,405],"filter_status":[],"threads":50,"timeout":7,"verbosity":0,"quiet":false,"json":false,"output":"","debug_log":"","user_agent":"feroxbuster/1.9.0","redirects":false,"insecure":false,"extensions":[],"headers":{{}},"queries":[],"no_recursion":false,"extract_links":false,"add_slash":false,"stdin":false,"depth":2,"scan_limit":1,"filter_size":[],"filter_line_count":[],"filter_word_count":[],"filter_regex":[],"dont_filter":false}}"#,
+        file.to_string_lossy(),
+        srv.url("/")
+    );
+
+    // // localhost:PORT/js/css has already been seen, expect not to be scanned
+    let response = format!(
+        r#"{{"type":"response","url":"{}","path":"/js/css","wildcard":true,"status":301,"content_length":173,"line_count":10,"word_count":16,"headers":{{"server":"nginx/1.16.1"}}}}"#,
+        srv.url("/js/css")
+    );
+    let responses = format!(r#""responses":[{}]"#, response);
+
+    // not scanned because /js is not complete, and /js/stuff response is not known
+    let not_scanned_yet = srv.mock(|when, then| {
+        when.method(GET).path("/js/stuff");
+        then.status(200).body("i expect to be scanned");
+    });
+
+    // will get scanned because /js is not complete, but because response of /js/css is known, the
+    // response will not be in stdout
+    let already_scanned = srv.mock(|when, then| {
+        when.method(GET).path("/js/css");
+        then.status(200);
+    });
+
+    // already scanned because scan on / is complete
+    let also_already_scanned = srv.mock(|when, then| {
+        when.method(GET).path("/css");
+        then.status(200).body("two words");
+    });
+
+    let state_file_contents = format!("{{{},{},{}}}", scans, config, responses);
+    let (tmp_dir2, state_file) = setup_tmp_directory(&[state_file_contents], "state-file").unwrap();
+
+    Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--resume-from")
+        .arg(state_file.as_os_str())
+        .assert()
+        .success()
+        .stdout(
+            predicate::str::contains("/js/stuff")
+                .and(predicate::str::contains("22c"))
+                .and(predicate::str::contains("5w"))
+                .and(predicate::str::contains("/js/css"))
+                .not()
+                .and(predicate::str::contains("2w"))
+                .not()
+                .and(predicate::str::contains("9c"))
+                .not(),
+        );
+
+    teardown_tmp_directory(tmp_dir);
+    teardown_tmp_directory(tmp_dir2);
+
+    assert_eq!(already_scanned.hits(), 1);
+    assert_eq!(also_already_scanned.hits(), 0);
+    assert_eq!(not_scanned_yet.hits(), 1);
+}
+
+#[test]
+/// kick off scan with a time limit;  
+fn time_limit_enforced_when_specified() {
+    let srv = MockServer::start();
+    let (tmp_dir, file) =
+        setup_tmp_directory(&["css".to_string(), "stuff".to_string()], "wordlist").unwrap();
+
+    // ensure the command will run long enough by adding crap to the wordlist
+    let more_words = read_to_string(Path::new("tests/extra-words")).unwrap();
+    write(&file, more_words).unwrap();
+
+    assert!(file.metadata().unwrap().len() > 100); // sanity check on wordlist size
+
+    let now = time::Instant::now();
+    let lower_bound = time::Duration::new(5, 0);
+    let upper_bound = time::Duration::new(6, 0);
+
+    Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg(srv.url("/"))
+        .arg("--wordlist")
+        .arg(file.as_os_str())
+        .arg("--time-limit")
+        .arg("5s")
+        .assert()
+        .failure();
+
+    // expected run time is somewhere in the 30 seconds ballpark (real    0m37.376s)
+    // so if the cmd returns in a significantly shorter amount of time, the test will have
+    // succeeded
+
+    // --time-limit is 5 seconds, so elapsed should be in a window that is greater than 5
+    // but significantly less than 30ish
+    assert!(now.elapsed() > lower_bound && now.elapsed() < upper_bound);
+
+    teardown_tmp_directory(tmp_dir);
+}

