Merge pull request #140 from epi052/136-add-regex-filter

add regex filter

.github/pull_request_template.md

@@ -11,7 +11,7 @@ Long form explanations of most of the items below can be found in the [CONTRIBUT
 
 ## Static analysis checks
 - [ ] All rust files are formatted using `cargo fmt`
-- [ ] All `clippy` checks pass when running `cargo clippy --all-targets --all-features -- -D warnings -A clippy::unnecessary_unwrap`
+- [ ] All `clippy` checks pass when running `cargo clippy --all-targets --all-features -- -D warnings -A clippy::deref_addrof`
 - [ ] All existing tests pass
 
 ## Documentation

.github/workflows/build.yml

@@ -41,6 +41,9 @@ jobs:
           use-cross: true
           command: build
           args: --release --target=${{ matrix.target }}
+      - name: Strip symbols from binary
+        run: |
+          strip -s ${{ matrix.path }}
       - name: Build tar.gz for homebrew installs
         if: matrix.type == 'ubuntu-x64'
         run: |
@@ -83,6 +86,9 @@ jobs:
           use-cross: true
           command: build
           args: --release --target=x86_64-apple-darwin
+      - name: Strip symbols from binary
+        run: |
+          strip -u -r target/x86_64-apple-darwin/release/feroxbuster
       - name: Build tar.gz for homebrew installs
         run: |
           tar czf x86_64-macos-feroxbuster.tar.gz -C target/x86_64-apple-darwin/release feroxbuster

.github/workflows/check.yml

@@ -1,6 +1,6 @@
 name: CI Pipeline
 
-on: [push]
+on: [push, pull_request]
 
 jobs:
   check:
@@ -61,4 +61,4 @@ jobs:
       - uses: actions-rs/cargo@v1
         with:
           command: clippy
-          args: --all-targets --all-features -- -D warnings -A clippy::unnecessary_unwrap
+          args: --all-targets --all-features -- -D warnings -A clippy::unnecessary_unwrap -A clippy::deref_addrof

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "feroxbuster"
-version = "1.0.4"
+version = "1.8.0"
 authors = ["Ben 'epi' Risher <epibar052@gmail.com>"]
 license = "MIT"
 edition = "2018"
@@ -19,17 +19,21 @@ futures = { version = "0.3"}
 tokio = { version = "0.2", features = ["full"] }
 tokio-util = {version = "0.3", features = ["codec"]}
 log = "0.4"
-env_logger = "0.7"
+env_logger = "0.8"
 reqwest = { version = "0.10", features = ["socks"] }
 clap = "2"
 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"
 openssl = { version = "0.10", features = ["vendored"] }
 dirs = "3.0"
+regex = "1"
+crossterm = "0.18"
+rlimit = "0.5"
 
 [dev-dependencies]
 tempfile = "3.1"

README.md

@@ -59,26 +59,37 @@ This attack is also known as Predictable Resource Location, File Enumeration, Di
 
 📖 Table of Contents
 -----------------
-- [Downloads](#-downloads)
 - [Installation](#-installation)
     - [Download a Release](#download-a-release)
+    - [Snap Install](#snap-install)
     - [Homebrew on MacOS and Linux](#homebrew-on-macos-and-linux)
     - [Cargo Install](#cargo-install)
     - [apt Install](#apt-install)
+    - [AUR Install](#aur-install)
     - [Docker Install](#docker-install)
-- [Configuration](#-configuration)
+- [Configuration](#%EF%B8%8F-configuration)
     - [Default Values](#default-values)
+    - [Threads and Connection Limits At A High-Level](#threads-and-connection-limits-at-a-high-level)
     - [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)
     - [Pass auth token via query parameter](#pass-auth-token-via-query-parameter)
+    - [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)
+    - [Filter Response Using a Regular Expression (new in `v1.8.0`)](#filter-response-using-a-regular-expression-new-in-v180)
+    - [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)
 - [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)
 
 ## 💿 Installation
 
@@ -86,25 +97,9 @@ This attack is also known as Predictable Resource Location, File Enumeration, Di
 
 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 x86
+#### Linux (32 and 64-bit) & MacOS
 ```
-wget -sLO https://github.com/epi052/feroxbuster/releases/latest/download/x86-linux-feroxbuster.zip
-unzip x86-linux-feroxbuster.zip
-./feroxbuster -V
-```
-#### Linux x86_64
-
-```
-wget -sLO https://github.com/epi052/feroxbuster/releases/latest/download/x86_64-linux-feroxbuster.zip
-unzip x86_64-linux-feroxbuster.zip
-./feroxbuster -V
-```
-
-#### MacOS x86_64
-```
-wget -sLO https://github.com/epi052/feroxbuster/releases/latest/download/x86_64-macos-feroxbuster.zip
-unzip x86_64-macos-feroxbuster.zip
-./feroxbuster -V
+curl -sL https://raw.githubusercontent.com/epi052/feroxbuster/master/install-nix.sh | bash
 ```
 
 #### Windows x86
@@ -123,9 +118,34 @@ Expand-Archive .\feroxbuster.zip
 .\feroxbuster\feroxbuster.exe -V
 ```
 
+### Snap Install
+
+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 
+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`
+
+```
+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.
+
+```
+cp /path/to/the/wordlist ~/snap/feroxbuster/common
+./feroxbuster -u http://localhost -w ~/snap/feroxbuster/common/wordlist
+``` 
+
 ### Homebrew on MacOS and Linux
 
-Installable by Homebrew throughout own formulas:
+Install using Homebrew via tap
 
 🍏 [MacOS](https://github.com/TGotwig/homebrew-feroxbuster/blob/main/feroxbuster.rb)
 
@@ -159,6 +179,14 @@ unzip feroxbuster_amd64.deb.zip
 sudo apt install ./feroxbuster_amd64.deb
 ```
 
+### AUR Install
+
+Install `feroxbuster-git` on Arch Linux with your AUR helper of choice:
+
+```
+yay -S feroxbuster-git
+```
+
 ### Docker Install
 
 > The following steps assume you have docker installed / setup
@@ -223,12 +251,30 @@ Configuration begins with with the following built-in default values baked into
 - wordlist: `/usr/share/seclists/Discovery/Web-Content/raft-medium-directories.txt`
 - threads: `50`
 - verbosity: `0` (no logging enabled)
-- statuscodes: `200 204 301 302 307 308 401 403 405`
-- useragent: `feroxbuster/VERSION`
+- scan_limit: `0` (no limit imposed on concurrent scans)
+- status_codes: `200 204 301 302 307 308 401 403 405`
+- user_agent: `feroxbuster/VERSION`
 - recursion depth: `4`
 - auto-filter wildcards - `true`
 - output: `stdout`
 
+### 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.
+
+#### 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
+
+#### Threads and Connection Limits: The Implementation
+
+* Threads: The `-t` option specifies the maximum amount of active threads *per-directory* during a scan
+* Connection Limits: The `-L` option specifies the maximum amount of active connections per thread
+
+#### 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:
+
 ### 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.  
@@ -239,6 +285,11 @@ built-in defaults.
 - The same directory as the `feroxbuster` executable (per-user)
 - The user's current working directory (per-target)
 
+> `CONFIG_DIR` is defined as the following:
+> - Linux: `$XDG_CONFIG_HOME` or `$HOME/.config` i.e. `/home/bob/.config`
+> - 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 no configuration file is found, nothing happens at this stage.
@@ -269,23 +320,33 @@ A pre-made configuration file with examples of all available settings can be fou
 # Any setting used here can be overridden by the corresponding command line option/argument
 #
 # wordlist = "/wordlists/jhaddix/all.txt"
-# statuscodes = [200, 500]
+# status_codes = [200, 500]
+# filter_status = [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"
-# useragent = "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:47.0) Gecko/20100101 Firefox/47.0"
+# 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
 # extensions = ["php", "html"]
-# norecursion = true
-# addslash = true
+# no_recursion = true
+# add_slash = true
 # stdin = true
-# dontfilter = true
+# dont_filter = true
+# extract_links = true
 # depth = 1
-# sizefilters = [5174]
+# filter_size = [5174]
+# filter_regex = ["^ignore me$"]
+# filter_word_count = [993]
+# filter_line_count = [35, 36]
 # queries = [["name","value"], ["rick", "astley"]]
 
 # headers can be specified on multiple lines or as an inline table
@@ -310,35 +371,57 @@ USAGE:
     feroxbuster [FLAGS] [OPTIONS] --url <URL>...
 
 FLAGS:
-    -f, --addslash       Append / to each request
-    -D, --dontfilter     Don't auto-filter wildcard responses
-    -h, --help           Prints help information
-    -k, --insecure       Disables TLS certificate validation
-    -n, --norecursion    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)
+    -f, --add-slash        Append / to each request
+    -D, --dont-filter      Don't auto-filter wildcard responses
+    -e, --extract-links    Extract links from response body (html, javascript, etc...); make new requests based on
+                           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. [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)
+    -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://host:port)
     -Q, --query <QUERY>...                  Specify URL query parameters (ex: -Q token=stuff -Q secret=key)
-    -S, --sizefilter <SIZE>...              Filter out messages of a particular size (ex: -S 5120 -S 4927,1970)
-    -s, --statuscodes <STATUS_CODE>...      Status Codes of interest (default: 200 204 301 302 307 308 401 403 405)
+    -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
+    -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)
     -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, --useragent <USER_AGENT>            Sets the User-Agent (default: feroxbuster/VERSION)
+    -a, --user-agent <USER_AGENT>           Sets the User-Agent (default: feroxbuster/VERSION)
     -w, --wordlist <FILE>                   Path to the wordlist
 ```
 
 ## 🧰 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:
@@ -357,10 +440,41 @@ 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
 
 ```
-./feroxbuster -u http://[::1] --norecursion -vv
+./feroxbuster -u http://[::1] --no-recursion -vv
 ```
 
 ### Read urls from STDIN; pipe only resulting urls out to another tool
@@ -381,12 +495,60 @@ cat targets | ./feroxbuster --stdin --quiet -s 200 301 302 --redirects -x js | f
 ./feroxbuster -u http://127.1 --proxy socks5://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
 ```
 
+### 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 
+`--scan-limit`.
+
+```
+./feroxbuster -u http://127.1 --scan-limit 2
+```
+
+![limit-demo](img/limit-demo.gif)
+
+### 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.
+
+```
+./feroxbuster -u http://127.1 --filter-status 301
+```
+
+### 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
+```
+
+### 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.  
+
+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.
+
+![replay-proxy-demo](img/replay-proxy-demo.gif)
 
 ## 🧐 Comparison w/ Similar Tools
 
@@ -402,29 +564,111 @@ a few of the use-cases in which feroxbuster may be a better fit:
 - 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 **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                                         | ✔ | ✔ |   |
-| blacklist status codes (in addition to whitelist)   |   | ✔ | ✔ |
-| 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 by response size                             | ✔ |   | ✔ |
-| 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                                                      | ✔ | ✔ |   |
+| 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                                 |   |   | ✔ |
 
 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)
+
+### No file descriptors available
+
+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 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` 😕.
+
+##### 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.  
+
+- `*` represents all users
+- `hard` and `soft` indicate the hard and soft limits for the OS 
+- `nofile` is the number of open files option. 
+
+```
+/etc/security/limits.conf
+-------------------------
+...
+*        soft nofile 4096
+*        hard nofile 8192
+...
+```
+
+##### Use `ulimit` directly
+
+A faster option, that is **not** persistent, is to simply use the `ulimit` command to change the setting.
+
+```
+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.  
+
+> 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 ✨
+
+##### 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
+
+- `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.
+
+```
+sudo sysctl net.ipv4.ip_local_port_range="15000 61000"
+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.
+
+```
+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.
+
+![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.

ferox-config.toml.example

@@ -8,23 +8,33 @@
 # Any setting used here can be overridden by the corresponding command line option/argument
 #
 # wordlist = "/wordlists/seclists/Discovery/Web-Content/raft-medium-directories.txt"
-# statuscodes = [200, 500]
+# status_codes = [200, 500]
+# filter_status = [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"
-# useragent = "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:47.0) Gecko/20100101 Firefox/47.0"
+# 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
 # extensions = ["php", "html"]
-# norecursion = true
-# addslash = true
+# no_recursion = true
+# add_slash = true
 # stdin = true
-# dontfilter = true
+# dont_filter = true
+# extract_links = true
 # depth = 1
-# sizefilters = [5174]
+# filter_size = [5174]
+# filter_regex = ["^ignore me$"]
+# filter_word_count = [993]
+# filter_line_count = [35, 36]
 # queries = [["name","value"], ["rick", "astley"]]
 
 # headers can be specified on multiple lines or as an inline table

install-nix.sh

@@ -0,0 +1,56 @@
+#!/usr/bin/env bash
+
+BASE_URL=https://github.com/epi052/feroxbuster/releases/latest/download
+
+MAC_ZIP=x86_64-macos-feroxbuster.zip
+MAC_URL="${BASE_URL}/${MAC_ZIP}"
+
+LIN32_ZIP=x86-linux-feroxbuster.zip
+LIN32_URL="${BASE_URL}/${LIN32_ZIP}"
+
+LIN64_ZIP=x86_64-linux-feroxbuster.zip
+LIN64_URL="${BASE_URL}/${LIN64_ZIP}"
+
+EMOJI_URL=https://gist.github.com/epi052/8196b550ea51d0907ad4b93751b1b57d/raw/6112c9f32ae07922983fdc549c54fd3fb9a38e4c/NotoColorEmoji.ttf
+
+echo "[+] Installing feroxbuster!"
+
+if [[ "$(uname)" == "Darwin" ]]; then
+    echo "[=] Found MacOS, downloading from ${MAC_URL}"
+
+    curl -sLO "${MAC_URL}"
+    unzip -o "${MAC_ZIP}" > /dev/null
+    rm "${MAC_ZIP}"
+elif [[ "$(expr substr $(uname -s) 1 5)" == "Linux" ]]; then
+    if [[ $(getconf LONG_BIT) == 32 ]]; then
+        echo "[=] Found 32-bit Linux, downloading from ${LIN32_URL}"
+
+        curl -sLO "${LIN32_URL}"
+        unzip -o "${LIN32_ZIP}" > /dev/null
+        rm "${LIN32_ZIP}"
+    else
+        echo "[=] Found 64-bit Linux, downloading from ${LIN64_URL}"
+
+        curl -sLO "${LIN64_URL}"
+        unzip -o "${LIN64_ZIP}" > /dev/null
+        rm "${LIN64_ZIP}"
+    fi
+
+    echo "[=] Installing Noto Emoji Font"
+    mkdir -p ~/.fonts
+    pushd ~/.fonts 2>&1 >/dev/null
+
+    curl -sLO "${EMOJI_URL}"
+
+    fc-cache -f -v >/dev/null
+
+    popd 2>&1 >/dev/null
+    echo "[+] Noto Emoji Font installed"
+fi
+
+chmod +x ./feroxbuster
+
+echo "[+] Installed feroxbuster version $(./feroxbuster -V)"
+
+
+

snapcraft.yaml

@@ -0,0 +1,41 @@
+name: feroxbuster
+version: git
+summary: A simple, fast, recursive content discovery tool written in Rust
+description: |
+  feroxbuster is a tool designed to perform 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.
+
+  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.
+
+
+base: core18
+
+plugs:
+  etc-feroxbuster:
+    interface: system-files
+    read:
+    - /etc/feroxbuster
+  dot-config-feroxbuster:
+    interface: personal-files
+    read:
+    - $HOME/.config/feroxbuster
+
+architectures:
+  - build-on: amd64
+  - build-on: i386
+
+parts:
+  feroxbuster:
+    plugin: rust
+    source: .
+
+apps:
+  feroxbuster:
+    command: bin/feroxbuster
+    plugs:
+      - etc-feroxbuster
+      - dot-config-feroxbuster
+      - network

src/banner.rs

@@ -1,4 +1,9 @@
-use crate::{config::Configuration, utils::status_colorizer, VERSION};
+use crate::config::{Configuration, CONFIGURATION};
+use crate::utils::{make_request, status_colorizer};
+use console::style;
+use reqwest::{Client, Url};
+use serde_json::Value;
+use std::io::Write;
 
 /// macro helper to abstract away repetitive string formatting
 macro_rules! format_banner_entry_helper {
@@ -40,239 +45,655 @@ macro_rules! format_banner_entry {
     };
 }
 
+/// Url used to query github's api; specifically used to look for the latest tagged release name
+const UPDATE_URL: &str = "https://api.github.com/repos/epi052/feroxbuster/releases/latest";
+
+/// Simple enum to hold three different update states
+#[derive(Debug)]
+enum UpdateStatus {
+    /// this version and latest release are the same
+    UpToDate,
+
+    /// this version and latest release are not the same
+    OutOfDate,
+
+    /// some error occurred during version check
+    Unknown,
+}
+
+/// Makes a request to the given url, expecting to receive a JSON response that contains a field
+/// named `tag_name` that holds a value representing the latest tagged release of this tool.
+///
+/// ex: v1.1.0
+///
+/// Returns `UpdateStatus`
+async fn needs_update(client: &Client, url: &str, bin_version: &str) -> UpdateStatus {
+    log::trace!("enter: needs_update({:?}, {})", client, url);
+
+    let unknown = UpdateStatus::Unknown;
+
+    let api_url = match Url::parse(url) {
+        Ok(url) => url,
+        Err(e) => {
+            log::error!("{}", e);
+            log::trace!("exit: needs_update -> {:?}", unknown);
+            return unknown;
+        }
+    };
+
+    if let Ok(response) = make_request(&client, &api_url).await {
+        let body = response.text().await.unwrap_or_default();
+
+        let json_response: Value = serde_json::from_str(&body).unwrap_or_default();
+
+        if json_response.is_null() {
+            // unwrap_or_default above should result in a null value for the json_response variable
+            log::error!("Could not parse JSON from response body");
+            log::trace!("exit: needs_update -> {:?}", unknown);
+            return unknown;
+        }
+
+        let latest_version = match json_response["tag_name"].as_str() {
+            Some(tag) => tag.trim_start_matches('v'),
+            None => {
+                log::error!("Could not get version field from JSON response");
+                log::debug!("{}", json_response);
+                log::trace!("exit: needs_update -> {:?}", unknown);
+                return unknown;
+            }
+        };
+
+        // if we've gotten this far, we have a string in the form of X.X.X where X is a number
+        // all that's left is to compare the current version with the version found above
+
+        return if latest_version == bin_version {
+            // there's really only two possible outcomes if we accept that the tag conforms to
+            // the X.X.X pattern:
+            //   1. the version strings match, meaning we're up to date
+            //   2. the version strings do not match, meaning we're out of date
+            //
+            // except for developers working on this code, nobody should ever be in a situation
+            // where they have a version greater than the latest tagged release
+            log::trace!("exit: needs_update -> UpdateStatus::UpToDate");
+            UpdateStatus::UpToDate
+        } else {
+            log::trace!("exit: needs_update -> UpdateStatus::OutOfDate");
+            UpdateStatus::OutOfDate
+        };
+    }
+
+    log::trace!("exit: needs_update -> {:?}", unknown);
+    unknown
+}
+
 /// Prints the banner to stdout.
 ///
 /// Only prints those settings which are either always present, or passed in by the user.
-pub fn initialize(targets: &[String], config: &Configuration) {
+pub async fn initialize<W>(targets: &[String], config: &Configuration, version: &str, mut writer: W)
+where
+    W: Write,
+{
     let artwork = format!(
         r#"
  ___  ___  __   __     __      __         __   ___
 |__  |__  |__) |__) | /  `    /  \ \_/ | |  \ |__
 |    |___ |  \ |  \ | \__,    \__/ / \ | |__/ |___
 by Ben "epi" Risher {}                  ver: {}"#,
-        '\u{1F913}', VERSION
+        '\u{1F913}', version
     );
 
+    let status = needs_update(&CONFIGURATION.client, UPDATE_URL, version).await;
+
     let top = "───────────────────────────┬──────────────────────";
+    let addl_section = "──────────────────────────────────────────────────";
     let bottom = "───────────────────────────┴──────────────────────";
 
-    eprintln!("{}", artwork);
-    eprintln!("{}", top);
+    writeln!(&mut writer, "{}", artwork).unwrap_or_default();
+    writeln!(&mut writer, "{}", top).unwrap_or_default();
 
     // begin with always printed items
     for target in targets {
-        eprintln!(
+        writeln!(
+            &mut writer,
             "{}",
             format_banner_entry!("\u{1F3af}", "Target Url", target)
-        ); // 🎯
+        )
+        .unwrap_or_default(); // 🎯
     }
 
     let mut codes = vec![];
 
-    for code in &config.statuscodes {
+    for code in &config.status_codes {
         codes.push(status_colorizer(&code.to_string()))
     }
 
-    eprintln!(
+    writeln!(
+        &mut writer,
         "{}",
         format_banner_entry!("\u{1F680}", "Threads", config.threads)
-    ); // 🚀
-    eprintln!(
+    )
+    .unwrap_or_default(); // 🚀
+
+    writeln!(
+        &mut writer,
         "{}",
         format_banner_entry!("\u{1f4d6}", "Wordlist", config.wordlist)
-    ); // 📖
-    eprintln!(
+    )
+    .unwrap_or_default(); // 📖
+
+    writeln!(
+        &mut writer,
         "{}",
         format_banner_entry!(
             "\u{1F197}",
             "Status Codes",
             format!("[{}]", codes.join(", "))
         )
-    ); // 🆗
-    eprintln!(
+    )
+    .unwrap_or_default(); // 🆗
+
+    if !config.filter_status.is_empty() {
+        // exception here for optional print due to me wanting the allows and denys to be printed
+        // one after the other
+        let mut code_filters = vec![];
+
+        for code in &config.filter_status {
+            code_filters.push(status_colorizer(&code.to_string()))
+        }
+
+        writeln!(
+            &mut writer,
+            "{}",
+            format_banner_entry!(
+                "\u{1f5d1}",
+                "Status Code Filters",
+                format!("[{}]", code_filters.join(", "))
+            )
+        )
+        .unwrap_or_default(); // 🗑
+    }
+
+    writeln!(
+        &mut writer,
         "{}",
         format_banner_entry!("\u{1f4a5}", "Timeout (secs)", config.timeout)
-    ); // 💥
-    eprintln!(
+    )
+    .unwrap_or_default(); // 💥
+
+    writeln!(
+        &mut writer,
         "{}",
-        format_banner_entry!("\u{1F9a1}", "User-Agent", config.useragent)
-    ); // 🦡
+        format_banner_entry!("\u{1F9a1}", "User-Agent", config.user_agent)
+    )
+    .unwrap_or_default(); // 🦡
 
     // followed by the maybe printed or variably displayed values
     if !config.config.is_empty() {
-        eprintln!(
+        writeln!(
+            &mut writer,
             "{}",
             format_banner_entry!("\u{1f489}", "Config File", config.config)
-        ); // 💉
+        )
+        .unwrap_or_default(); // 💉
     }
 
     if !config.proxy.is_empty() {
-        eprintln!(
+        writeln!(
+            &mut writer,
             "{}",
             format_banner_entry!("\u{1f48e}", "Proxy", config.proxy)
-        ); // 💎
+        )
+        .unwrap_or_default(); // 💎
+    }
+
+    if !config.replay_proxy.is_empty() {
+        // i include replay codes logic here because in config.rs, replay codes are set to the
+        // value in status codes, meaning it's never empty
+
+        let mut replay_codes = vec![];
+
+        writeln!(
+            &mut writer,
+            "{}",
+            format_banner_entry!("\u{1f3a5}", "Replay Proxy", config.replay_proxy)
+        )
+        .unwrap_or_default(); // 🎥
+
+        for code in &config.replay_codes {
+            replay_codes.push(status_colorizer(&code.to_string()))
+        }
+
+        writeln!(
+            &mut writer,
+            "{}",
+            format_banner_entry!(
+                "\u{1f4fc}",
+                "Replay Proxy Codes",
+                format!("[{}]", replay_codes.join(", "))
+            )
+        )
+        .unwrap_or_default(); // 📼
     }
 
     if !config.headers.is_empty() {
         for (name, value) in &config.headers {
-            eprintln!(
+            writeln!(
+                &mut writer,
                 "{}",
                 format_banner_entry!("\u{1f92f}", "Header", name, value)
-            ); // 🤯
+            )
+            .unwrap_or_default(); // 🤯
         }
     }
 
-    if !config.sizefilters.is_empty() {
-        for filter in &config.sizefilters {
-            eprintln!(
+    if !config.filter_size.is_empty() {
+        for filter in &config.filter_size {
+            writeln!(
+                &mut writer,
                 "{}",
                 format_banner_entry!("\u{1f4a2}", "Size Filter", filter)
-            ); // 💢
+            )
+            .unwrap_or_default(); // 💢
         }
     }
 
+    for filter in &config.filter_word_count {
+        writeln!(
+            &mut writer,
+            "{}",
+            format_banner_entry!("\u{1f4a2}", "Word Count Filter", filter)
+        )
+        .unwrap_or_default(); // 💢
+    }
+
+    for filter in &config.filter_line_count {
+        writeln!(
+            &mut writer,
+            "{}",
+            format_banner_entry!("\u{1f4a2}", "Line Count Filter", filter)
+        )
+        .unwrap_or_default(); // 💢
+    }
+
+    for filter in &config.filter_regex {
+        writeln!(
+            &mut writer,
+            "{}",
+            format_banner_entry!("\u{1f4a2}", "Regex Filter", filter)
+        )
+        .unwrap_or_default(); // 💢
+    }
+
+    if config.extract_links {
+        writeln!(
+            &mut writer,
+            "{}",
+            format_banner_entry!("\u{1F50E}", "Extract Links", config.extract_links)
+        )
+        .unwrap_or_default(); // 🔎
+    }
+
+    if config.json {
+        writeln!(
+            &mut writer,
+            "{}",
+            format_banner_entry!("\u{1F9d4}", "JSON Output", config.json)
+        )
+        .unwrap_or_default(); // 🧔
+    }
+
     if !config.queries.is_empty() {
         for query in &config.queries {
-            eprintln!(
+            writeln!(
+                &mut writer,
                 "{}",
                 format_banner_entry!(
                     "\u{1f914}",
                     "Query Parameter",
                     format!("{}={}", query.0, query.1)
                 )
-            ); // 🤔
+            )
+            .unwrap_or_default(); // 🤔
         }
     }
 
     if !config.output.is_empty() {
-        eprintln!(
+        writeln!(
+            &mut writer,
             "{}",
             format_banner_entry!("\u{1f4be}", "Output File", config.output)
-        ); // 💾
+        )
+        .unwrap_or_default(); // 💾
+    }
+
+    if !config.debug_log.is_empty() {
+        writeln!(
+            &mut writer,
+            "{}",
+            format_banner_entry!("\u{1fab2}", "Debugging Log", config.debug_log)
+        )
+        .unwrap_or_default(); // 🪲
     }
 
     if !config.extensions.is_empty() {
-        eprintln!(
+        writeln!(
+            &mut writer,
             "{}",
             format_banner_entry!(
                 "\u{1f4b2}",
                 "Extensions",
                 format!("[{}]", config.extensions.join(", "))
             )
-        ); // 💲
+        )
+        .unwrap_or_default(); // 💲
     }
 
     if config.insecure {
-        eprintln!(
+        writeln!(
+            &mut writer,
             "{}",
             format_banner_entry!("\u{1f513}", "Insecure", config.insecure)
-        ); // 🔓
+        )
+        .unwrap_or_default(); // 🔓
     }
 
     if config.redirects {
-        eprintln!(
+        writeln!(
+            &mut writer,
             "{}",
             format_banner_entry!("\u{1f4cd}", "Follow Redirects", config.redirects)
-        ); // 📍
+        )
+        .unwrap_or_default(); // 📍
     }
 
-    if config.dontfilter {
-        eprintln!(
+    if config.dont_filter {
+        writeln!(
+            &mut writer,
             "{}",
-            format_banner_entry!("\u{1f92a}", "Filter Wildcards", !config.dontfilter)
-        ); // 🤪
+            format_banner_entry!("\u{1f92a}", "Filter Wildcards", !config.dont_filter)
+        )
+        .unwrap_or_default(); // 🤪
     }
 
     match config.verbosity {
         //speaker medium volume (increasing with verbosity to loudspeaker)
         1 => {
-            eprintln!(
+            writeln!(
+                &mut writer,
                 "{}",
                 format_banner_entry!("\u{1f508}", "Verbosity", config.verbosity)
-            ); // 🔈
+            )
+            .unwrap_or_default(); // 🔈
         }
         2 => {
-            eprintln!(
+            writeln!(
+                &mut writer,
                 "{}",
                 format_banner_entry!("\u{1f509}", "Verbosity", config.verbosity)
-            ); // 🔉
+            )
+            .unwrap_or_default(); // 🔉
         }
         3 => {
-            eprintln!(
+            writeln!(
+                &mut writer,
                 "{}",
                 format_banner_entry!("\u{1f50a}", "Verbosity", config.verbosity)
-            ); // 🔊
+            )
+            .unwrap_or_default(); // 🔊
         }
         4 => {
-            eprintln!(
+            writeln!(
+                &mut writer,
                 "{}",
                 format_banner_entry!("\u{1f4e2}", "Verbosity", config.verbosity)
-            ); // 📢
+            )
+            .unwrap_or_default(); // 📢
         }
         _ => {}
     }
 
-    if config.addslash {
-        eprintln!(
+    if config.add_slash {
+        writeln!(
+            &mut writer,
             "{}",
-            format_banner_entry!("\u{1fa93}", "Add Slash", config.addslash)
-        ); // 🪓
+            format_banner_entry!("\u{1fa93}", "Add Slash", config.add_slash)
+        )
+        .unwrap_or_default(); // 🪓
     }
 
-    if !config.norecursion {
+    if !config.no_recursion {
         if config.depth == 0 {
-            eprintln!(
+            writeln!(
+                &mut writer,
                 "{}",
                 format_banner_entry!("\u{1f503}", "Recursion Depth", "INFINITE")
-            ); // 🔃
+            )
+            .unwrap_or_default(); // 🔃
         } else {
-            eprintln!(
+            writeln!(
+                &mut writer,
                 "{}",
                 format_banner_entry!("\u{1f503}", "Recursion Depth", config.depth)
-            ); // 🔃
+            )
+            .unwrap_or_default(); // 🔃
         }
     } else {
-        eprintln!(
+        writeln!(
+            &mut writer,
             "{}",
-            format_banner_entry!("\u{1f6ab}", "Do Not Recurse", config.norecursion)
-        ); // 🚫
+            format_banner_entry!("\u{1f6ab}", "Do Not Recurse", config.no_recursion)
+        )
+        .unwrap_or_default(); // 🚫
     }
 
-    eprintln!("{}", bottom);
+    if CONFIGURATION.scan_limit > 0 {
+        writeln!(
+            &mut writer,
+            "{}",
+            format_banner_entry!("\u{1f9a5}", "Concurrent Scan Limit", config.scan_limit)
+        )
+        .unwrap_or_default(); // 🦥
+    }
+
+    if matches!(status, UpdateStatus::OutOfDate) {
+        writeln!(
+            &mut writer,
+            "{}",
+            format_banner_entry!(
+                "\u{1f389}",
+                "New Version Available",
+                "https://github.com/epi052/feroxbuster/releases/latest"
+            )
+        )
+        .unwrap_or_default(); // 🎉
+    }
+
+    writeln!(&mut writer, "{}", bottom).unwrap_or_default();
+    // ⏯
+    writeln!(
+        &mut writer,
+        " \u{23ef}   Press [{}] to {}|{} your scan",
+        style("ENTER").yellow(),
+        style("pause").red(),
+        style("resume").green()
+    )
+    .unwrap_or_default();
+    writeln!(&mut writer, "{}", addl_section).unwrap_or_default();
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::VERSION;
+    use httpmock::Method::GET;
+    use httpmock::{Mock, MockServer};
+    use std::fs::read_to_string;
+    use std::io::stderr;
+    use std::time::Duration;
+    use tempfile::NamedTempFile;
 
-    #[test]
+    #[tokio::test(core_threads = 1)]
     /// test to hit no execution of targets for loop in banner
-    fn banner_without_targets() {
+    async fn banner_intialize_without_targets() {
         let config = Configuration::default();
-        initialize(&[], &config);
+        initialize(&[], &config, VERSION, stderr()).await;
     }
 
-    #[test]
+    #[tokio::test(core_threads = 1)]
     /// test to hit no execution of statuscode for loop in banner
-    fn banner_without_status_codes() {
+    async fn banner_intialize_without_status_codes() {
         let mut config = Configuration::default();
-        config.statuscodes = vec![];
-        initialize(&[String::from("http://localhost")], &config);
+        config.status_codes = vec![];
+        initialize(
+            &[String::from("http://localhost")],
+            &config,
+            VERSION,
+            stderr(),
+        )
+        .await;
     }
 
-    #[test]
+    #[tokio::test(core_threads = 1)]
     /// test to hit an empty config file
-    fn banner_without_config_file() {
+    async fn banner_intialize_without_config_file() {
         let mut config = Configuration::default();
         config.config = String::new();
-        initialize(&[String::from("http://localhost")], &config);
+        initialize(
+            &[String::from("http://localhost")],
+            &config,
+            VERSION,
+            stderr(),
+        )
+        .await;
     }
 
-    #[test]
+    #[tokio::test(core_threads = 1)]
     /// test to hit an empty config file
-    fn banner_without_queries() {
+    async fn banner_intialize_without_queries() {
         let mut config = Configuration::default();
         config.queries = vec![(String::new(), String::new())];
-        initialize(&[String::from("http://localhost")], &config);
+        initialize(
+            &[String::from("http://localhost")],
+            &config,
+            VERSION,
+            stderr(),
+        )
+        .await;
+    }
+
+    #[tokio::test(core_threads = 1)]
+    /// test to show that a new version is available for download
+    async fn banner_intialize_with_mismatched_version() {
+        let config = Configuration::default();
+        let file = NamedTempFile::new().unwrap();
+        initialize(
+            &[String::from("http://localhost")],
+            &config,
+            "mismatched-version",
+            &file,
+        )
+        .await;
+        let contents = read_to_string(file.path()).unwrap();
+        println!("contents: {}", contents);
+        assert!(contents.contains("New Version Available"));
+        assert!(contents.contains("https://github.com/epi052/feroxbuster/releases/latest"));
+    }
+
+    #[tokio::test(core_threads = 1)]
+    /// test that
+    async fn banner_needs_update_returns_unknown_with_bad_url() {
+        let result = needs_update(&CONFIGURATION.client, &"", VERSION).await;
+        assert!(matches!(result, UpdateStatus::Unknown));
+    }
+
+    #[tokio::test(core_threads = 1)]
+    /// test return value of good url to needs_update
+    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 result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.1.0").await;
+
+        assert_eq!(mock.times_called(), 1);
+        assert!(matches!(result, UpdateStatus::UpToDate));
+    }
+
+    #[tokio::test(core_threads = 1)]
+    /// test return value of good url to needs_update that returns a newer version than current
+    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 result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.0.1").await;
+
+        assert_eq!(mock.times_called(), 1);
+        assert!(matches!(result, UpdateStatus::OutOfDate));
+    }
+
+    #[tokio::test(core_threads = 1)]
+    /// test return value of good url that times out
+    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 result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.0.1").await;
+
+        assert_eq!(mock.times_called(), 1);
+        assert!(matches!(result, UpdateStatus::Unknown));
+    }
+
+    #[tokio::test(core_threads = 1)]
+    /// test return value of good url with bad json response
+    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 result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.0.1").await;
+
+        assert_eq!(mock.times_called(), 1);
+        assert!(matches!(result, UpdateStatus::Unknown));
+    }
+
+    #[tokio::test(core_threads = 1)]
+    /// test return value of good url with json response that lacks the tag_name field
+    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 result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.0.1").await;
+
+        assert_eq!(mock.times_called(), 1);
+        assert!(matches!(result, UpdateStatus::Unknown));
     }
 }

src/client.rs

@@ -10,7 +10,7 @@ use std::time::Duration;
 /// Create and return an instance of [reqwest::Client](https://docs.rs/reqwest/latest/reqwest/struct.Client.html)
 pub fn initialize(
     timeout: u64,
-    useragent: &str,
+    user_agent: &str,
     redirects: bool,
     insecure: bool,
     headers: &HashMap<String, String>,
@@ -27,46 +27,43 @@ pub fn initialize(
 
     let client = Client::builder()
         .timeout(Duration::new(timeout, 0))
-        .user_agent(useragent)
+        .user_agent(user_agent)
         .danger_accept_invalid_certs(insecure)
         .default_headers(header_map)
         .redirect(policy);
 
-    let client = if proxy.is_some() && !proxy.unwrap().is_empty() {
-        match Proxy::all(proxy.unwrap()) {
-            Ok(proxy_obj) => client.proxy(proxy_obj),
-            Err(e) => {
-                eprintln!(
-                    "{} {} Could not add proxy ({:?}) to Client configuration",
-                    status_colorizer("ERROR"),
-                    module_colorizer("Client::initialize"),
-                    proxy
-                );
-                eprintln!(
-                    "{} {} {}",
-                    status_colorizer("ERROR"),
-                    module_colorizer("Client::initialize"),
-                    e
-                );
+    let client = match proxy {
+        // a proxy is specified, need to add it to the client
+        Some(some_proxy) => {
+            if !some_proxy.is_empty() {
+                // it's not an empty string
+                match Proxy::all(some_proxy) {
+                    Ok(proxy_obj) => client.proxy(proxy_obj),
+                    Err(e) => {
+                        eprintln!(
+                            "{} {} {}",
+                            status_colorizer("ERROR"),
+                            module_colorizer("Client::initialize"),
+                            e
+                        );
 