tests/test_scanner.rs

@@ -1,7 +1,7 @@
 mod utils;
 use assert_cmd::prelude::*;
 use httpmock::Method::GET;
-use httpmock::{Mock, MockServer};
+use httpmock::MockServer;
 use predicates::prelude::*;
 use std::process::Command;
 use utils::{setup_tmp_directory, teardown_tmp_directory};
@@ -12,12 +12,10 @@ fn scanner_single_request_scan() -> Result<(), Box<dyn std::error::Error>> {
     let srv = MockServer::start();
     let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_status(200)
-        .return_body("this is a test")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200).body("this is a test");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -34,7 +32,7 @@ fn scanner_single_request_scan() -> Result<(), Box<dyn std::error::Error>> {
             .and(predicate::str::contains("14")),
     );
 
-    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
     teardown_tmp_directory(tmp_dir);
     Ok(())
 }
@@ -51,33 +49,26 @@ fn scanner_recursive_request_scan() -> Result<(), Box<dyn std::error::Error>> {
     ];
     let (tmp_dir, file) = setup_tmp_directory(&urls, "wordlist")?;
 
-    let js_mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/js")
-        .return_status(301)
-        .return_header("Location", &srv.url("/js/"))
-        .create_on(&srv);
+    let js_mock = srv.mock(|when, then| {
+        when.method(GET).path("/js");
+        then.status(301).header("Location", &srv.url("/js/"));
+    });
 
-    let js_prod_mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/js/prod")
-        .return_status(301)
-        .return_header("Location", &srv.url("/js/prod/"))
-        .create_on(&srv);
+    let js_prod_mock = srv.mock(|when, then| {
+        when.method(GET).path("/js/prod");
+        then.status(301).header("Location", &srv.url("/js/prod/"));
+    });
 
-    let js_dev_mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/js/dev")
-        .return_status(301)
-        .return_header("Location", &srv.url("/js/dev/"))
-        .create_on(&srv);
+    let js_dev_mock = srv.mock(|when, then| {
+        when.method(GET).path("/js/dev");
+        then.status(301).header("Location", &srv.url("/js/dev/"));
+    });
 
-    let js_dev_file_mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/js/dev/file.js")
-        .return_status(200)
-        .return_body("this is a test and is more bytes than other ones")
-        .create_on(&srv);
+    let js_dev_file_mock = srv.mock(|when, then| {
+        when.method(GET).path("/js/dev/file.js");
+        then.status(200)
+            .body("this is a test and is more bytes than other ones");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -98,10 +89,10 @@ fn scanner_recursive_request_scan() -> Result<(), Box<dyn std::error::Error>> {
             .and(predicate::str::is_match("200.*js/dev/file.js").unwrap()),
     );
 
-    assert_eq!(js_mock.times_called(), 1);
-    assert_eq!(js_prod_mock.times_called(), 1);
-    assert_eq!(js_dev_mock.times_called(), 1);
-    assert_eq!(js_dev_file_mock.times_called(), 1);
+    assert_eq!(js_mock.hits(), 1);
+    assert_eq!(js_prod_mock.hits(), 1);
+    assert_eq!(js_dev_mock.hits(), 1);
+    assert_eq!(js_dev_file_mock.hits(), 1);
 
     teardown_tmp_directory(tmp_dir);
 
@@ -121,33 +112,26 @@ fn scanner_recursive_request_scan_using_only_success_responses(
     ];
     let (tmp_dir, file) = setup_tmp_directory(&urls, "wordlist")?;
 
-    let js_mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/js/")
-        .return_status(200)
-        .return_header("Location", &srv.url("/js/"))
-        .create_on(&srv);
+    let js_mock = srv.mock(|when, then| {
+        when.method(GET).path("/js/");
+        then.status(200).header("Location", &srv.url("/js/"));
+    });
 