-                #[cfg(test)]
-                panic!();
-                #[cfg(not(test))]
-                exit(1);
+                        #[cfg(test)]
+                        panic!();
+                        #[cfg(not(test))]
+                        exit(1);
+                    }
+                }
+            } else {
+                client // Some("") was used?
             }
         }
-    } else {
-        client
+        // no proxy specified
+        None => client,
     };
 
     match client.build() {
         Ok(client) => client,
         Err(e) => {
-            eprintln!(
-                "{} {} Could not create a Client with the given configuration, exiting.",
-                status_colorizer("ERROR"),
-                module_colorizer("Client::build")
-            );
             eprintln!(
                 "{} {} {}",
                 status_colorizer("ERROR"),

src/config.rs

@@ -1,15 +1,16 @@
 use crate::utils::{module_colorizer, status_colorizer};
 use crate::{client, parser, progress};
-use crate::{DEFAULT_CONFIG_NAME, DEFAULT_STATUS_CODES, DEFAULT_WORDLIST, VERSION};
+use crate::{FeroxSerialize, DEFAULT_CONFIG_NAME, DEFAULT_STATUS_CODES, DEFAULT_WORDLIST, VERSION};
 use clap::value_t;
 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;
 use std::path::PathBuf;
+#[cfg(not(test))]
 use std::process::exit;
 
 lazy_static! {
@@ -23,6 +24,21 @@ lazy_static! {
     pub static ref PROGRESS_PRINTER: ProgressBar = progress::add_bar("", 0, true);
 }
 
+/// simple helper to clean up some code reuse below; panics under test / exits in prod
+fn report_and_exit(err: &str) -> ! {
+    eprintln!(
+        "{} {}: {}",
+        status_colorizer("ERROR"),
+        module_colorizer("Configuration::new"),
+        err
+    );
+
+    #[cfg(test)]
+    panic!();
+    #[cfg(not(test))]
+    exit(1);
+}
+
 /// Represents the final, global configuration of the program.
 ///
 /// This struct is the combination of the following:
@@ -33,8 +49,12 @@ lazy_static! {
 /// 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,
@@ -47,18 +67,34 @@ pub struct Configuration {
     #[serde(default)]
     pub proxy: String,
 
+    /// Replay Proxy to use for requests (ex: http(s)://host:port, socks5://host:port)
+    #[serde(default)]
+    pub replay_proxy: String,
+
     /// The target URL
     #[serde(default)]
     pub target_url: String,
 
-    /// Status Codes of interest (default: 200 204 301 302 307 308 401 403 405)
-    #[serde(default = "statuscodes")]
-    pub statuscodes: Vec<u16>,
+    /// Status Codes to include (allow list) (default: 200 204 301 302 307 308 401 403 405)
+    #[serde(default = "status_codes")]
+    pub status_codes: Vec<u16>,
+
+    /// Status Codes to replay to the Replay Proxy (default: whatever is passed to --status-code)
+    #[serde(default)]
+    pub replay_codes: Vec<u16>,
+
+    /// Status Codes to filter out (deny list)
+    #[serde(default)]
+    pub filter_status: Vec<u16>,
 
     /// Instance of [reqwest::Client](https://docs.rs/reqwest/latest/reqwest/struct.Client.html)
     #[serde(skip)]
     pub client: Client,
 
+    /// Instance of [reqwest::Client](https://docs.rs/reqwest/latest/reqwest/struct.Client.html)
+    #[serde(skip)]
+    pub replay_client: Option<Client>,
+
     /// Number of concurrent threads (default: 50)
     #[serde(default = "threads")]
     pub threads: usize,
@@ -75,13 +111,22 @@ 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 = "useragent")]
-    pub useragent: String,
+    #[serde(default = "user_agent")]
+    pub user_agent: String,
 
     /// Follow redirects
     #[serde(default)]
@@ -105,11 +150,15 @@ pub struct Configuration {
 
     /// Do not scan recursively
     #[serde(default)]
-    pub norecursion: bool,
+    pub no_recursion: bool,
+
+    /// Extract links from html/javscript
+    #[serde(default)]
+    pub extract_links: bool,
 
     /// Append / to each request
     #[serde(default)]
-    pub addslash: bool,
+    pub add_slash: bool,
 
     /// Read url(s) from STDIN
     #[serde(default)]
@@ -119,19 +168,40 @@ pub struct Configuration {
     #[serde(default = "depth")]
     pub depth: usize,
 
+    /// Number of concurrent scans permitted; a limit of 0 means no limit is imposed
+    #[serde(default)]
+    pub scan_limit: usize,
+
     /// Filter out messages of a particular size
     #[serde(default)]
-    pub sizefilters: Vec<u64>,
+    pub filter_size: Vec<u64>,
+
+    /// Filter out messages of a particular line count
+    #[serde(default)]
+    pub filter_line_count: Vec<usize>,
+
+    /// Filter out messages of a particular word count
+    #[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 dontfilter: bool,
+    pub dont_filter: bool,
 }
 
-// functions timeout, threads, statuscodes, useragent, wordlist, and depth are used to provide
+// functions timeout, threads, status_codes, user_agent, wordlist, 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
@@ -143,7 +213,7 @@ fn threads() -> usize {
 }
 
 /// default status codes
-fn statuscodes() -> Vec<u16> {
+fn status_codes() -> Vec<u16> {
     DEFAULT_STATUS_CODES
         .iter()
         .map(|code| code.as_u16())
@@ -155,8 +225,8 @@ fn wordlist() -> String {
     String::from(DEFAULT_WORDLIST)
 }
 
-/// default useragent
-fn useragent() -> String {
+/// default user-agent
+fn user_agent() -> String {
     format!("feroxbuster/{}", VERSION)
 }
 
@@ -169,33 +239,49 @@ impl Default for Configuration {
     /// Builds the default Configuration for feroxbuster
     fn default() -> Self {
         let timeout = timeout();
-        let useragent = useragent();
-        let client = client::initialize(timeout, &useragent, false, false, &HashMap::new(), None);
+        let user_agent = user_agent();
+        let client = client::initialize(timeout, &user_agent, false, false, &HashMap::new(), None);
+        let replay_client = None;
+        let status_codes = status_codes();
+        let replay_codes = status_codes.clone();
+        let kind = serialized_type();
 
         Configuration {
+            kind,
             client,
             timeout,
-            useragent,
-            dontfilter: false,
+            user_agent,
+            replay_codes,
+            status_codes,
+            replay_client,
+            dont_filter: false,
             quiet: false,
             stdin: false,
+            json: false,
             verbosity: 0,
-            addslash: false,
+            scan_limit: 0,
+            add_slash: false,
             insecure: false,
-            norecursion: false,
             redirects: false,
+            no_recursion: false,
+            extract_links: false,
             proxy: String::new(),
             config: String::new(),
             output: String::new(),
+            debug_log: String::new(),
             target_url: String::new(),
+            replay_proxy: String::new(),
             queries: Vec::new(),
             extensions: Vec::new(),
-            sizefilters: Vec::new(),
+            filter_size: Vec::new(),
+            filter_regex: Vec::new(),
+            filter_line_count: Vec::new(),
+            filter_word_count: Vec::new(),
+            filter_status: Vec::new(),
             headers: HashMap::new(),
-            threads: threads(),
             depth: depth(),
+            threads: threads(),
             wordlist: wordlist(),
-            statuscodes: statuscodes(),
         }
     }
 }
@@ -206,26 +292,36 @@ impl Configuration {
     ///
     /// - **timeout**: `5` seconds
     /// - **redirects**: `false`
+    /// - **extract-links**: `false`
     /// - **wordlist**: [`DEFAULT_WORDLIST`](constant.DEFAULT_WORDLIST.html)
     /// - **config**: `None`
     /// - **threads**: `50`
     /// - **timeout**: `7` seconds
     /// - **verbosity**: `0` (no logging enabled)
     /// - **proxy**: `None`
-    /// - **statuscodes**: [`DEFAULT_RESPONSE_CODES`](constant.DEFAULT_RESPONSE_CODES.html)
+    /// - **status_codes**: [`DEFAULT_RESPONSE_CODES`](constant.DEFAULT_RESPONSE_CODES.html)
+    /// - **filter_status**: `None`
     /// - **output**: `None` (print to stdout)
+    /// - **debug_log**: `None`
     /// - **quiet**: `false`
-    /// - **useragent**: `feroxer/VERSION`
+    /// - **user_agent**: `feroxbuster/VERSION`
     /// - **insecure**: `false` (don't be insecure, i.e. don't allow invalid certs)
     /// - **extensions**: `None`
-    /// - **sizefilters**: `None`
+    /// - **filter_size**: `None`
+    /// - **filter_regex**: `None`
+    /// - **filter_word_count**: `None`
+    /// - **filter_line_count**: `None`
     /// - **headers**: `None`
     /// - **queries**: `None`
-    /// - **norecursion**: `false` (recursively scan enumerated sub-directories)
-    /// - **addslash**: `false`
+    /// - **no_recursion**: `false` (recursively scan enumerated sub-directories)
+    /// - **add_slash**: `false`
     /// - **stdin**: `false`
-    /// - **dontfilter**: `false` (auto filter wildcard responses)
+    /// - **json**: `false`
+    /// - **dont_filter**: `false` (auto filter wildcard responses)
     /// - **depth**: `4` (maximum recursion depth)
+    /// - **scan_limit**: `0` (no limit on concurrent scans imposed)
+    /// - **replay_proxy**: `None` (no limit on concurrent scans imposed)
+    /// - **replay_codes**: [`DEFAULT_RESPONSE_CODES`](constant.DEFAULT_RESPONSE_CODES.html)
     ///
     /// After which, any values defined in a
     /// [ferox-config.toml](constant.DEFAULT_CONFIG_NAME.html) config file will override the
@@ -298,68 +394,94 @@ impl Configuration {
 
         let args = parser::initialize().get_matches();
 
-        // the .is_some appears clunky, but it allows default values to be incrementally
-        // overwritten from Struct defaults, to file config, to command line args, soooo ¯\_(ツ)_/¯
-        if args.value_of("threads").is_some() {
-            let threads = value_t!(args.value_of("threads"), usize).unwrap_or_else(|e| e.exit());
-            config.threads = threads;
+        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
+                }
+            };
         }
 
-        if args.value_of("depth").is_some() {
-            let depth = value_t!(args.value_of("depth"), usize).unwrap_or_else(|e| e.exit());
-            config.depth = depth;
-        }
+        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);
 
-        if args.value_of("wordlist").is_some() {
-            config.wordlist = String::from(args.value_of("wordlist").unwrap());
-        }
-
-        if args.value_of("output").is_some() {
-            config.output = String::from(args.value_of("output").unwrap());
-        }
-
-        if args.values_of("statuscodes").is_some() {
-            config.statuscodes = args
-                .values_of("statuscodes")
-                .unwrap() // already known good
+        if let Some(arg) = args.values_of("status_codes") {
+            config.status_codes = arg
                 .map(|code| {
                     StatusCode::from_bytes(code.as_bytes())
-                        .unwrap_or_else(|e| {
-                            eprintln!(
-                                "{} {}: {}",
-                                status_colorizer("ERROR"),
-                                module_colorizer("Configuration::new"),
-                                e
-                            );
-                            exit(1)
-                        })
+                        .unwrap_or_else(|e| report_and_exit(&e.to_string()))
                         .as_u16()
                 })
                 .collect();
         }
 
-        if args.values_of("extensions").is_some() {
-            config.extensions = args
-                .values_of("extensions")
-                .unwrap()
-                .map(|val| val.to_string())
+        if let Some(arg) = args.values_of("replay_codes") {
+            // replay codes passed in by the user
+            config.replay_codes = arg
+                .map(|code| {
+                    StatusCode::from_bytes(code.as_bytes())
+                        .unwrap_or_else(|e| report_and_exit(&e.to_string()))
+                        .as_u16()
+                })
+                .collect();
+        } else {
+            // not passed in by the user, use whatever value is held in status_codes
+            config.replay_codes = config.status_codes.clone();
+        }
+
+        if let Some(arg) = args.values_of("filter_status") {
+            config.filter_status = arg
+                .map(|code| {
+                    StatusCode::from_bytes(code.as_bytes())
+                        .unwrap_or_else(|e| report_and_exit(&e.to_string()))
+                        .as_u16()
+                })
                 .collect();
         }
 
-        if args.values_of("sizefilters").is_some() {
-            config.sizefilters = args
-                .values_of("sizefilters")
-                .unwrap() // already known good
+        if let Some(arg) = args.values_of("extensions") {
+            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_size") {
+            config.filter_size = arg
                 .map(|size| {
-                    size.parse::<u64>().unwrap_or_else(|e| {
-                        eprintln!(
-                            "{} {}: {}",
-                            status_colorizer("ERROR"),
-                            module_colorizer("Configuration::new"),
-                            e
-                        );
-                        exit(1)
-                    })
+                    size.parse::<u64>()
+                        .unwrap_or_else(|e| report_and_exit(&e.to_string()))
+                })
+                .collect();
+        }
+
+        if let Some(arg) = args.values_of("filter_words") {
+            config.filter_word_count = arg
+                .map(|size| {
+                    size.parse::<usize>()
+                        .unwrap_or_else(|e| report_and_exit(&e.to_string()))
+                })
+                .collect();
+        }
+
+        if let Some(arg) = args.values_of("filter_lines") {
+            config.filter_line_count = arg
+                .map(|size| {
+                    size.parse::<usize>()
+                        .unwrap_or_else(|e| report_and_exit(&e.to_string()))
                 })
                 .collect();
         }
@@ -369,11 +491,11 @@ impl Configuration {
             // consider a user specifying quiet = true in ferox-config.toml
             // if the line below is outside of the if, we'd overwrite true with
             // false if no -q is used on the command line
-            config.quiet = args.is_present("quiet");
+            config.quiet = true;
         }
 
-        if args.is_present("dontfilter") {
-            config.dontfilter = args.is_present("dontfilter");
+        if args.is_present("dont_filter") {
+            config.dont_filter = true;
         }
 
         if args.occurrences_of("verbosity") > 0 {
@@ -382,16 +504,24 @@ impl Configuration {
             config.verbosity = args.occurrences_of("verbosity") as u8;
         }
 
-        if args.is_present("norecursion") {
-            config.norecursion = args.is_present("norecursion");
+        if args.is_present("no_recursion") {
+            config.no_recursion = true;
         }
 
-        if args.is_present("addslash") {
-            config.addslash = args.is_present("addslash");
+        if args.is_present("add_slash") {
+            config.add_slash = true;
+        }
+
+        if args.is_present("extract_links") {
+            config.extract_links = true;
+        }
+
+        if args.is_present("json") {
+            config.json = true;
         }
 
         if args.is_present("stdin") {
-            config.stdin = args.is_present("stdin");
+            config.stdin = true;
         } else {
             config.target_url = String::from(args.value_of("url").unwrap());
         }
@@ -399,29 +529,21 @@ impl Configuration {
         ////
         // organizational breakpoint; all options below alter the Client configuration
         ////
-        if args.value_of("proxy").is_some() {
-            config.proxy = String::from(args.value_of("proxy").unwrap());
-        }
-
-        if args.value_of("useragent").is_some() {
-            config.useragent = String::from(args.value_of("useragent").unwrap());
-        }
-
-        if args.value_of("timeout").is_some() {
-            let timeout = value_t!(args.value_of("timeout"), u64).unwrap_or_else(|e| e.exit());
-            config.timeout = timeout;
-        }
+        update_config_if_present!(&mut config.proxy, args, "proxy", String);
+        update_config_if_present!(&mut config.replay_proxy, args, "replay_proxy", String);
+        update_config_if_present!(&mut config.user_agent, args, "user_agent", String);
+        update_config_if_present!(&mut config.timeout, args, "timeout", u64);
 
         if args.is_present("redirects") {
-            config.redirects = args.is_present("redirects");
+            config.redirects = true;
         }
 
         if args.is_present("insecure") {
-            config.insecure = args.is_present("insecure");
+            config.insecure = true;
         }
 
-        if args.values_of("headers").is_some() {
-            for val in args.values_of("headers").unwrap() {
+        if let Some(headers) = args.values_of("headers") {
+            for val in headers {
                 let mut split_val = val.split(':');
 
                 // explicitly take first split value as header's name
@@ -434,8 +556,8 @@ impl Configuration {
             }
         }
 
-        if args.values_of("queries").is_some() {
-            for val in args.values_of("queries").unwrap() {
+        if let Some(queries) = args.values_of("queries") {
+            for val in queries {
                 // same basic logic used as reading in the headers HashMap above
                 let mut split_val = val.split('=');
 
@@ -452,7 +574,7 @@ impl Configuration {
         // the client and store it in the config struct
         if !config.proxy.is_empty()
             || config.timeout != timeout()
-            || config.useragent != useragent()
+            || config.user_agent != user_agent()
             || config.redirects
             || config.insecure
             || !config.headers.is_empty()
@@ -460,7 +582,7 @@ impl Configuration {
             if config.proxy.is_empty() {
                 config.client = client::initialize(
                     config.timeout,
-                    &config.useragent,
+                    &config.user_agent,
                     config.redirects,
                     config.insecure,
                     &config.headers,
@@ -469,7 +591,7 @@ impl Configuration {
             } else {
                 config.client = client::initialize(
                     config.timeout,
-                    &config.useragent,
+                    &config.user_agent,
                     config.redirects,
                     config.insecure,
                     &config.headers,
@@ -478,6 +600,18 @@ impl Configuration {
             }
         }
 
+        if !config.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),
+            ));
+        }
+
         config
     }
 
@@ -505,24 +639,34 @@ impl Configuration {
     fn merge_config(settings: &mut Self, settings_to_merge: Self) {
         settings.threads = settings_to_merge.threads;
         settings.wordlist = settings_to_merge.wordlist;
-        settings.statuscodes = settings_to_merge.statuscodes;
+        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.useragent = settings_to_merge.useragent;
+        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.norecursion = settings_to_merge.norecursion;
-        settings.addslash = settings_to_merge.addslash;
+        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.sizefilters = settings_to_merge.sizefilters;
-        settings.dontfilter = settings_to_merge.dontfilter;
+        settings.filter_size = settings_to_merge.filter_size;
+        settings.filter_regex = settings_to_merge.filter_regex;
+        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;
+        settings.debug_log = settings_to_merge.debug_log;
+        settings.json = settings_to_merge.json;
     }
 