-    let js_prod_mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/js/prod/")
-        .return_status(200)
-        .return_header("Location", &srv.url("/js/prod/"))
-        .create_on(&srv);
+    let js_prod_mock = srv.mock(|when, then| {
+        when.method(GET).path("/js/prod/");
+        then.status(200).header("Location", &srv.url("/js/prod/"));
+    });
 
-    let js_dev_mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/js/dev/")
-        .return_status(200)
-        .return_header("Location", &srv.url("/js/dev/"))
-        .create_on(&srv);
+    let js_dev_mock = srv.mock(|when, then| {
+        when.method(GET).path("/js/dev/");
+        then.status(200).header("Location", &srv.url("/js/dev/"));
+    });
 
-    let js_dev_file_mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/js/dev/file.js")
-        .return_status(200)
-        .return_body("this is a test and is more bytes than other ones")
-        .create_on(&srv);
+    let js_dev_file_mock = srv.mock(|when, then| {
+        when.method(GET).path("/js/dev/file.js");
+        then.status(200)
+            .body("this is a test and is more bytes than other ones");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -169,10 +153,10 @@ fn scanner_recursive_request_scan_using_only_success_responses(
             .and(predicate::str::is_match("200.*js/dev/file.js").unwrap()),
     );
 
-    assert_eq!(js_mock.times_called(), 1);
-    assert_eq!(js_prod_mock.times_called(), 1);
-    assert_eq!(js_dev_mock.times_called(), 1);
-    assert_eq!(js_dev_file_mock.times_called(), 1);
+    assert_eq!(js_mock.hits(), 1);
+    assert_eq!(js_prod_mock.hits(), 1);
+    assert_eq!(js_dev_mock.hits(), 1);
+    assert_eq!(js_dev_file_mock.hits(), 1);
 
     teardown_tmp_directory(tmp_dir);
 
@@ -185,12 +169,10 @@ fn scanner_single_request_scan_with_file_output() -> Result<(), Box<dyn std::err
     let srv = MockServer::start();
     let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_status(200)
-        .return_body("this is a test")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200).body("this is a test");
+    });
 
     let outfile = tmp_dir.path().join("output");
 
@@ -211,7 +193,7 @@ fn scanner_single_request_scan_with_file_output() -> Result<(), Box<dyn std::err
     assert!(contents.contains("200"));
     assert!(contents.contains("14"));
 
-    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
     teardown_tmp_directory(tmp_dir);
     Ok(())
 }
@@ -223,12 +205,10 @@ fn scanner_single_request_scan_with_file_output_and_tack_q(
     let srv = MockServer::start();
     let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_status(200)
-        .return_body("this is a test")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200).body("this is a test");
+    });
 
     let outfile = tmp_dir.path().join("output");
 
@@ -249,7 +229,7 @@ fn scanner_single_request_scan_with_file_output_and_tack_q(
     let url = srv.url("/LICENSE");
     assert!(contents.contains(&url));
 
-    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
     teardown_tmp_directory(tmp_dir);
     Ok(())
 }
@@ -261,12 +241,10 @@ fn scanner_single_request_scan_with_invalid_file_output() -> Result<(), Box<dyn
     let srv = MockServer::start();
     let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_status(200)
-        .return_body("this is a test")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200).body("this is a test");
+    });
 
     let outfile = tmp_dir.path(); // outfile is a directory
 
@@ -285,7 +263,7 @@ fn scanner_single_request_scan_with_invalid_file_output() -> Result<(), Box<dyn
     let contents = std::fs::read_to_string(outfile);
     assert!(contents.is_err());
 
-    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
     teardown_tmp_directory(tmp_dir);
     Ok(())
 }
@@ -296,12 +274,10 @@ fn scanner_single_request_quiet_scan() -> Result<(), Box<dyn std::error::Error>>
     let srv = MockServer::start();
     let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_status(200)
-        .return_body("this is a test")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200).body("this is a test");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -321,7 +297,7 @@ fn scanner_single_request_quiet_scan() -> Result<(), Box<dyn std::error::Error>>
             .not(),
     );
 