     /// If present, read in `DEFAULT_CONFIG_NAME` and deserialize the specified values
@@ -548,6 +692,47 @@ 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::*;
@@ -558,24 +743,34 @@ mod tests {
     fn setup_config_test() -> Configuration {
         let data = r#"
             wordlist = "/some/path"
-            statuscodes = [201, 301, 401]
+            status_codes = [201, 301, 401]
+            replay_codes = [201, 301]
             threads = 40
             timeout = 5
             proxy = "http://127.0.0.1:8080"
+            replay_proxy = "http://127.0.0.1:8081"
             quiet = true
             verbosity = 1
+            scan_limit = 6
             output = "/some/otherpath"
+            debug_log = "/yet/anotherpath"
             redirects = true
             insecure = true
             extensions = ["html", "php", "js"]
             headers = {stuff = "things", mostuff = "mothings"}
             queries = [["name","value"], ["rick", "astley"]]
-            norecursion = true
-            addslash = true
+            no_recursion = true
+            add_slash = true
             stdin = true
-            dontfilter = true
+            dont_filter = true
+            extract_links = true
+            json = true
             depth = 1
-            sizefilters = [4120]
+            filter_size = [4120]
+            filter_regex = ["^ignore me$"]
+            filter_word_count = [994, 992]
+            filter_line_count = [34]
+            filter_status = [201]
         "#;
         let tmp_dir = TempDir::new().unwrap();
         let file = tmp_dir.path().join(DEFAULT_CONFIG_NAME);
@@ -590,22 +785,33 @@ mod tests {
         assert_eq!(config.wordlist, wordlist());
         assert_eq!(config.proxy, String::new());
         assert_eq!(config.target_url, String::new());
+        assert_eq!(config.debug_log, String::new());
         assert_eq!(config.config, String::new());
-        assert_eq!(config.statuscodes, statuscodes());
+        assert_eq!(config.replay_proxy, String::new());
+        assert_eq!(config.status_codes, status_codes());
+        assert_eq!(config.replay_codes, config.status_codes);
+        assert!(config.replay_client.is_none());
         assert_eq!(config.threads, threads());
         assert_eq!(config.depth, depth());
         assert_eq!(config.timeout, timeout());
         assert_eq!(config.verbosity, 0);
+        assert_eq!(config.scan_limit, 0);
         assert_eq!(config.quiet, false);
-        assert_eq!(config.dontfilter, false);
-        assert_eq!(config.norecursion, false);
+        assert_eq!(config.dont_filter, false);
+        assert_eq!(config.no_recursion, false);
+        assert_eq!(config.json, false);
         assert_eq!(config.stdin, false);
-        assert_eq!(config.addslash, false);
+        assert_eq!(config.add_slash, false);
         assert_eq!(config.redirects, false);
+        assert_eq!(config.extract_links, false);
         assert_eq!(config.insecure, false);
         assert_eq!(config.queries, Vec::new());
         assert_eq!(config.extensions, Vec::<String>::new());
-        assert_eq!(config.sizefilters, Vec::<u64>::new());
+        assert_eq!(config.filter_size, Vec::<u64>::new());
+        assert_eq!(config.filter_regex, 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());
         assert_eq!(config.headers, HashMap::new());
     }
 
@@ -618,9 +824,23 @@ mod tests {
 
     #[test]
     /// parse the test config and see that the value parsed is correct
-    fn config_reads_statuscodes() {
+    fn config_reads_debug_log() {
         let config = setup_config_test();
-        assert_eq!(config.statuscodes, vec![201, 301, 401]);
+        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() {
+        let config = setup_config_test();
+        assert_eq!(config.status_codes, vec![201, 301, 401]);
+    }
+
+    #[test]
+    /// parse the test config and see that the value parsed is correct
+    fn config_reads_replay_codes() {
+        let config = setup_config_test();
+        assert_eq!(config.replay_codes, vec![201, 301]);
     }
 
     #[test]
@@ -637,6 +857,13 @@ mod tests {
         assert_eq!(config.depth, 1);
     }
 
+    #[test]
+    /// parse the test config and see that the value parsed is correct
+    fn config_reads_scan_limit() {
+        let config = setup_config_test();
+        assert_eq!(config.scan_limit, 6);
+    }
+
     #[test]
     /// parse the test config and see that the value parsed is correct
     fn config_reads_timeout() {
@@ -651,6 +878,13 @@ mod tests {
         assert_eq!(config.proxy, "http://127.0.0.1:8080");
     }
 
+    #[test]
+    /// parse the test config and see that the value parsed is correct
+    fn config_reads_replay_proxy() {
+        let config = setup_config_test();
+        assert_eq!(config.replay_proxy, "http://127.0.0.1:8081");
+    }
+
     #[test]
     /// parse the test config and see that the value parsed is correct
     fn config_reads_quiet() {
@@ -658,6 +892,13 @@ 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() {
@@ -688,9 +929,9 @@ mod tests {
 
     #[test]
     /// parse the test config and see that the value parsed is correct
-    fn config_reads_norecursion() {
+    fn config_reads_no_recursion() {
         let config = setup_config_test();
-        assert_eq!(config.norecursion, true);
+        assert_eq!(config.no_recursion, true);
     }
 
     #[test]
@@ -702,16 +943,23 @@ mod tests {
 
     #[test]
     /// parse the test config and see that the value parsed is correct
-    fn config_reads_dontfilter() {
+    fn config_reads_dont_filter() {
         let config = setup_config_test();
-        assert_eq!(config.dontfilter, true);
+        assert_eq!(config.dont_filter, true);
     }
 
     #[test]
     /// parse the test config and see that the value parsed is correct
-    fn config_reads_addslash() {
+    fn config_reads_add_slash() {
         let config = setup_config_test();
-        assert_eq!(config.addslash, true);
+        assert_eq!(config.add_slash, true);
+    }
+
+    #[test]
+    /// parse the test config and see that the value parsed is correct
+    fn config_reads_extract_links() {
+        let config = setup_config_test();
+        assert_eq!(config.extract_links, true);
     }
 
     #[test]
@@ -723,9 +971,37 @@ mod tests {
 
     #[test]
     /// parse the test config and see that the value parsed is correct
-    fn config_reads_sizefilters() {
+    fn config_reads_filter_regex() {
         let config = setup_config_test();
-        assert_eq!(config.sizefilters, vec![4120]);
+        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_size() {
+        let config = setup_config_test();
+        assert_eq!(config.filter_size, vec![4120]);
+    }
+
+    #[test]
+    /// parse the test config and see that the value parsed is correct
+    fn config_reads_filter_word_count() {
+        let config = setup_config_test();
+        assert_eq!(config.filter_word_count, vec![994, 992]);
+    }
+
+    #[test]
+    /// parse the test config and see that the value parsed is correct
+    fn config_reads_filter_line_count() {
+        let config = setup_config_test();
+        assert_eq!(config.filter_line_count, vec![34]);
+    }
+
+    #[test]
+    /// parse the test config and see that the value parsed is correct
+    fn config_reads_filter_status() {
+        let config = setup_config_test();
+        assert_eq!(config.filter_status, vec![201]);
     }
 
     #[test]
@@ -747,4 +1023,39 @@ mod tests {
         queries.push(("rick".to_string(), "astley".to_string()));
         assert_eq!(config.queries, queries);
     }
+
+    #[test]
+    #[should_panic]
+    /// test that an error message is printed and panic is called when report_and_exit is called
+    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

@@ -0,0 +1,269 @@
+use crate::FeroxResponse;
+use lazy_static::lazy_static;
+use regex::Regex;
+use reqwest::Url;
+use std::collections::HashSet;
+
+/// Regular expression used in [LinkFinder](https://github.com/GerbenJavado/LinkFinder)
+///
+/// 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,}|)))(?:"|')"#;
+
+lazy_static! {
+    /// `LINKFINDER_REGEX` as a regex::Regex type
+    static ref REGEX: Regex = Regex::new(LINKFINDER_REGEX).unwrap();
+}
+
+/// Iterate over a given path, return a list of every sub-path found
+///
+/// example: `path` contains a link fragment `homepage/assets/img/icons/handshake.svg`
+/// the following fragments would be returned:
+///   - homepage/assets/img/icons/handshake.svg
+///   - homepage/assets/img/icons/
+///   - homepage/assets/img/
+///   - homepage/assets/
+///   - homepage/
+fn get_sub_paths_from_path(path: &str) -> Vec<String> {
+    log::trace!("enter: get_sub_paths_from_path({})", path);
+    let mut paths = vec![];
+
+    // filter out any empty strings caused by .split
+    let mut parts: Vec<&str> = path.split('/').filter(|s| !s.is_empty()).collect();
+
+    let length = parts.len();
+
+    for _ in 0..length {
+        // iterate over all parts of the path
+        if parts.is_empty() {
+            // pop left us with an empty vector, we're done
+            break;
+        }
+
+        let possible_path = parts.join("/");
+
+        if possible_path.is_empty() {
+            // .join can result in an empty string, which we don't need, ignore
+            continue;
+        }
+
+        paths.push(possible_path); // good sub-path found
+        parts.pop(); // use .pop() to remove the last part of the path and continue iteration
+    }
+
+    log::trace!("exit: get_sub_paths_from_path -> {:?}", paths);
+    paths
+}
+
+/// simple helper to stay DRY, trys to join a url + fragment and add it to the `links` HashSet
+fn add_link_to_set_of_links(link: &str, url: &Url, links: &mut HashSet<String>) {
+    log::trace!(
+        "enter: add_link_to_set_of_links({}, {}, {:?})",
+        link,
+        url.to_string(),
+        links
+    );
+    match url.join(&link) {
+        Ok(new_url) => {
+            links.insert(new_url.to_string());
+        }
+        Err(e) => {
+            log::error!("Could not join given url to the base url: {}", e);
+        }
+    }
+    log::trace!("exit: add_link_to_set_of_links");
+}
+
+/// Given a `reqwest::Response`, perform the following actions
+///   - parse the response's text for links using the linkfinder regex
+///   - for every link found take its url path and parse each sub-path
+///     - example: Response contains a link fragment `homepage/assets/img/icons/handshake.svg`
+///       with a base url of http://localhost, the following urls would be returned:
+///         - homepage/assets/img/icons/handshake.svg
+///         - homepage/assets/img/icons/
+///         - homepage/assets/img/
+///         - homepage/assets/
+///         - homepage/
+pub async fn get_links(response: &FeroxResponse) -> HashSet<String> {
+    log::trace!("enter: get_links({})", response.url().as_str());
+
+    let mut links = HashSet::<String>::new();
+
+    let body = response.text();
+
+    for capture in 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 == '"');
+
+        match Url::parse(link) {
+            Ok(absolute) => {
+                if absolute.domain() != response.url().domain()
+                    || absolute.host() != response.url().host()
+                {
+                    // domains/ips are not the same, don't scan things that aren't part of the original
+                    // target url
+                    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);
+                }
+            }
+            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);
+                    }
+                } else {
+                    // unexpected error has occurred
+                    log::error!("Could not parse given url: {}", e);
+                }
+            }
+        }
+    }
+
+    log::trace!("exit: get_links -> {:?}", links);
+    links
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::utils::make_request;
+    use httpmock::Method::GET;
+    use httpmock::{Mock, MockServer};
+    use reqwest::Client;
+
+    #[test]
+    /// extract sub paths from the given url fragment; expect 4 sub paths and that all are
+    /// in the expected array
+    fn extractor_get_sub_paths_from_path_with_multiple_paths() {
+        let path = "homepage/assets/img/icons/handshake.svg";
+        let paths = get_sub_paths_from_path(&path);
+        let expected = vec![
+            "homepage",
+            "homepage/assets",
+            "homepage/assets/img",
+            "homepage/assets/img/icons",
+            "homepage/assets/img/icons/handshake.svg",
+        ];
+
+        assert_eq!(paths.len(), expected.len());
+        for expected_path in expected {
+            assert_eq!(paths.contains(&expected_path.to_string()), true);
+        }
+    }
+
+    #[test]
+    /// extract sub paths from the given url fragment; expect 2 sub paths and that all are
+    /// in the expected array. the fragment is wrapped in slashes to ensure no empty strings are
+    /// returned
+    fn extractor_get_sub_paths_from_path_with_enclosing_slashes() {
+        let path = "/homepage/assets/";
+        let paths = get_sub_paths_from_path(&path);
+        let expected = vec!["homepage", "homepage/assets"];
+
+        assert_eq!(paths.len(), expected.len());
+        for expected_path in expected {
+            assert_eq!(paths.contains(&expected_path.to_string()), true);
+        }
+    }
+
+    #[test]
+    /// extract sub paths from the given url fragment; expect 1 sub path, no forward slashes are
+    /// included
+    fn extractor_get_sub_paths_from_path_with_only_a_word() {
+        let path = "homepage";
+        let paths = get_sub_paths_from_path(&path);
+        let expected = vec!["homepage"];
+
+        assert_eq!(paths.len(), expected.len());
+        for expected_path in expected {
+            assert_eq!(paths.contains(&expected_path.to_string()), true);
+        }
+    }
+
+    #[test]
+    /// extract sub paths from the given url fragment; expect 1 sub path, forward slash removed
+    fn extractor_get_sub_paths_from_path_with_an_absolute_word() {
+        let path = "/homepage";
+        let paths = get_sub_paths_from_path(&path);
+        let expected = vec!["homepage"];
+
+        assert_eq!(paths.len(), expected.len());
+        for expected_path in expected {
+            assert_eq!(paths.contains(&expected_path.to_string()), true);
+        }
+    }
+
+    #[test]
+    /// test that a full url and fragment are joined correctly, then added to the given list
+    /// i.e. the happy path
+    fn extractor_add_link_to_set_of_links_happy_path() {
+        let url = Url::parse("https://localhost").unwrap();
+        let mut links = HashSet::<String>::new();
+        let link = "admin";
+
+        assert_eq!(links.len(), 0);
+        add_link_to_set_of_links(link, &url, &mut links);
+
+        assert_eq!(links.len(), 1);
+        assert!(links.contains("https://localhost/admin"));
+    }
+
+    #[test]
+    /// test that an invalid path fragment doesn't add anything to the set of links
+    fn extractor_add_link_to_set_of_links_with_non_base_url() {
+        let url = Url::parse("https://localhost").unwrap();
+        let mut links = HashSet::<String>::new();
+        let link = "\\\\\\\\";
+
+        assert_eq!(links.len(), 0);
+        add_link_to_set_of_links(link, &url, &mut links);
+
+        assert_eq!(links.len(), 0);
+        assert!(links.is_empty());
+    }
+
+    #[tokio::test(core_threads = 1)]
+    /// use make_request to generate a Response, and use the Response to test get_links;
+    /// the response will contain an absolute path to a domain that is not part of the scanned
+    /// domain; expect an empty set returned
+    async fn extractor_get_links_with_absolute_url_that_differs_from_target_domain(
+    ) -> 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 client = Client::new();
+        let url = Url::parse(&srv.url("/some-path")).unwrap();
+
+        let response = make_request(&client, &url).await.unwrap();
+
+        let ferox_response = FeroxResponse::from(response, true).await;
+
+        let links = get_links(&ferox_response).await;
+
+        assert!(links.is_empty());
+
+        assert_eq!(mock.times_called(), 1);
+        Ok(())
+    }
+}

src/filters.rs

@@ -0,0 +1,416 @@
+use crate::config::CONFIGURATION;
+use crate::utils::get_url_path_length;
+use crate::FeroxResponse;
+use regex::Regex;
+use std::any::Any;
+use std::fmt::Debug;
+
+// references:
+//   https://dev.to/magnusstrale/rust-trait-objects-in-a-vector-non-trivial-4co5
+//   https://stackoverflow.com/questions/25339603/how-to-test-for-equality-between-trait-objects
+
+/// FeroxFilter trait; represents different types of possible filters that can be applied to
+/// responses
+pub trait FeroxFilter: Debug + Send + Sync {
+    /// Determine whether or not this particular filter should be applied or not
+    fn should_filter_response(&self, response: &FeroxResponse) -> bool;
+
+    /// delegates to the FeroxFilter-implementing type which gives us the actual type of self
+    fn box_eq(&self, other: &dyn Any) -> bool;
+
+    /// gives us `other` as Any in box_eq
+    fn as_any(&self) -> &dyn Any;
+}
+
+/// implementation of PartialEq, necessary long-form due to "trait cannot be made into an object"
+/// error when attempting to derive PartialEq on the trait itself
+impl PartialEq for Box<dyn FeroxFilter> {
+    /// Perform a comparison of two implementors of the FeroxFilter trait
+    fn eq(&self, other: &Box<dyn FeroxFilter>) -> bool {
+        self.box_eq(other.as_any())
+    }
+}
+
+/// Data holder for two pieces of data needed when auto-filtering out wildcard responses
+///
+/// `dynamic` is the size of the response that will later be combined with the length
+/// of the path of the url requested and used to determine interesting pages from custom
+/// 404s where the requested url is reflected back in the response
+///
+/// `size` is size of the response that should be included with filters passed via runtime
+/// configuration and any static wildcard lengths.
+#[derive(Debug, Default, Clone, PartialEq)]
+pub struct WildcardFilter {
+    /// size of the response that will later be combined with the length of the path of the url
+    /// requested
+    pub dynamic: u64,
+
+    /// size of the response that should be included with filters passed via runtime configuration
+    pub size: u64,
+}
+
+/// implementation of FeroxFilter for WildcardFilter
+impl FeroxFilter for WildcardFilter {
+    /// Examine size, dynamic, and content_len to determine whether or not the response received
+    /// is a wildcard response and therefore should be filtered out
+    fn should_filter_response(&self, response: &FeroxResponse) -> bool {
+        log::trace!("enter: should_filter_response({:?} {})", self, response);
+
+        // quick return if dont_filter is set
+        if CONFIGURATION.dont_filter {
+            // --dont-filter applies specifically to wildcard filters, it is not a 100% catch all
+            // for not filtering anything.  As such, it should live in the implementation of
+            // a wildcard filter
+            return false;
+        }
+
+        if self.size > 0 && self.size == response.content_length() {
+            // static wildcard size found during testing
+            // size isn't default, size equals response length, and auto-filter is on
+            log::debug!("static wildcard: filtered out {}", response.url());
+            log::trace!("exit: should_filter_response -> true");
+            return true;
+        }
+
+        if self.dynamic > 0 {
+            // dynamic wildcard offset found during testing
+
+            // I'm about to manually split this url path instead of using reqwest::Url's
+            // builtin parsing. The reason is that they call .split() on the url path
+            // except that I don't want an empty string taking up the last index in the
+            // event that the url ends with a forward slash.  It's ugly enough to be split
+            // into its own function for readability.
+            let url_len = get_url_path_length(&response.url());
+
+            if url_len + self.dynamic == response.content_length() {
+                log::debug!("dynamic wildcard: filtered out {}", response.url());
+                log::trace!("exit: should_filter_response -> true");
+                return true;
+            }
+        }
+        log::trace!("exit: should_filter_response -> false");
+        false
+    }
+
+    /// Compare one WildcardFilter 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
+    }
+}
+
+/// Simple implementor of FeroxFilter; used to filter out status codes specified using
+/// -C|--filter-status
+#[derive(Default, Debug, PartialEq)]
+pub struct StatusCodeFilter {
+    /// Status code that should not be displayed to the user
+    pub filter_code: u16,
+}
+
+/// implementation of FeroxFilter for StatusCodeFilter
+impl FeroxFilter for StatusCodeFilter {
+    /// Check `filter_code` against what was passed in via -C|--filter-status
+    fn should_filter_response(&self, response: &FeroxResponse) -> bool {
+        log::trace!("enter: should_filter_response({:?} {})", self, response);
+
+        if response.status().as_u16() == self.filter_code {
+            log::debug!(
+                "filtered out {} based on --filter-status of {}",
+                response.url(),
+                self.filter_code
+            );
+            log::trace!("exit: should_filter_response -> true");
+            return true;
+        }
+
+        log::trace!("exit: should_filter_response -> false");
+        false
+    }
+
+    /// Compare one StatusCodeFilter 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
+    }
+}
+
+/// Simple implementor of FeroxFilter; used to filter out responses based on the number of lines
+/// in a Response body; specified using -N|--filter-lines
+#[derive(Default, Debug, PartialEq)]
+pub struct LinesFilter {
+    /// Number of lines in a Response's body that should be filtered
+    pub line_count: usize,
+}
+
+/// implementation of FeroxFilter for LinesFilter
+impl FeroxFilter for LinesFilter {
+    /// Check `line_count` against what was passed in via -N|--filter-lines
+    fn should_filter_response(&self, response: &FeroxResponse) -> bool {
+        log::trace!("enter: should_filter_response({:?} {})", self, response);
+
+        let result = response.line_count() == self.line_count;
+
+        log::trace!("exit: should_filter_response -> {}", result);
+
+        result
+    }
+
+    /// Compare one LinesFilter 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
+    }
+}
+
+/// Simple implementor of FeroxFilter; used to filter out responses based on the number of words
+/// in a Response body; specified using -W|--filter-words
+#[derive(Default, Debug, PartialEq)]
+pub struct WordsFilter {
+    /// Number of words in a Response's body that should be filtered
+    pub word_count: usize,
+}
+
+/// implementation of FeroxFilter for WordsFilter
+impl FeroxFilter for WordsFilter {
+    /// Check `word_count` against what was passed in via -W|--filter-words
+    fn should_filter_response(&self, response: &FeroxResponse) -> bool {
+        log::trace!("enter: should_filter_response({:?} {})", self, response);
+
+        let result = response.word_count() == self.word_count;
+
+        log::trace!("exit: should_filter_response -> {}", result);
+
+        result
+    }
+
+    /// Compare one WordsFilter 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
+    }
+}
+
+/// Simple implementor of FeroxFilter; used to filter out responses based on the length of a
+/// Response body; specified using -S|--filter-size
+#[derive(Default, Debug, PartialEq)]
+pub struct SizeFilter {
+    /// Overall length of a Response's body that should be filtered
+    pub content_length: u64,
+}
+
+/// implementation of FeroxFilter for SizeFilter
+impl FeroxFilter for SizeFilter {
+    /// Check `content_length` against what was passed in via -S|--filter-size
+    fn should_filter_response(&self, response: &FeroxResponse) -> bool {
+        log::trace!("enter: should_filter_response({:?} {})", self, response);
+
+        let result = response.content_length() == self.content_length;
+
+        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
+    }
+}
+
+/// 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
+    }
+}
+
+#[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
+    fn lines_filter_as_any() {
+        let filter = LinesFilter { line_count: 1 };
+
+        assert_eq!(filter.line_count, 1);
+        assert_eq!(
+            *filter.as_any().downcast_ref::<LinesFilter>().unwrap(),
+            filter
+        );
+    }
+
+    #[test]
+    /// just a simple test to increase code coverage by hitting as_any and the inner value
+    fn words_filter_as_any() {
+        let filter = WordsFilter { word_count: 1 };
+
+        assert_eq!(filter.word_count, 1);
+        assert_eq!(
+            *filter.as_any().downcast_ref::<WordsFilter>().unwrap(),
+            filter
+        );
+    }
+
+    #[test]
+    /// just a simple test to increase code coverage by hitting as_any and the inner value
+    fn size_filter_as_any() {
+        let filter = SizeFilter { content_length: 1 };
+
+        assert_eq!(filter.content_length, 1);
+        assert_eq!(
+            *filter.as_any().downcast_ref::<SizeFilter>().unwrap(),
+            filter
+        );
+    }
+
+    #[test]
+    /// just a simple test to increase code coverage by hitting as_any and the inner value
+    fn status_code_filter_as_any() {
+        let filter = StatusCodeFilter { filter_code: 200 };
+
+        assert_eq!(filter.filter_code, 200);
+        assert_eq!(
+            *filter.as_any().downcast_ref::<StatusCodeFilter>().unwrap(),
+            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,
+            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,
+            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,
+            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));
+    }
+}

src/heuristics.rs

@@ -1,35 +1,18 @@
-use crate::config::{CONFIGURATION, PROGRESS_PRINTER};
-use crate::utils::{
-    ferox_print, format_url, get_url_path_length, make_request, module_colorizer, status_colorizer,
+use crate::{
+    config::{CONFIGURATION, PROGRESS_PRINTER},
+    filters::WildcardFilter,
+    scanner::should_filter_response,
+    utils::{ferox_print, format_url, get_url_path_length, make_request, status_colorizer},
+    FeroxResponse,
 };
 use console::style;
 use indicatif::ProgressBar;
-use reqwest::Response;
-use std::process;
 use tokio::sync::mpsc::UnboundedSender;
 use uuid::Uuid;
 
 /// length of a standard UUID, used when determining wildcard responses
 const UUID_LENGTH: u64 = 32;
 
-/// Data holder for two pieces of data needed when auto-filtering out wildcard responses
-///
-/// `dynamic` is the size of the response that will later be combined with the length
-/// of the path of the url requested and used to determine interesting pages from custom
-/// 404s where the requested url is reflected back in the response
-///
-/// `size` is size of the response that should be included with filters passed via runtime
-/// configuration and any static wildcard lengths.
-#[derive(Default, Debug)]
-pub struct WildcardFilter {
-    /// size of the response that will later be combined with the length of the path of the url
-    /// requested
-    pub dynamic: u64,
-
-    /// size of the response that should be included with filters passed via runtime configuration
-    pub size: u64,
-}
-
 /// Simple helper to return a uuid, formatted as lowercase without hyphens
 ///
 /// `length` determines the number of uuids to string together. Each uuid
@@ -56,31 +39,31 @@ 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.dontfilter {
-        // early return, dontfilter scans don't need tested
+    if CONFIGURATION.dont_filter {
+        // early return, dont_filter scans don't need tested
         log::trace!("exit: wildcard_test -> None");
         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(resp_one) = 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
         let mut wildcard = WildcardFilter::default();
 
-        let wc_length = resp_one.content_length().unwrap_or(0);
+        let wc_length = ferox_response.content_length();
 
         if wc_length == 0 {
             log::trace!("exit: wildcard_test -> Some({:?})", wildcard);
@@ -89,56 +72,49 @@ 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().unwrap_or(0);
+            let wc2_length = resp_two.content_length();
 
             if wc2_length == wc_length + (UUID_LENGTH * 2) {
                 // second length is what we'd expect to see if the requested url is
                 // reflected in the response along with some static content; aka custom 404
-                let url_len = get_url_path_length(&resp_one.url());
-
-                if !CONFIGURATION.quiet {
-                    let msg = format!(
-                            "{} {:>10} Wildcard response is dynamic; {} ({} + url length) responses; toggle this behavior by using {}\n",
-                            status_colorizer("WLD"),
-                            wc_length - url_len,
-                            style("auto-filtering").yellow(),
-                            style(wc_length - url_len).cyan(),
-                            style("--dontfilter").yellow()
-                        );
-
-                    ferox_print(&msg, &PROGRESS_PRINTER);
-
-                    try_send_message_to_file(
-                        &msg,
-                        tx_file.clone(),
-                        !CONFIGURATION.output.is_empty(),
-                    );
-                }
+                let url_len = get_url_path_length(&ferox_response.url());
 
                 wildcard.dynamic = wc_length - url_len;
-            } else if wc_length == wc2_length {
+
                 if !CONFIGURATION.quiet {
                     let msg = format!(
-                        "{} {:>10} Wildcard response is static; {} {} responses; toggle this behavior by using {}\n",
-                        status_colorizer("WLD"),
-                        wc_length,
-                        style("auto-filtering").yellow(),
-                        style(wc_length).cyan(),
-                        style("--dontfilter").yellow()
+                            "{} {:>9} {:>9} {:>9} Wildcard response is dynamic; {} ({} + url length) responses; toggle this behavior by using {}\n",
+                            status_colorizer("WLD"),
+                            "-",
+                            "-",
+                            "-",
+                            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!(
+                        "{} {:>9} {:>9} {:>9} Wildcard response is static; {} {} responses; toggle this behavior by using {}\n",
+                        status_colorizer("WLD"),
+                        "-",
+                        "-",
+                        "-",
+                        style("auto-filtering").yellow(),
+                        style(wc_length).cyan(),
+                        style("--dont-filter").yellow()
+                    );
+
+                    ferox_print(&msg, &PROGRESS_PRINTER);
+                }
             }
         } else {
             bar.inc(2);
@@ -161,8 +137,8 @@ pub async fn wildcard_test(
 async fn make_wildcard_request(
     target_url: &str,
     length: usize,
-    tx_file: UnboundedSender<String>,
-) -> Option<Response> {
+    tx_file: UnboundedSender<FeroxResponse>,
+) -> Option<FeroxResponse> {
     log::trace!(
         "enter: make_wildcard_request({}, {}, {:?})",
         target_url,
@@ -175,7 +151,7 @@ async fn make_wildcard_request(
     let nonexistent = match format_url(
         target_url,
         &unique_str,
-        CONFIGURATION.addslash,
+        CONFIGURATION.add_slash,
         &CONFIGURATION.queries,
         None,
     ) {
@@ -187,79 +163,25 @@ async fn make_wildcard_request(
         }
     };
 
-    let wildcard = status_colorizer("WLD");
-
     match make_request(&CONFIGURATION.client, &nonexistent.to_owned()).await {
         Ok(response) => {
             if CONFIGURATION
-                .statuscodes
+                .status_codes
                 .contains(&response.status().as_u16())
             {
                 // found a wildcard response
-                let url_len = get_url_path_length(&response.url());
-                let content_len = response.content_length().unwrap_or(0);
+                let mut ferox_response = FeroxResponse::from(response, true).await;
+                ferox_response.wildcard = true;
 
-                if !CONFIGURATION.quiet {
-                    let msg = format!(
-                        "{} {:>10} Got {} for {} (url length: {})\n",
-                        wildcard,
-                        content_len,
-                        status_colorizer(&response.status().as_str()),
-                        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 response.status().is_redirection() {
-                    // show where it goes, if possible
-                    if let Some(next_loc) = response.headers().get("Location") {
-                        if let Ok(next_loc_str) = next_loc.to_str() {
-                            if !CONFIGURATION.quiet {
-                                let msg = format!(
-                                    "{} {:>10} {} redirects to => {}\n",
-                                    wildcard,
-                                    content_len,
-                                    response.url(),
-                                    next_loc_str
-                                );
-
-                                ferox_print(&msg, &PROGRESS_PRINTER);
-
-                                try_send_message_to_file(
-                                    &msg,
-                                    tx_file.clone(),
-                                    !CONFIGURATION.output.is_empty(),
-                                );
-                            }
-                        } else if !CONFIGURATION.quiet {
-                            let msg = format!(
-                                "{} {:>10} {} redirects to => {:?}\n",
-                                wildcard,
-                                content_len,
-                                response.url(),
-                                next_loc
-                            );
-
-                            ferox_print(&msg, &PROGRESS_PRINTER);
-
-                            try_send_message_to_file(
-                                &msg,
-                                tx_file.clone(),
-                                !CONFIGURATION.output.is_empty(),
-                            );
-                        }
-                    }
-                }
-                log::trace!("exit: make_wildcard_request -> {:?}", response);
-                return Some(response);
+                log::trace!("exit: make_wildcard_request -> {}", ferox_response);
+                return Some(ferox_response);
             }
         }
         Err(e) => {
@@ -286,7 +208,7 @@ pub async fn connectivity_test(target_urls: &[String]) -> Vec<String> {
         let request = match format_url(
             target_url,
             "",
-            CONFIGURATION.addslash,
+            CONFIGURATION.add_slash,
             &CONFIGURATION.queries,
             None,
         ) {
@@ -315,14 +237,6 @@ pub async fn connectivity_test(target_urls: &[String]) -> Vec<String> {
 
     if good_urls.is_empty() {
         log::error!("Could not connect to any target provided, exiting.");
-        log::trace!("exit: connectivity_test");
-        eprintln!(
-            "{} {} Could not connect to any target provided",
-            status_colorizer("ERROR"),
-            module_colorizer("heuristics::connectivity_test"),
-        );
-
-        process::exit(1);
     }
 
     log::trace!("exit: connectivity_test -> {:?}", good_urls);
@@ -330,36 +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!(
-                    "{} {} {}",
-                    status_colorizer("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
@@ -376,41 +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

@@ -1,20 +1,42 @@
 pub mod banner;
 pub mod client;
 pub mod config;
+pub mod extractor;
+pub mod filters;
 pub mod heuristics;
 pub mod logger;
 pub mod parser;
 pub mod progress;
 pub mod reporter;
+pub mod scan_manager;
 pub mod scanner;
 pub mod utils;
 
-use reqwest::StatusCode;
+use crate::utils::{get_url_path_length, status_colorizer};
+use console::{style, Color};
+use reqwest::{header::HeaderMap, Response, StatusCode, Url};
+use serde::{ser::SerializeStruct, Deserialize, Serialize, Serializer};
+use std::collections::HashMap;
+use std::{error, fmt};
 use tokio::sync::mpsc::{UnboundedReceiver, UnboundedSender};
 
 /// Generic Result type to ease error handling in async contexts
-pub type FeroxResult<T> =
-    std::result::Result<T, Box<dyn std::error::Error + Send + Sync + 'static>>;
+pub type FeroxResult<T> = std::result::Result<T, Box<dyn error::Error + Send + Sync + 'static>>;
+
+/// Simple Error implementation to allow for custom error returns
+#[derive(Debug, Default)]
+pub struct FeroxError {
+    /// fancy string that can be printed via Display
+    pub message: String,
+}
+
+impl error::Error for FeroxError {}
+
+impl fmt::Display for FeroxError {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        write!(f, "{}", &self.message)
+    }
+}
 
 /// Generic mpsc::unbounded_channel type to tidy up some code
 pub type FeroxChannel<T> = (UnboundedSender<T>, UnboundedReceiver<T>);
@@ -22,6 +44,9 @@ pub type FeroxChannel<T> = (UnboundedSender<T>, UnboundedReceiver<T>);
 /// Version pulled from Cargo.toml at compile time
 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 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.
 ///
@@ -30,6 +55,9 @@ pub const VERSION: &str = env!("CARGO_PKG_VERSION");
 pub const DEFAULT_WORDLIST: &str =
     "/usr/share/seclists/Discovery/Web-Content/raft-medium-directories.txt";
 
+/// Number of milliseconds to wait between polls of `PAUSE_SCAN` when user pauses a scan
+pub static SLEEP_DURATION: u64 = 500;
+
 /// Default list of status codes to report
 ///
 /// * 200 Ok
@@ -58,6 +86,354 @@ 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 {
+    /// The final `Url` of this `FeroxResponse`
+    url: Url,
+
+    /// The `StatusCode` of this `FeroxResponse`
+    status: StatusCode,
+
+    /// The full response text
+    text: String,
+
+    /// The content-length of this response, if known
+    content_length: u64,
+
+    /// The `Headers` of this `FeroxResponse`
+    headers: HeaderMap,
+
+    /// Wildcard response status
+    wildcard: bool,
+}
+
+/// Implement Display for FeroxResponse
+impl fmt::Display for FeroxResponse {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        write!(
+            f,
+            "FeroxResponse {{ url: {}, status: {}, content-length: {} }}",
+            self.url(),
+            self.status(),
+            self.content_length()
+        )
+    }
+}
+
+/// `FeroxResponse` implementation
+impl FeroxResponse {
+    /// Get the `StatusCode` of this `FeroxResponse`
+    pub fn status(&self) -> &StatusCode {
+        &self.status
+    }
+
+    /// Get the final `Url` of this `FeroxResponse`.
+    pub fn url(&self) -> &Url {
+        &self.url
+    }
+
+    /// Get the full response text
+    pub fn text(&self) -> &str {
+        &self.text
+    }
+
+    /// Get the `Headers` of this `FeroxResponse`
+    pub fn headers(&self) -> &HeaderMap {
+        &self.headers
+    }
+
+    /// Get the content-length of this response, if known
+    pub fn content_length(&self) -> u64 {
+        self.content_length
+    }
+
+    /// Set `FeroxResponse`'s `url` attribute, has no affect if an error occurs
+    pub fn set_url(&mut self, url: &str) {
+        match Url::parse(&url) {
+            Ok(url) => {
+                self.url = url;
+            }
+            Err(e) => {
+                log::error!("Could not parse {} into a Url: {}", url, e);
+            }
+        };
+    }
+
+    /// Make a reasonable guess at whether the response is a file or not
+    ///
+    /// Examines the last part of a path to determine if it has an obvious extension
+    /// i.e. http://localhost/some/path/stuff.js where stuff.js indicates a file
+    ///
+    /// Additionally, inspects query parameters, as they're also often indicative of a file
+    pub fn is_file(&self) -> bool {
+        let has_extension = match self.url.path_segments() {
+            Some(path) => {
+                if let Some(last) = path.last() {
+                    last.contains('.') // last segment has some sort of extension, probably
+                } else {
+                    false
+                }
+            }
+            None => false,
+        };
+
+        self.url.query_pairs().count() > 0 || has_extension
+    }
+
+    /// Returns line count of the response text.
+    pub fn line_count(&self) -> usize {
+        self.text().lines().count()
+    }
+
+    /// Returns word count of the response text.
+    pub fn word_count(&self) -> usize {
+        self.text()
+            .lines()
+            .map(|s| s.split_whitespace().count())
+            .sum()
+    }
+
+    /// Create a new `FeroxResponse` from the given `Response`
+    pub async fn from(response: Response, read_body: bool) -> Self {
+        let url = response.url().clone();
+        let status = response.status();
+        let headers = response.headers().clone();
+        let content_length = response.content_length().unwrap_or(0);
+
+        let text = if read_body {
+            // .text() consumes the response, must be called last
+            // additionally, --extract-links is currently the only place we use the body of the
+            // response, so we forego the processing if not performing extraction
+            match response.text().await {
+                // await the response's body
+                Ok(text) => text,
+                Err(e) => {
+                    log::error!("Could not parse body from response: {}", e);
+                    String::new()
+                }
+            }
+        } else {
+            String::new()
+        };
+
+        FeroxResponse {
+            url,
+            status,
+            content_length,
+            text,
+            headers,
+            wildcard: false,
+        }
+    }
+}
+
+/// Implement FeroxSerialize for FeroxResponse
+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()
+    }
+}
+
+#[derive(Serialize, Deserialize, Default)]
+/// Representation of a log entry, can be represented as a human readable string or JSON
+pub struct FeroxMessage {
+    // todo probably move to lib
+    #[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::*;
@@ -82,4 +458,46 @@ 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;
@@ -19,8 +22,8 @@ pub fn initialize(verbosity: u8) {
                 0 => (),
                 1 => env::set_var("RUST_LOG", "warn"),
                 2 => env::set_var("RUST_LOG", "info"),
-                3 => env::set_var("RUST_LOG", "debug,hyper=info,reqwest=info"),
-                _ => env::set_var("RUST_LOG", "trace,hyper=info,reqwest=info"),
+                3 => env::set_var("RUST_LOG", "feroxbuster=debug,info"),
+                _ => env::set_var("RUST_LOG", "feroxbuster=trace,info"),
             }
         }
     }
@@ -28,43 +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(),
-                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

@@ -1,18 +1,62 @@
-use feroxbuster::config::{CONFIGURATION, PROGRESS_PRINTER};
-use feroxbuster::scanner::scan_url;
-use feroxbuster::utils::{ferox_print, get_current_depth, module_colorizer, status_colorizer};
-use feroxbuster::{banner, heuristics, logger, reporter, FeroxResult};
+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},
+    utils::{ferox_print, get_current_depth, module_colorizer, status_colorizer},
+    FeroxError, FeroxResponse, FeroxResult, SLEEP_DURATION, VERSION,
+};
+#[cfg(not(target_os = "windows"))]
+use feroxbuster::{utils::set_open_file_limit, DEFAULT_OPEN_FILE_LIMIT};
 use futures::StreamExt;
-use reqwest::Response;
-use std::collections::HashSet;
-use std::fs::File;
-use std::io::{BufRead, BufReader};
-use std::process;
-use std::sync::Arc;
-use tokio::io;
-use tokio::sync::mpsc::UnboundedSender;
+use std::{
+    collections::HashSet,
+    fs::File,
+    io::{stderr, BufRead, BufReader},
+    process,
+    sync::{
+        atomic::{AtomicBool, Ordering},
+        Arc,
+    },
+    time::Duration,
+};
+use tokio::{io, sync::mpsc::UnboundedSender, task::JoinHandle};
 use tokio_util::codec::{FramedRead, LinesCodec};
 