-    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
     teardown_tmp_directory(tmp_dir);
     Ok(())
 }
@@ -334,12 +310,10 @@ fn scanner_single_request_returns_301_without_location_header(
     let srv = MockServer::start();
     let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_body("this is a test")
-        .return_status(301)
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(301).body("this is a test");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -359,7 +333,52 @@ fn scanner_single_request_returns_301_without_location_header(
             .and(predicate::str::contains("14")),
     );
 
-    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
+    teardown_tmp_directory(tmp_dir);
+    Ok(())
+}
+
+#[test]
+/// send a single valid request, expect a 200 response that then gets routed to the replay
+/// proxy
+fn scanner_single_request_replayed_to_proxy() -> Result<(), Box<dyn std::error::Error>> {
+    let srv = MockServer::start();
+    let proxy = MockServer::start();
+    let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
+
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200).body("this is a test");
+    });
+
+    let mock_two = proxy.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200).body("this is a test");
+    });
+
+    let cmd = Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg(srv.url("/"))
+        .arg("--wordlist")
+        .arg(file.as_os_str())
+        .arg("--replay-proxy")
+        .arg(format!("http://{}", proxy.address().to_string()))
+        .arg("--replay-codes")
+        .arg("200")
+        .unwrap();
+
+    cmd.assert()
+        .success()
+        .stdout(
+            predicate::str::contains("/LICENSE")
+                .and(predicate::str::contains("200"))
+                .and(predicate::str::contains("14c")),
+        )
+        .stderr(predicate::str::contains("Replay Proxy Codes"));
+
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(mock_two.hits(), 1);
     teardown_tmp_directory(tmp_dir);
     Ok(())
 }
@@ -371,19 +390,15 @@ fn scanner_single_request_scan_with_filtered_result() -> Result<(), Box<dyn std:
     let (tmp_dir, file) =
         setup_tmp_directory(&["LICENSE".to_string(), "ignored".to_string()], "wordlist")?;
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_status(200)
-        .return_body("this is a not a test")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200).body("this is a not a test");
+    });
 
-    let filtered_mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/ignored")
-        .return_status(200)
-        .return_body("this is a test")
-        .create_on(&srv);
+    let filtered_mock = srv.mock(|when, then| {
+        when.method(GET).path("/ignored");
+        then.status(200).body("this is a test");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -406,33 +421,106 @@ fn scanner_single_request_scan_with_filtered_result() -> Result<(), Box<dyn std:
             .not(),
     );
 
-    assert_eq!(mock.times_called(), 1);
-    assert_eq!(filtered_mock.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(filtered_mock.hits(), 1);
     teardown_tmp_directory(tmp_dir);
     Ok(())
 }
 
 #[test]
-/// send a single valid request, expect a 200 response that then gets routed to the replay
-/// proxy
-fn scanner_single_request_replayed_to_proxy() -> Result<(), Box<dyn std::error::Error>> {
+/// send a single valid request, get a response, and write the logging messages to disk
+fn scanner_single_request_scan_with_debug_logging() {
     let srv = MockServer::start();
-    let proxy = MockServer::start();
-    let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
+    let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist").unwrap();
 
-    let mock = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_status(200)
-        .return_body("this is a test")
-        .create_on(&srv);
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200).body("this is a test");
+    });
 