+/// Atomic boolean flag, used to determine whether or not the terminal input handler should exit
+pub static SCAN_COMPLETE: AtomicBool = AtomicBool::new(false);
+
+/// Handles specific key events triggered by the user over stdin
+fn terminal_input_handler() {
+    log::trace!("enter: terminal_input_handler");
+
+    loop {
+        if event::poll(Duration::from_millis(SLEEP_DURATION)).unwrap_or(false) {
+            // It's guaranteed that the `read()` won't block when the `poll()`
+            // function returns `true`
+
+            if let Ok(key_pressed) = event::read() {
+                if key_pressed == Event::Key(KeyCode::Enter.into()) {
+                    // if the user presses Enter, toggle the value stored in PAUSE_SCAN
+                    // ignore any other keys
+                    let current = PAUSE_SCAN.load(Ordering::Acquire);
+
+                    PAUSE_SCAN.store(!current, Ordering::Release);
+                }
+            }
+        } else {
+            // Timeout expired and no `Event` is available; use the timeout to check SCAN_COMPLETE
+            if SCAN_COMPLETE.load(Ordering::Relaxed) {
+                // scan has been marked complete by main, time to exit the loop
+                break;
+            }
+        }
+    }
+    log::trace!("exit: terminal_input_handler");
+}
+
 /// Create a HashSet of Strings from the given wordlist then stores it inside an Arc
 fn get_unique_words_from_wordlist(path: &str) -> FeroxResult<Arc<HashSet<String>>> {
     log::trace!("enter: get_unique_words_from_wordlist({})", path);
@@ -20,12 +64,6 @@ fn get_unique_words_from_wordlist(path: &str) -> FeroxResult<Arc<HashSet<String>
     let file = match File::open(&path) {
         Ok(f) => f,
         Err(e) => {
-            eprintln!(
-                "{} {} {}",
-                status_colorizer("ERROR"),
-                module_colorizer("main::get_unique_words_from_wordlist"),
-                e
-            );
             log::error!("Could not open wordlist: {}", e);
             log::trace!("exit: get_unique_words_from_wordlist -> {}", e);
 
@@ -38,7 +76,13 @@ fn get_unique_words_from_wordlist(path: &str) -> FeroxResult<Arc<HashSet<String>
     let mut words = HashSet::new();
 
     for line in reader.lines() {
-        words.insert(line?);
+        let result = line?;
+
+        if result.starts_with('#') || result.is_empty() {
+            continue;
+        }
+
+        words.insert(result);
     }
 
     log::trace!(
@@ -52,8 +96,8 @@ 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>,
-    tx_term: UnboundedSender<Response>,
-    tx_file: UnboundedSender<String>,
+    tx_term: UnboundedSender<FeroxResponse>,
+    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)
@@ -64,15 +108,13 @@ async fn scan(
             .await??;
 
     if words.len() == 0 {
-        eprintln!(
-            "{} {} Did not find any words in {}",
-            status_colorizer("ERROR"),
-            module_colorizer("main::scan"),
-            CONFIGURATION.wordlist
-        );
-        process::exit(1);
+        let mut err = FeroxError::default();
+        err.message = format!("Did not find any words in {}", CONFIGURATION.wordlist);
+        return Err(Box::new(err));
     }
 
+    scanner::initialize(words.len(), &CONFIGURATION);
+
     let mut tasks = vec![];
 
     for target in targets {
@@ -95,6 +137,7 @@ async fn scan(
     Ok(())
 }
 
+/// Get targets from either commandline or stdin, pass them back to the caller as a Result<Vec>
 async fn get_targets() -> FeroxResult<Vec<String>> {
     log::trace!("enter: get_targets");
 
@@ -118,14 +161,29 @@ async fn get_targets() -> FeroxResult<Vec<String>> {
     Ok(targets)
 }
 
-#[tokio::main]
-async fn main() {
-    // setup logging based on the number of -v's used
-    logger::initialize(CONFIGURATION.verbosity);
+/// async main called from real main, broken out in this way to allow for some synchronous code
+/// to be executed before bringing the tokio runtime online
+async fn wrapped_main() {
+    // join can only be called once, otherwise it causes the thread to panic
+    tokio::task::spawn_blocking(move || {
+        // ok, lazy_static! uses (unsurprisingly in retrospect) a lazy loading model where the
+        // thing obtained through deref isn't actually created until it's used. This created a
+        // problem when initializing the logger as it relied on PROGRESS_PRINTER which may or may
+        // not have been created by the time it was needed for logging (really only occurred in
+        // heuristics / banner / main). In order to initialize logging properly, we need to ensure
+        // PROGRESS_PRINTER and PROGRESS_BAR have been used at least once.  This call satisfies
+        // that constraint
+        PROGRESS_PRINTER.println("");
+        PROGRESS_BAR.join().unwrap();
+    });
 
-    // can't trace main until after logger is initialized
+    // 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
+    // scans that are already running
+    tokio::task::spawn_blocking(terminal_input_handler);
 
     let save_output = !CONFIGURATION.output.is_empty(); // was -o used?
 
@@ -137,37 +195,64 @@ async fn main() {
         Ok(t) => t,
         Err(e) => {
             // should only happen in the event that there was an error reading from stdin
-            log::error!("{}", e);
-            ferox_print(
-                &format!(
-                    "{} {} {}",
-                    status_colorizer("ERROR"),
-                    module_colorizer("main::get_targets"),
-                    e
-                ),
-                &PROGRESS_PRINTER,
-            );
-            process::exit(1);
+            log::error!("{} {}", module_colorizer("main::get_targets"), e);
+            clean_up(tx_term, term_handle, tx_file, file_handle, save_output).await;
+            return;
         }
     };
 
     if !CONFIGURATION.quiet {
         // only print banner if -q isn't used
-        banner::initialize(&targets, &CONFIGURATION);
+        let std_stderr = stderr(); // std::io::stderr
+        banner::initialize(&targets, &CONFIGURATION, &VERSION, std_stderr).await;
     }
 
     // discard non-responsive targets
     let live_targets = heuristics::connectivity_test(&targets).await;
 
+    if live_targets.is_empty() {
+        clean_up(tx_term, term_handle, tx_file, file_handle, save_output).await;
+        return;
+    }
+
     // kick off a scan against any targets determined to be responsive
     match scan(live_targets, tx_term.clone(), tx_file.clone()).await {
         Ok(_) => {
             log::info!("All scans complete!");
         }
-        Err(e) => log::error!("An error occurred: {}", e),
+        Err(e) => {
+            ferox_print(
+                &format!("{} while scanning: {}", status_colorizer("Error"), e),
+                &PROGRESS_PRINTER,
+            );
+            clean_up(tx_term, term_handle, tx_file, file_handle, save_output).await;
+            process::exit(1);
+        }
     };
 
-    // manually drop tx in order for the rx task's while loops to eval to false
+    clean_up(tx_term, term_handle, tx_file, file_handle, save_output).await;
+
+    log::trace!("exit: main");
+}
+
+/// Single cleanup function that handles all the necessary drops/finishes etc required to gracefully
+/// shutdown the program
+async fn clean_up(
+    tx_term: UnboundedSender<FeroxResponse>,
+    term_handle: JoinHandle<()>,
+    tx_file: UnboundedSender<FeroxResponse>,
+    file_handle: Option<JoinHandle<()>>,
+    save_output: bool,
+) {
+    log::trace!(
+        "enter: clean_up({:?}, {:?}, {:?}, {:?}, {})",
+        tx_term,
+        term_handle,
+        tx_file,
+        file_handle,
+        save_output
+    );
+
     drop(tx_term);
     log::trace!("dropped terminal output handler's transmitter");
 
@@ -199,9 +284,26 @@ async fn main() {
         log::trace!("done awaiting file output handler's receiver");
     }
 
-    log::trace!("exit: main");
+    // mark all scans complete so the terminal input handler will exit cleanly
+    SCAN_COMPLETE.store(true, Ordering::Relaxed);
 
     // clean-up function for the MultiProgress bar; must be called last in order to still see
-    // the final trace message above
+    // the final trace messages above
     PROGRESS_PRINTER.finish();
+
+    log::trace!("exit: clean_up");
+}
+
+fn main() {
+    // setup logging based on the number of -v's used
+    logger::initialize(CONFIGURATION.verbosity);
+
+    // this function uses rlimit, which is not supported on windows
+    #[cfg(not(target_os = "windows"))]
+    set_open_file_limit(DEFAULT_OPEN_FILE_LIMIT);
+
+    if let Ok(mut runtime) = tokio::runtime::Runtime::new() {
+        let future = wrapped_main();
+        runtime.block_on(future);
+    }
 }

src/parser.rs

@@ -55,7 +55,7 @@ pub fn initialize() -> App<'static, 'static> {
                 .long("verbosity")
                 .takes_value(false)
                 .multiple(true)
-                .help("Increase verbosity level (use -vv or more for greater effect)"),
+                .help("Increase verbosity level (use -vv or more for greater effect. [CAUTION] 4 -v's is probably too much)"),
         )
         .arg(
             Arg::with_name("proxy")
@@ -68,15 +68,38 @@ pub fn initialize() -> App<'static, 'static> {
                 ),
         )
         .arg(
-            Arg::with_name("statuscodes")
+            Arg::with_name("replay_proxy")
+                .short("P")
+                .long("replay-proxy")
+                .takes_value(true)
+                .value_name("REPLAY_PROXY")
+                .help(
+                    "Send only unfiltered requests through a Replay Proxy, instead of all requests",
+                ),
+        )
+        .arg(
+            Arg::with_name("replay_codes")
+                .short("R")
+                .long("replay-codes")
+                .value_name("REPLAY_CODE")
+                .takes_value(true)
+                .multiple(true)
+                .use_delimiter(true)
+                .requires("replay_proxy")
+                .help(
+                    "Status Codes to send through a Replay Proxy when found (default: --status-codes value)",
+                ),
+        )
+        .arg(
+            Arg::with_name("status_codes")
                 .short("s")
-                .long("statuscodes")
+                .long("status-codes")
                 .value_name("STATUS_CODE")
                 .takes_value(true)
                 .multiple(true)
                 .use_delimiter(true)
                 .help(
-                    "Status Codes of interest (default: 200 204 301 302 307 308 401 403 405)",
+                    "Status Codes to include (allow list) (default: 200 204 301 302 307 308 401 403 405)",
                 ),
         )
         .arg(
@@ -87,9 +110,15 @@ pub fn initialize() -> App<'static, 'static> {
                 .help("Only print URLs; Don't print status codes, response size, running config, etc...")
         )
         .arg(
-            Arg::with_name("dontfilter")
+            Arg::with_name("json")
+                .long("json")
+                .takes_value(false)
+                .help("Emit JSON logs to --output and --debug-log instead of normal text")
+        )
+        .arg(
+            Arg::with_name("dont_filter")
                 .short("D")
-                .long("dontfilter")
+                .long("dont-filter")
                 .takes_value(false)
                 .help("Don't auto-filter wildcard responses")
         )
@@ -98,13 +127,20 @@ 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("useragent")
+            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(
+            Arg::with_name("user_agent")
                 .short("a")
-                .long("useragent")
+                .long("user-agent")
                 .value_name("USER_AGENT")
                 .takes_value(true)
                 .help(
@@ -162,16 +198,16 @@ pub fn initialize() -> App<'static, 'static> {
                 ),
         )
         .arg(
-            Arg::with_name("norecursion")
+            Arg::with_name("no_recursion")
                 .short("n")
-                .long("norecursion")
+                .long("no-recursion")
                 .takes_value(false)
                 .help("Do not scan recursively")
         )
         .arg(
-            Arg::with_name("addslash")
+            Arg::with_name("add_slash")
                 .short("f")
-                .long("addslash")
+                .long("add-slash")
                 .takes_value(false)
                 .conflicts_with("extensions")
                 .help("Append / to each request")
@@ -184,9 +220,9 @@ pub fn initialize() -> App<'static, 'static> {
                 .conflicts_with("url")
         )
         .arg(
-            Arg::with_name("sizefilters")
+            Arg::with_name("filter_size")
                 .short("S")
-                .long("sizefilter")
+                .long("filter-size")
                 .value_name("SIZE")
                 .takes_value(true)
                 .multiple(true)
@@ -195,7 +231,69 @@ 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")
+                .long("filter-words")
+                .value_name("WORDS")
+                .takes_value(true)
+                .multiple(true)
+                .use_delimiter(true)
+                .help(
+                    "Filter out messages of a particular word count (ex: -W 312 -W 91,82)",
+                ),
+        )
+        .arg(
+            Arg::with_name("filter_lines")
+                .short("N")
+                .long("filter-lines")
+                .value_name("LINES")
+                .takes_value(true)
+                .multiple(true)
+                .use_delimiter(true)
+                .help(
+                    "Filter out messages of a particular line count (ex: -N 20 -N 31,30)",
+                ),
+        )
+        .arg(
+            Arg::with_name("filter_status")
+                .short("C")
+                .long("filter-status")
+                .value_name("STATUS_CODE")
+                .takes_value(true)
+                .multiple(true)
+                .use_delimiter(true)
+                .help(
+                    "Filter out status codes (deny list) (ex: -C 200 -C 401)",
+                ),
+        )
+        .arg(
+            Arg::with_name("extract_links")
+                .short("e")
+                .long("extract-links")
+                .takes_value(false)
+                .help("Extract links from response body (html, javascript, etc...); make new requests based on findings (default: false)")
+        )
+        .arg(
+            Arg::with_name("scan_limit")
+                .short("L")
+                .long("scan-limit")
+                .value_name("SCAN_LIMIT")
+                .takes_value(true)
+                .help("Limit total number of concurrent scans (default: 0, i.e. no limit)")
+        )
         .after_help(r#"NOTE:
     Options that take multiple values are very flexible.  Consider the following ways of specifying
     extensions:
@@ -211,7 +309,7 @@ EXAMPLES:
         ./feroxbuster -u http://127.1 -H Accept:application/json "Authorization: Bearer {token}"
 
     IPv6, non-recursive scan with INFO-level logging enabled:
-        ./feroxbuster -u http://[::1] --norecursion -vv
+        ./feroxbuster -u http://[::1] --no-recursion -vv
 
     Read urls from STDIN; pipe only resulting urls out to another tool
         cat targets | ./feroxbuster --stdin --quiet -s 200 301 302 --redirects -x js | fff -s 200 -o js-files
@@ -225,6 +323,9 @@ EXAMPLES:
     Pass auth token via query parameter
         ./feroxbuster -u http://127.1 --query token=0123456789ABCDEF
 
+    Find links in javascript/html and make additional requests based on results
+        ./feroxbuster -u http://127.1 --extract-links
+
     Ludicrous speed... go!
         ./feroxbuster -u http://127.1 -t 200
     "#)

src/reporter.rs

@@ -1,8 +1,9 @@
-use crate::config::{CONFIGURATION, PROGRESS_PRINTER};
-use crate::utils::{ferox_print, status_colorizer};
-use crate::FeroxChannel;
+use crate::{
+    config::{CONFIGURATION, PROGRESS_PRINTER},
+    utils::{ferox_print, make_request, open_file},
+    FeroxChannel, FeroxResponse, FeroxSerialize,
+};
 use console::strip_ansi_codes;
-use reqwest::Response;
 use std::io::Write;
 use std::sync::{Arc, Once, RwLock};
 use std::{fs, io};
@@ -41,15 +42,15 @@ pub fn initialize(
     output_file: &str,
     save_output: bool,
 ) -> (
-    UnboundedSender<Response>,
-    UnboundedSender<String>,
+    UnboundedSender<FeroxResponse>,
+    UnboundedSender<FeroxResponse>,
     JoinHandle<()>,
     Option<JoinHandle<()>>,
 ) {
     log::trace!("enter: initialize({}, {})", output_file, save_output);
 
-    let (tx_rpt, rx_rpt): FeroxChannel<Response> = mpsc::unbounded_channel();
-    let (tx_file, rx_file): FeroxChannel<String> = mpsc::unbounded_channel();
+    let (tx_rpt, rx_rpt): FeroxChannel<FeroxResponse> = mpsc::unbounded_channel();
+    let (tx_file, rx_file): FeroxChannel<FeroxResponse> = mpsc::unbounded_channel();
 
     let file_clone = tx_file.clone();
 
@@ -81,8 +82,8 @@ pub fn initialize(
 /// The consumer simply receives responses and prints them if they meet the given
 /// reporting criteria
 async fn spawn_terminal_reporter(
-    mut resp_chan: UnboundedReceiver<Response>,
-    file_chan: UnboundedSender<String>,
+    mut resp_chan: UnboundedReceiver<FeroxResponse>,
+    file_chan: UnboundedSender<FeroxResponse>,
     save_output: bool,
 ) {
     log::trace!(
@@ -93,31 +94,15 @@ async fn spawn_terminal_reporter(
     );
 
     while let Some(resp) = resp_chan.recv().await {
-        log::debug!("received {} on reporting channel", resp.url());
-
-        if CONFIGURATION.statuscodes.contains(&resp.status().as_u16()) {
-            let report = if CONFIGURATION.quiet {
-                // -q used, just need the url
-                format!("{}\n", resp.url())
-            } else {
-                // normal printing with status and size
-                let status = status_colorizer(&resp.status().as_str());
-                format!(
-                    // example output
-                    // 200       3280 https://localhost.com/FAQ
-                    "{} {:>10} {}\n",
-                    status,
-                    resp.content_length().unwrap_or(0),
-                    resp.url()
-                )
-            };
+        log::trace!("received {} on reporting channel", resp.url());
 
+        if CONFIGURATION.status_codes.contains(&resp.status().as_u16()) {
             // 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());
                     }
@@ -127,7 +112,20 @@ async fn spawn_terminal_reporter(
                 }
             }
         }
-        log::debug!("report complete: {}", resp.url());
+        log::trace!("report complete: {}", resp.url());
+
+        if CONFIGURATION.replay_client.is_some()
+            && CONFIGURATION.replay_codes.contains(&resp.status().as_u16())
+        {
+            // 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 {
+                Ok(_) => {}
+                Err(e) => {
+                    log::error!("{}", e);
+                }
+            }
+        }
     }
     log::trace!("exit: spawn_terminal_reporter");
 }
@@ -136,7 +134,10 @@ 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 => {
@@ -153,47 +154,33 @@ 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

@@ -0,0 +1,531 @@
+use crate::{config::PROGRESS_PRINTER, progress, scanner::NUMBER_OF_REQUESTS, SLEEP_DURATION};
+use console::style;
+use indicatif::{ProgressBar, ProgressStyle};
+use lazy_static::lazy_static;
+use std::{
+    cmp::PartialEq,
+    fmt,
+    sync::{Arc, Mutex, RwLock},
+};
+use std::{
+    io::{stderr, Write},
+    sync::atomic::{AtomicBool, AtomicUsize, Ordering},
+};
+use tokio::{task::JoinHandle, time};
+use uuid::Uuid;
+
+lazy_static! {
+    /// A clock spinner protected with a RwLock to allow for a single thread to use at a time
+    // todo remove this when issue #107 is resolved
+    static ref SINGLE_SPINNER: RwLock<ProgressBar> = RwLock::new(get_single_spinner());
+}
+
+/// Single atomic number that gets incremented once, used to track first thread to interact with
+/// when pausing a scan
+static INTERACTIVE_BARRIER: AtomicUsize = AtomicUsize::new(0);
+
+/// Atomic boolean flag, used to determine whether or not a scan should pause or resume
+pub static PAUSE_SCAN: AtomicBool = AtomicBool::new(false);
+
+/// Simple enum used to flag a `FeroxScan` as likely a directory or file
+#[derive(Debug)]
+pub enum ScanType {
+    File,
+    Directory,
+}
+
+/// Struct to hold scan-related state
+///
+/// The purpose of this container is to open up the pathway to aborting currently running tasks and
+/// serialization of all scan state into a state file in order to resume scans that were cut short
+#[derive(Debug)]
+pub struct FeroxScan {
+    /// UUID that uniquely ID's the scan
+    pub id: String,
+
+    /// The URL that to be scanned
+    pub url: String,
+
+    /// The type of scan
+    pub scan_type: ScanType,
+
+    /// Whether or not this scan has completed
+    pub complete: bool,
+
+    /// The spawned tokio task performing this scan
+    pub task: Option<JoinHandle<()>>,
+
+    /// The progress bar associated with this scan
+    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 (issue #107)
+        }
+    }
+
+    /// Create a default FeroxScan, populates ID with a new UUID
+    fn default() -> Self {
+        let new_id = Uuid::new_v4().to_simple().to_string();
+
+        FeroxScan {
+            id: new_id,
+            task: None,
+            complete: false,
+            url: String::new(),
+            progress_bar: None,
+            scan_type: ScanType::File,
+        }
+    }
+
+    /// Simple helper to call .finish on the scan's progress bar
+    fn stop_progress_bar(&self) {
+        if let Some(pb) = &self.progress_bar {
+            pb.finish();
+        }
+    }
+
+    /// Simple helper get a progress bar
+    pub fn progress_bar(&mut self) -> ProgressBar {
+        if let Some(pb) = &self.progress_bar {
+            pb.clone()
+        } else {
+            let num_requests = NUMBER_OF_REQUESTS.load(Ordering::Relaxed);
+            let pb = progress::add_bar(&self.url, num_requests, false);
+
+            pb.reset_elapsed();
+
+            self.progress_bar = Some(pb.clone());
+
+            pb
+        }
+    }
+
+    /// Given a URL and ProgressBar, create a new FeroxScan, wrap it in an Arc and return it
+    pub fn new(url: &str, scan_type: ScanType, pb: Option<ProgressBar>) -> Arc<Mutex<Self>> {
+        let mut me = Self::default();
+
+        me.url = url.to_string();
+        me.scan_type = scan_type;
+        me.progress_bar = pb;
+
+        Arc::new(Mutex::new(me))
+    }
+
+    /// Mark the scan as complete and stop the scan's progress bar
+    pub fn finish(&mut self) {
+        self.complete = true;
+        self.stop_progress_bar();
+    }
+}
+
+/// Display implementation
+impl fmt::Display for FeroxScan {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        let complete = if self.complete {
+            style("complete").green()
+        } else {
+            style("incomplete").red()
+        };
+
+        write!(f, "{:10} {}", complete, self.url)
+    }
+}
+
+/// PartialEq implementation; uses FeroxScan.id for comparison
+impl PartialEq for FeroxScan {
+    fn eq(&self, other: &Self) -> bool {
+        self.id == other.id
+    }
+}
+
+/// Container around a locked hashset of `FeroxScan`s, adds wrappers for insertion and searching
+#[derive(Debug, Default)]
+pub struct FeroxScans {
+    /// Internal structure: locked hashset of `FeroxScan`s
+    pub scans: Mutex<Vec<Arc<Mutex<FeroxScan>>>>,
+}
+
+/// Implementation of `FeroxScans`
+impl FeroxScans {
+    /// Add a `FeroxScan` to the internal container
+    ///
+    /// If the internal container did NOT contain the scan, true is returned; else false
+    pub fn insert(&self, scan: Arc<Mutex<FeroxScan>>) -> bool {
+        let sentry = match scan.lock() {
+            Ok(locked_scan) => {
+                // If the container did contain the scan, set sentry to false
+                // If the container did not contain the scan, set sentry to true
+                !self.contains(&locked_scan.url)
+            }
+            Err(e) => {
+                // poisoned lock
+                log::error!("FeroxScan's ({:?}) mutex is poisoned: {}", self, e);
+                false
+            }
+        };
+
+        if sentry {
+            // can't update the internal container while the scan itself is locked, so first
+            // lock the scan and check the container for the scan's presence, then add if
+            // not found
+            match self.scans.lock() {
+                Ok(mut scans) => {
+                    scans.push(scan);
+                }
+                Err(e) => {
+                    log::error!("FeroxScans' container's mutex is poisoned: {}", e);
+                    return false;
+                }
+            }
+        }
+
+        sentry
+    }
+
+    /// Simple check for whether or not a FeroxScan is contained within the inner container based
+    /// on the given URL
+    pub fn contains(&self, url: &str) -> bool {
+        match self.scans.lock() {
+            Ok(scans) => {
+                for scan in scans.iter() {
+                    if let Ok(locked_scan) = scan.lock() {
+                        if locked_scan.url == url {
+                            return true;
+                        }
+                    }
+                }
+            }
+            Err(e) => {
+                log::error!("FeroxScans' container's mutex is poisoned: {}", e);
+            }
+        }
+        false
+    }
+
+    /// Find and return a `FeroxScan` based on the given URL
+    pub fn get_scan_by_url(&self, url: &str) -> Option<Arc<Mutex<FeroxScan>>> {
+        if let Ok(scans) = self.scans.lock() {
+            for scan in scans.iter() {
+                if let Ok(locked_scan) = scan.lock() {
+                    if locked_scan.url == url {
+                        return Some(scan.clone());
+                    }
+                }
+            }
+        }
+        None
+    }
+
+    /// Print all FeroxScans of type Directory
+    ///
+    /// Example:
+    ///   0: complete   https://10.129.45.20
+    ///   9: complete   https://10.129.45.20/images
+    ///  10: complete   https://10.129.45.20/assets
+    pub fn display_scans(&self) {
+        if let Ok(scans) = self.scans.lock() {
+            for (i, scan) in scans.iter().enumerate() {
+                if let Ok(unlocked_scan) = scan.lock() {
+                    match unlocked_scan.scan_type {
+                        ScanType::Directory => {
+                            PROGRESS_PRINTER.println(format!("{:3}: {}", i, unlocked_scan));
+                        }
+                        ScanType::File => {
+                            // we're only interested in displaying directory scans, as those are
+                            // the only ones that make sense to be stopped
+                        }
+                    }
+                }
+            }
+        }
+    }
+
+    /// Forced the calling thread into a busy loop
+    ///
+    /// Every `SLEEP_DURATION` milliseconds, the function examines the result stored in `PAUSE_SCAN`
+    ///
+    /// When the value stored in `PAUSE_SCAN` becomes `false`, the function returns, exiting the busy
+    /// loop
+    pub async fn pause(&self, get_user_input: bool) {
+        // function uses tokio::time, not std
+
+        // local testing showed a pretty slow increase (less than linear) in CPU usage as # of
+        // concurrent scans rose when SLEEP_DURATION was set to 500, using that as the default for now
+        let mut interval = time::interval(time::Duration::from_millis(SLEEP_DURATION));
+
+        // ignore any error returned
+        let _ = stderr().flush();
+
+        if INTERACTIVE_BARRIER.load(Ordering::Relaxed) == 0 {
+            INTERACTIVE_BARRIER.fetch_add(1, Ordering::Relaxed);
+
+            if get_user_input {
+                self.display_scans();
+
+                let mut user_input = String::new();
+                std::io::stdin().read_line(&mut user_input).unwrap();
+                // 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
+            }
+        }
+
+        if SINGLE_SPINNER.read().unwrap().is_finished() {
+            // todo remove this when issue #107 is resolved
+
+            // in order to not leave draw artifacts laying around in the terminal, we call
+            // finish_and_clear on the progress bar when resuming scans. For this reason, we need to
+            // check if the spinner is finished, and repopulate the RwLock with a new spinner if
+            // necessary
+            if let Ok(mut guard) = SINGLE_SPINNER.write() {
+                *guard = get_single_spinner();
+            }
+        }
+
+        if let Ok(spinner) = SINGLE_SPINNER.write() {
+            spinner.enable_steady_tick(120);
+        }
+
+        loop {
+            // first tick happens immediately, all others wait the specified duration
+            interval.tick().await;
+
+            if !PAUSE_SCAN.load(Ordering::Acquire) {
+                // PAUSE_SCAN is false, so we can exit the busy loop
+
+                if INTERACTIVE_BARRIER.load(Ordering::Relaxed) == 1 {
+                    INTERACTIVE_BARRIER.fetch_sub(1, Ordering::Relaxed);
+                }
+
+                if let Ok(spinner) = SINGLE_SPINNER.write() {
+                    // todo remove this when issue #107 is resolved
+                    spinner.finish_and_clear();
+                }
+
+                let _ = stderr().flush();
+
+                log::trace!("exit: pause_scan");
+                return;
+            }
+        }
+    }
+
+    /// Given a url, create a new `FeroxScan` and add it to `FeroxScans`
+    ///
+    /// If `FeroxScans` did not already contain the scan, return true; otherwise return false
+    ///
+    /// Also return a reference to the new `FeroxScan`
+    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);
+
+                progress_bar.reset_elapsed();
+
+                Some(progress_bar)
+            }
+            ScanType::File => None,
+        };
+
+        let ferox_scan = FeroxScan::new(&url, scan_type, bar);
+
+        // If the set did not contain the scan, true is returned.
+        // If the set did contain the scan, false is returned.
+        let response = self.insert(ferox_scan.clone());
+
+        (response, ferox_scan)
+    }
+
+    /// Given a url, create a new `FeroxScan` and add it to `FeroxScans` as a Directory Scan
+    ///
+    /// If `FeroxScans` did not already contain the scan, return true; otherwise return false
+    ///
+    /// Also return a reference to the new `FeroxScan`
+    pub fn add_directory_scan(&self, url: &str) -> (bool, Arc<Mutex<FeroxScan>>) {
+        self.add_scan(&url, ScanType::Directory)
+    }
+
+    /// Given a url, create a new `FeroxScan` and add it to `FeroxScans` as a File Scan
+    ///
+    /// If `FeroxScans` did not already contain the scan, return true; otherwise return false
+    ///
+    /// Also return a reference to the new `FeroxScan`
+    pub fn add_file_scan(&self, url: &str) -> (bool, Arc<Mutex<FeroxScan>>) {
+        self.add_scan(&url, ScanType::File)
+    }
+}
+
+/// Return a clock spinner, used when scans are paused
+// todo remove this when issue #107 is resolved
+fn get_single_spinner() -> ProgressBar {
+    log::trace!("enter: get_single_spinner");
+
+    let spinner = ProgressBar::new_spinner().with_style(
+        ProgressStyle::default_spinner()
+            .tick_strings(&[
+                "🕛", "🕐", "🕑", "🕒", "🕓", "🕔", "🕕", "🕖", "🕗", "🕘", "🕙", "🕚",
+            ])
+            .template(&format!(
+                "\t-= All Scans {{spinner}} {} =-",
+                style("Paused").red()
+            )),
+    );
+
+    log::trace!("exit: get_single_spinner -> {:?}", spinner);
+    spinner
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    /// test that get_single_spinner returns the correct spinner
+    // todo remove this when issue #107 is resolved
+    fn scanner_get_single_spinner_returns_spinner() {
+        let spinner = get_single_spinner();
+        assert!(!spinner.is_finished());
+    }
+
+    #[tokio::test(core_threads = 1)]
+    /// tests that pause_scan pauses execution and releases execution when PAUSE_SCAN is toggled
+    /// the spinner used during the test has had .finish_and_clear called on it, meaning that
+    /// a new one will be created, taking the if branch within the function
+    async fn scanner_pause_scan_with_finished_spinner() {
+        let now = time::Instant::now();
+        let urls = FeroxScans::default();
+
+        PAUSE_SCAN.store(true, Ordering::Relaxed);
+
+        let expected = time::Duration::from_secs(2);
+
+        tokio::spawn(async move {
+            time::delay_for(expected).await;
+            PAUSE_SCAN.store(false, Ordering::Relaxed);
+        });
+
+        urls.pause(false).await;
+
+        assert!(now.elapsed() > expected);
+    }
+
+    #[test]
+    /// add an unknown url to the hashset, expect true
+    fn add_url_to_list_of_scanned_urls_with_unknown_url() {
+        let urls = FeroxScans::default();
+        let url = "http://unknown_url";
+        let (result, _scan) = urls.add_scan(url, ScanType::Directory);
+        assert_eq!(result, true);
+    }
+
+    #[test]
+    /// add a known url to the hashset, with a trailing slash, expect false
+    fn add_url_to_list_of_scanned_urls_with_known_url() {
+        let urls = FeroxScans::default();
+        let pb = ProgressBar::new(1);
+        let url = "http://unknown_url/";
+        let scan = FeroxScan::new(url, ScanType::Directory, Some(pb));
+
+        assert_eq!(urls.insert(scan), true);
+
+        let (result, _scan) = urls.add_scan(url, ScanType::Directory);
+
+        assert_eq!(result, false);
+    }
+
+    #[test]
+    /// abort should call stop_progress_bar, marking it as finished
+    fn abort_stops_progress_bar() {
+        let pb = ProgressBar::new(1);
+        let url = "http://unknown_url/";
+        let scan = FeroxScan::new(url, ScanType::Directory, Some(pb));
+
+        assert_eq!(
+            scan.lock()
+                .unwrap()
+                .progress_bar
+                .as_ref()
+                .unwrap()
+                .is_finished(),
+            false
+        );
+
+        scan.lock().unwrap().abort();
+
+        assert_eq!(
+            scan.lock()
+                .unwrap()
+                .progress_bar
+                .as_ref()
+                .unwrap()
+                .is_finished(),
+            true
+        );
+    }
+
+    #[test]
+    /// add a known url to the hashset, without a trailing slash, expect false
+    fn add_url_to_list_of_scanned_urls_with_known_url_without_slash() {
+        let urls = FeroxScans::default();
+        let url = "http://unknown_url";
+        let scan = FeroxScan::new(url, ScanType::File, None);
+
+        assert_eq!(urls.insert(scan), true);
+
+        let (result, _scan) = urls.add_scan(url, ScanType::File);
+
+        assert_eq!(result, false);
+    }
+
+    #[test]
+    /// just increasing coverage, no real expectations
+    fn call_display_scans() {
+        let urls = FeroxScans::default();
+        let pb = ProgressBar::new(1);
+        let pb_two = ProgressBar::new(2);
+        let url = "http://unknown_url/";
+        let url_two = "http://unknown_url/fa";
+        let scan = FeroxScan::new(url, ScanType::Directory, Some(pb));
+        let scan_two = FeroxScan::new(url_two, ScanType::Directory, Some(pb_two));
+
+        scan_two.lock().unwrap().finish(); // one complete, one incomplete
+
+        assert_eq!(urls.insert(scan), true);
+
+        urls.display_scans();
+    }
+
+    #[test]
+    /// ensure that PartialEq compares FeroxScan.id fields
+    fn partial_eq_compares_the_id_field() {
+        let url = "http://unknown_url/";
+        let scan = FeroxScan::new(url, ScanType::Directory, None);
+        let scan_two = FeroxScan::new(url, ScanType::Directory, None);
+
+        assert!(!scan.lock().unwrap().eq(&scan_two.lock().unwrap()));
+
+        scan_two.lock().unwrap().id = scan.lock().unwrap().id.clone();
+
+        assert!(scan.lock().unwrap().eq(&scan_two.lock().unwrap()));
+    }
+
+    #[test]
+    /// show that a new progress bar is created if one doesn't exist
+    fn ferox_scan_get_progress_bar_when_none_is_set() {
+        let mut scan = FeroxScan::default();
+
+        assert!(scan.progress_bar.is_none()); // no pb exists
+
+        let pb = scan.progress_bar();
+
+        assert!(scan.progress_bar.is_some()); // new pb created
+        assert!(!pb.is_finished()) // not finished
+    }
+}

src/scanner.rs

@@ -1,59 +1,87 @@
-use crate::config::{CONFIGURATION, PROGRESS_BAR};
-use crate::heuristics::WildcardFilter;
-use crate::utils::{format_url, get_current_depth, get_url_path_length, make_request};
-use crate::{heuristics, progress, FeroxChannel};
-use futures::future::{BoxFuture, FutureExt};
-use futures::{stream, StreamExt};
+use crate::{
+    config::{Configuration, CONFIGURATION},
+    extractor::get_links,
+    filters::{
+        FeroxFilter, LinesFilter, RegexFilter, SizeFilter, StatusCodeFilter, WildcardFilter,
+        WordsFilter,
+    },
+    heuristics,
+    scan_manager::{FeroxScans, PAUSE_SCAN},
+    utils::{format_url, get_current_depth, make_request},
+    FeroxChannel, FeroxResponse,
+};
+use futures::{
+    future::{BoxFuture, FutureExt},
+    stream, StreamExt,
+};
 use lazy_static::lazy_static;
-use reqwest::{Response, Url};
-use std::collections::HashSet;
-use std::convert::TryInto;
-use std::ops::Deref;
-use std::sync::atomic::{AtomicUsize, Ordering};
-use std::sync::{Arc, RwLock};
-use tokio::sync::mpsc::{self, UnboundedReceiver, UnboundedSender};
-use tokio::task::JoinHandle;
+use regex::Regex;
+use reqwest::Url;
+#[cfg(not(test))]
+use std::process::exit;
+use std::{
+    collections::HashSet,
+    convert::TryInto,
+    ops::Deref,
+    sync::atomic::{AtomicU64, AtomicUsize, Ordering},
+    sync::{Arc, RwLock},
+};
+use tokio::{
+    sync::{
+        mpsc::{self, UnboundedReceiver, UnboundedSender},
+        Semaphore,
+    },
+    task::JoinHandle,
+};
 
 /// Single atomic number that gets incremented once, used to track first scan vs. all others
 static CALL_COUNT: AtomicUsize = AtomicUsize::new(0);
 
+/// Single atomic number that gets holds the number of requests to be sent per directory scanned
+pub static NUMBER_OF_REQUESTS: AtomicU64 = AtomicU64::new(0);
+
 lazy_static! {
     /// Set of urls that have been sent to [scan_url](fn.scan_url.html), used for deduplication
-    static ref SCANNED_URLS: RwLock<HashSet<String>> = RwLock::new(HashSet::new());
+    pub static ref SCANNED_URLS: FeroxScans = FeroxScans::default();
+
+    /// 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()));
+
+    /// Bounded semaphore used as a barrier to limit concurrent scans
+    static ref SCAN_LIMITER: Semaphore = Semaphore::new(CONFIGURATION.scan_limit);
 }
 