-    let mock_two = Mock::new()
-        .expect_method(GET)
-        .expect_path("/LICENSE")
-        .return_status(200)
-        .return_body("this is a test")
-        .create_on(&proxy);
+    let outfile = tmp_dir.path().join("debug.log");
+
+    Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg(srv.url("/"))
+        .arg("--wordlist")
+        .arg(file.as_os_str())
+        .arg("-vvvv")
+        .arg("--debug-log")
+        .arg(outfile.as_os_str())
+        .unwrap();
+
+    let contents = std::fs::read_to_string(outfile).unwrap();
+    println!("{}", contents);
+    assert!(contents.starts_with("Configuration {"));
+    assert!(contents.contains("TRC"));
+    assert!(contents.contains("DBG"));
+    assert!(contents.contains("INF"));
+    assert!(contents.contains("feroxbuster All scans complete!"));
+    assert!(contents.contains("feroxbuster exit: terminal_input_handler"));
+
+    assert_eq!(mock.hits(), 1);
+    teardown_tmp_directory(tmp_dir);
+}
+
+#[test]
+/// send a single valid request, get a response, and write the logging messages to disk as NDJSON
+fn scanner_single_request_scan_with_debug_logging_as_json() {
+    let srv = MockServer::start();
+    let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist").unwrap();
+
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200).body("this is a test");
+    });
+
+    let outfile = tmp_dir.path().join("debug.log");
+
+    Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg(srv.url("/"))
+        .arg("--wordlist")
+        .arg(file.as_os_str())
+        .arg("-vvvv")
+        .arg("--debug-log")
+        .arg(outfile.as_os_str())
+        .arg("--json")
+        .unwrap();
+
+    let contents = std::fs::read_to_string(outfile).unwrap();
+    println!("{}", contents);
+    assert!(contents.starts_with("{\"type\":\"configuration\""));
+    assert!(contents.contains("\"level\":\"TRACE\""));
+    assert!(contents.contains("\"level\":\"DEBUG\""));
+    assert!(contents.contains("\"level\":\"INFO\""));
+    assert!(contents.contains("time_offset"));
+    assert!(contents.contains("\"module\":\"feroxbuster::scanner\""));
+    assert!(contents.contains("All scans complete!"));
+    assert!(contents.contains("exit: terminal_input_handler"));
+
+    assert_eq!(mock.hits(), 1);
+    teardown_tmp_directory(tmp_dir);
+}
+
+#[test]
+/// send a single valid request, filter the response by regex, expect one out of 2 urls
+fn scanner_single_request_scan_with_regex_filtered_result() {
+    let srv = MockServer::start();
+    let (tmp_dir, file) =
+        setup_tmp_directory(&["LICENSE".to_string(), "ignored".to_string()], "wordlist").unwrap();
+
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200).body("this is a test");
+    });
+
+    let filtered_mock = srv.mock(|when, then| {
+        when.method(GET).path("/ignored");
+        then.status(200)
+            .body("this is a test\nThat rug really tied the room together");
+    });
 
     let cmd = Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -440,23 +528,21 @@ fn scanner_single_request_replayed_to_proxy() -> Result<(), Box<dyn std::error::
         .arg(srv.url("/"))
         .arg("--wordlist")
         .arg(file.as_os_str())
-        .arg("--replay-proxy")
-        .arg(format!("http://{}", proxy.address().to_string()))
-        .arg("--replay-codes")
-        .arg("200")
+        .arg("--filter-regex")
+        .arg("'That rug.*together$'")
         .unwrap();
 
-    cmd.assert()
-        .success()
-        .stdout(
-            predicate::str::contains("/LICENSE")
-                .and(predicate::str::contains("200"))
-                .and(predicate::str::contains("14")),
-        )
-        .stderr(predicate::str::contains("Replay Proxy Codes"));
+    cmd.assert().success().stdout(
+        predicate::str::contains("/LICENSE")
+            .and(predicate::str::contains("200"))
+            .and(predicate::str::contains("20"))
+            .and(predicate::str::contains("ignored"))
+            .not()
+            .and(predicate::str::contains(" 14 "))
+            .not(),
+    );
 
-    assert_eq!(mock.times_called(), 1);
-    assert_eq!(mock_two.times_called(), 1);
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(filtered_mock.hits(), 1);
     teardown_tmp_directory(tmp_dir);
-    Ok(())
 }