-/// Adds the given url to `SCANNED_URLS`
+/// Adds the given FeroxFilter to the given list of FeroxFilter implementors
 ///
-/// If `SCANNED_URLS` did not already contain the url, return true; otherwise return false
-fn add_url_to_list_of_scanned_urls(resp: &str, scanned_urls: &RwLock<HashSet<String>>) -> bool {
+/// If the given list did not already contain the filter, return true; otherwise return false
+fn add_filter_to_list_of_ferox_filters(
+    filter: Box<dyn FeroxFilter>,
+    ferox_filters: Arc<RwLock<Vec<Box<dyn FeroxFilter>>>>,
+) -> bool {
     log::trace!(
-        "enter: add_url_to_list_of_scanned_urls({}, {:?})",
-        resp,
-        scanned_urls
+        "enter: add_filter_to_list_of_ferox_filters({:?}, {:?})",
+        filter,
+        ferox_filters
     );
 
-    match scanned_urls.write() {
-        // check new url against what's already been scanned
-        Ok(mut urls) => {
-            let normalized_url = if resp.ends_with('/') {
-                // append a / to the list of 'seen' urls, this is to prevent the case where
-                // 3xx and 2xx duplicate eachother
-                resp.to_string()
-            } else {
-                format!("{}/", resp)
-            };
+    match ferox_filters.write() {
+        Ok(mut filters) => {
+            // If the set did not contain the assigned filter, true is returned.
+            // If the set did contain the assigned filter, false is returned.
+            if filters.contains(&filter) {
+                log::trace!("exit: add_filter_to_list_of_ferox_filters -> false");
+                return false;
+            }
 
-            // If the set did not contain resp, true is returned.
-            // If the set did contain resp, false is returned.
-            let response = urls.insert(normalized_url);
+            filters.push(filter);
 
-            log::trace!("exit: add_url_to_list_of_scanned_urls -> {}", response);
-            response
+            log::trace!("exit: add_filter_to_list_of_ferox_filters -> true");
+            true
         }
         Err(e) => {
             // poisoned lock
-            log::error!("Set of scanned urls poisoned: {}", e);
-            log::trace!("exit: add_url_to_list_of_scanned_urls -> false");
+            log::error!("Set of wildcard filters poisoned: {}", e);
+            log::trace!("exit: add_filter_to_list_of_ferox_filters -> false");
             false
         }
     }
@@ -66,8 +94,8 @@ fn spawn_recursion_handler(
     mut recursion_channel: UnboundedReceiver<String>,
     wordlist: Arc<HashSet<String>>,
     base_depth: usize,
-    tx_term: UnboundedSender<Response>,
-    tx_file: UnboundedSender<String>,
+    tx_term: UnboundedSender<FeroxResponse>,
+    tx_file: UnboundedSender<FeroxResponse>,
 ) -> BoxFuture<'static, Vec<JoinHandle<()>>> {
     log::trace!(
         "enter: spawn_recursion_handler({:?}, wordlist[{} words...], {}, {:?}, {:?})",
@@ -80,8 +108,9 @@ fn spawn_recursion_handler(
 
     let boxed_future = async move {
         let mut scans = vec![];
+
         while let Some(resp) = recursion_channel.recv().await {
-            let unknown = add_url_to_list_of_scanned_urls(&resp, &SCANNED_URLS);
+            let (unknown, _) = SCANNED_URLS.add_directory_scan(&resp);
 
             if !unknown {
                 // not unknown, i.e. we've seen the url before and don't need to scan again
@@ -95,7 +124,7 @@ fn spawn_recursion_handler(
             let resp_clone = resp.clone();
             let list_clone = wordlist.clone();
 
-            scans.push(tokio::spawn(async move {
+            let future = tokio::spawn(async move {
                 scan_url(
                     resp_clone.to_owned().as_str(),
                     list_clone,
@@ -104,7 +133,9 @@ fn spawn_recursion_handler(
                     file_clone,
                 )
                 .await
-            }));
+            });
+
+            scans.push(future);
         }
         scans
     }
@@ -133,7 +164,7 @@ fn create_urls(target_url: &str, word: &str, extensions: &[String]) -> Vec<Url>
     if let Ok(url) = format_url(
         &target_url,
         &word,
-        CONFIGURATION.addslash,
+        CONFIGURATION.add_slash,
         &CONFIGURATION.queries,
         None,
     ) {
@@ -144,7 +175,7 @@ fn create_urls(target_url: &str, word: &str, extensions: &[String]) -> Vec<Url>
         if let Ok(url) = format_url(
             &target_url,
             &word,
-            CONFIGURATION.addslash,
+            CONFIGURATION.add_slash,
             &CONFIGURATION.queries,
             Some(ext),
         ) {
@@ -160,8 +191,8 @@ fn create_urls(target_url: &str, word: &str, extensions: &[String]) -> Vec<Url>
 ///
 /// handles 2xx and 3xx responses by either checking if the url ends with a / (2xx)
 /// or if the Location header is present and matches the base url + / (3xx)
-fn response_is_directory(response: &Response) -> bool {
-    log::trace!("enter: is_directory({:?})", response);
+fn response_is_directory(response: &FeroxResponse) -> bool {
+    log::trace!("enter: is_directory({})", response);
 
     if response.status().is_redirection() {
         // status code is 3xx
@@ -187,16 +218,14 @@ fn response_is_directory(response: &Response) -> bool {
                 }
             }
             None => {
-                log::debug!(
-                    "expected Location header, but none was found: {:?}",
-                    response
-                );
+                log::debug!("expected Location header, but none was found: {}", response);
                 log::trace!("exit: is_directory -> false");
                 return false;
             }
         }
     } else if response.status().is_success() {
         // status code is 2xx, need to check if it ends in /
+
         if response.url().as_str().ends_with('/') {
             log::debug!("{} is directory suitable for recursion", response.url());
             log::trace!("exit: is_directory -> true");
@@ -240,12 +269,12 @@ fn reached_max_depth(url: &Url, base_depth: usize, max_depth: usize) -> bool {
 ///
 /// When a recursion opportunity is found, the new url is sent across the recursion channel
 async fn try_recursion(
-    response: &Response,
+    response: &FeroxResponse,
     base_depth: usize,
     transmitter: UnboundedSender<String>,
 ) {
     log::trace!(
-        "enter: try_recursion({:?}, {}, {:?})",
+        "enter: try_recursion({}, {}, {:?})",
         response,
         base_depth,
         transmitter
@@ -290,6 +319,25 @@ async fn try_recursion(
     log::trace!("exit: try_recursion");
 }
 
+/// Simple helper to stay DRY; determines whether or not a given `FeroxResponse` should be reported
+/// to the user or not.
+pub fn should_filter_response(response: &FeroxResponse) -> bool {
+    match FILTERS.read() {
+        Ok(filters) => {
+            for filter in filters.iter() {
+                // wildcard.should_filter goes here
+                if filter.should_filter_response(&response) {
+                    return true;
+                }
+            }
+        }
+        Err(e) => {
+            log::error!("{}", e);
+        }
+    }
+    false
+}
+
 /// Wrapper for [make_request](fn.make_request.html)
 ///
 /// Handles making multiple requests based on the presence of extensions
@@ -299,9 +347,8 @@ async fn make_requests(
     target_url: &str,
     word: &str,
     base_depth: usize,
-    filter: Arc<WildcardFilter>,
     dir_chan: UnboundedSender<String>,
-    report_chan: UnboundedSender<Response>,
+    report_chan: UnboundedSender<FeroxResponse>,
 ) {
     log::trace!(
         "enter: make_requests({}, {}, {}, {:?}, {:?})",
@@ -316,61 +363,105 @@ async fn make_requests(
 
     for url in urls {
         if let Ok(response) = make_request(&CONFIGURATION.client, &url).await {
-            // response came back without error
+            // response came back without error, convert it to FeroxResponse
+            let ferox_response = FeroxResponse::from(response, true).await;
 
             // do recursion if appropriate
-            if !CONFIGURATION.norecursion && response_is_directory(&response) {
-                try_recursion(&response, base_depth, dir_chan.clone()).await;
+            if !CONFIGURATION.no_recursion {
+                try_recursion(&ferox_response, base_depth, dir_chan.clone()).await;
             }
 
             // purposefully doing recursion before filtering. the thought process is that
             // even though this particular url is filtered, subsequent urls may not
 
-            let content_len = &response.content_length().unwrap_or(0);
-
-            if CONFIGURATION.sizefilters.contains(content_len) {
-                // filtered value from --sizefilters, move on to the next url
-                log::debug!("size filter: filtered out {}", response.url());
+            if should_filter_response(&ferox_response) {
                 continue;
             }
 
-            if filter.size > 0 && filter.size == *content_len && !CONFIGURATION.dontfilter {
-                // static wildcard size found during testing
-                // size isn't default, size equals response length, and auto-filter is on
-                log::debug!("static wildcard: filtered out {}", response.url());
-                continue;
-            }
+            if CONFIGURATION.extract_links && !ferox_response.status().is_redirection() {
+                let new_links = get_links(&ferox_response).await;
 
-            if filter.dynamic > 0 && !CONFIGURATION.dontfilter {
-                // dynamic wildcard offset found during testing
+                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,
+                    };
 
-                // I'm about to manually split this url path instead of using reqwest::Url's
-                // builtin parsing. The reason is that they call .split() on the url path
-                // except that I don't want an empty string taking up the last index in the
-                // event that the url ends with a forward slash.  It's ugly enough to be split
-                // into its own function for readability.
-                let url_len = get_url_path_length(&response.url());
+                    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;
+                    }
 
-                if url_len + filter.dynamic == *content_len {
-                    log::debug!("dynamic wildcard: filtered out {}", response.url());
-                    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;
+
+                    // filter if necessary
+                    if should_filter_response(&new_ferox_response) {
+                        continue;
+                    }
+
+                    if new_ferox_response.is_file() {
+                        // very likely a file, simply request and report
+                        log::debug!("Singular extraction: {}", new_ferox_response);
+
+                        SCANNED_URLS.add_file_scan(&new_url.to_string());
+
+                        send_report(report_chan.clone(), new_ferox_response);
+
+                        continue;
+                    }
+
+                    if !CONFIGURATION.no_recursion {
+                        log::debug!("Recursive extraction: {}", new_ferox_response);
+
+                        if new_ferox_response.status().is_success()
+                            && !new_ferox_response.url().as_str().ends_with('/')
+                        {
+                            // since all of these are 2xx, recursion is only attempted if the
+                            // url ends in a /. I am actually ok with adding the slash and not
+                            // adding it, as both have merit.  Leaving it in for now to see how
+                            // things turn out (current as of: v1.1.0)
+                            new_ferox_response.set_url(&format!("{}/", new_ferox_response.url()));
+                        }
+
+                        try_recursion(&new_ferox_response, base_depth, dir_chan.clone()).await;
+                    }
                 }
             }
 
             // everything else should be reported
-            match report_chan.send(response) {
-                Ok(_) => {
-                    log::debug!("sent {}/{} over reporting channel", &target_url, &word);
-                }
-                Err(e) => {
-                    log::error!("wtf: {}", e);
-                }
-            }
+            send_report(report_chan.clone(), ferox_response);
         }
     }
     log::trace!("exit: 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) {
+    log::trace!("enter: send_report({:?}, {}", report_sender, response);
+
+    match report_sender.send(response) {
+        Ok(_) => {}
+        Err(e) => {
+            log::error!("{}", e);
+        }
+    }
+
+    log::trace!("exit: send_report");
+}
+
 /// Scan a given url using a given wordlist
 ///
 /// This is the primary entrypoint for the scanner
@@ -378,8 +469,8 @@ pub async fn scan_url(
     target_url: &str,
     wordlist: Arc<HashSet<String>>,
     base_depth: usize,
-    tx_term: UnboundedSender<Response>,
-    tx_file: UnboundedSender<String>,
+    tx_term: UnboundedSender<FeroxResponse>,
+    tx_file: UnboundedSender<FeroxResponse>,
 ) {
     log::trace!(
         "enter: scan_url({:?}, wordlist[{} words...], {}, {:?}, {:?})",
@@ -394,29 +485,42 @@ pub async fn scan_url(
 
     let (tx_dir, rx_dir): FeroxChannel<String> = mpsc::unbounded_channel();
 
-    let num_reqs_expected: u64 = if CONFIGURATION.extensions.is_empty() {
-        wordlist.len().try_into().unwrap()
-    } else {
-        let total = wordlist.len() * (CONFIGURATION.extensions.len() + 1);
-        total.try_into().unwrap()
-    };
-
-    let progress_bar = progress::add_bar(&target_url, num_reqs_expected, false);
-    progress_bar.reset_elapsed();
-
     if CALL_COUNT.load(Ordering::Relaxed) == 0 {
-        // join can only be called once, otherwise it causes the thread to panic
-        tokio::task::spawn_blocking(move || PROGRESS_BAR.join().unwrap());
         CALL_COUNT.fetch_add(1, Ordering::Relaxed);
 
-        // this protection around join also allows us to add the first scanned url to SCANNED_URLS
+        // this protection allows us to add the first scanned url to SCANNED_URLS
         // from within the scan_url function instead of the recursion handler
-        add_url_to_list_of_scanned_urls(&target_url, &SCANNED_URLS);
+        SCANNED_URLS.add_directory_scan(&target_url);
     }
 
+    let ferox_scan = match SCANNED_URLS.get_scan_by_url(&target_url) {
+        Some(scan) => scan,
+        None => {
+            log::error!(
+                "Could not find FeroxScan associated with {}; this shouldn't happen... exiting",
+                target_url
+            );
+            return;
+        }
+    };
+
+    let progress_bar = match ferox_scan.lock() {
+        Ok(mut scan) => scan.progress_bar(),
+        Err(e) => {
+            log::error!("FeroxScan's ({:?}) mutex is poisoned: {}", ferox_scan, e);
+            return;
+        }
+    };
+
+    // When acquire is called and the semaphore has remaining permits, the function immediately
+    // returns a permit. However, if no remaining permits are available, acquire (asynchronously)
+    // waits until an outstanding permit is dropped. At this point, the freed permit is assigned
+    // to the caller.
+    let permit = SCAN_LIMITER.acquire().await;
+
     // 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();
@@ -433,23 +537,33 @@ pub async fn scan_url(
         .await
     });
 
+    // add any wildcard filters to `FILTERS`
     let filter =
-        match heuristics::wildcard_test(&target_url, wildcard_bar, heuristics_file_clone).await {
-            Some(f) => Arc::new(f),
-            None => Arc::new(WildcardFilter::default()),
+        match heuristics::wildcard_test(&target_url, wildcard_bar, heuristics_term_clone).await {
+            Some(f) => Box::new(f),
+            None => Box::new(WildcardFilter::default()),
         };
 
+    add_filter_to_list_of_ferox_filters(filter, FILTERS.clone());
+
     // producer tasks (mp of mpsc); responsible for making requests
     let producers = stream::iter(looping_words.deref().to_owned())
         .map(|word| {
-            let wc_filter = filter.clone();
             let txd = tx_dir.clone();
             let txr = tx_term.clone();
             let pb = progress_bar.clone(); // progress bar is an Arc around internal state
             let tgt = target_url.to_string(); // done to satisfy 'static lifetime below
             (
                 tokio::spawn(async move {
-                    make_requests(&tgt, &word, base_depth, wc_filter, txd, txr).await
+                    if PAUSE_SCAN.load(Ordering::Acquire) {
+                        // for every word in the wordlist, check to see if PAUSE_SCAN is set to true
+                        // when true; enter a busy loop that only exits by setting PAUSE_SCAN back
+                        // to false
+
+                        // todo change to true when issue #107 is resolved
+                        SCANNED_URLS.pause(false).await;
+                    }
+                    make_requests(&tgt, &word, base_depth, txd, txr).await
                 }),
                 pb,
             )
@@ -457,7 +571,7 @@ pub async fn scan_url(
         .for_each_concurrent(CONFIGURATION.threads, |(resp, bar)| async move {
             match resp.await {
                 Ok(_) => {
-                    bar.inc(1);
+                    bar.inc((CONFIGURATION.extensions.len() + 1) as u64);
                 }
                 Err(e) => {
                     log::error!("error awaiting a response: {}", e);
@@ -470,7 +584,12 @@ pub async fn scan_url(
     producers.await;
     log::trace!("done awaiting scan producers");
 
-    progress_bar.finish();
+    // drop the current permit so the semaphore will allow another scan to proceed
+    drop(permit);
+
+    if let Ok(mut scan) = ferox_scan.lock() {
+        scan.finish();
+    }
 
     // manually drop tx in order for the rx task's while loops to eval to false
     log::trace!("dropped recursion handler's transmitter");
@@ -484,6 +603,89 @@ pub async fn scan_url(
     log::trace!("exit: 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, 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 config.extensions.is_empty() {
+        num_words.try_into().unwrap()
+    } else {
+        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 &config.filter_status {
+        let filter = StatusCodeFilter {
+            filter_code: *code_filter,
+        };
+        let boxed_filter = Box::new(filter);
+        add_filter_to_list_of_ferox_filters(boxed_filter, FILTERS.clone());
+    }
+
+    // add any line count filters to `FILTERS` (-N|--filter-lines)
+    for lines_filter in &config.filter_line_count {
+        let filter = LinesFilter {
+            line_count: *lines_filter,
+        };
+        let boxed_filter = Box::new(filter);
+        add_filter_to_list_of_ferox_filters(boxed_filter, FILTERS.clone());
+    }
+
+    // add any line count filters to `FILTERS` (-W|--filter-words)
+    for words_filter in &config.filter_word_count {
+        let filter = WordsFilter {
+            word_count: *words_filter,
+        };
+        let boxed_filter = Box::new(filter);
+        add_filter_to_list_of_ferox_filters(boxed_filter, FILTERS.clone());
+    }
+
+    // add any line count filters to `FILTERS` (-S|--filter-size)
+    for size_filter in &config.filter_size {
+        let filter = SizeFilter {
+            content_length: *size_filter,
+        };
+        let boxed_filter = Box::new(filter);
+        add_filter_to_list_of_ferox_filters(boxed_filter, FILTERS.clone());
+    }
+
+    // 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());
+    }
+
+    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'
+        SCAN_LIMITER.add_permits(usize::MAX >> 4);
+    }
+
+    log::trace!("exit: initialize");
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
@@ -583,37 +785,11 @@ mod tests {
     }
 
     #[test]
-    /// add an unknown url to the hashset, expect true
-    fn add_url_to_list_of_scanned_urls_with_unknown_url() {
-        let urls = RwLock::new(HashSet::<String>::new());
-        let url = "http://unknown_url";
-        assert_eq!(add_url_to_list_of_scanned_urls(url, &urls), true);
-    }
-
-    #[test]
-    /// add a known url to the hashset, with a trailing slash, expect false
-    fn add_url_to_list_of_scanned_urls_with_known_url() {
-        let urls = RwLock::new(HashSet::<String>::new());
-        let url = "http://unknown_url/";
-
-        assert_eq!(urls.write().unwrap().insert(url.to_string()), true);
-
-        assert_eq!(add_url_to_list_of_scanned_urls(url, &urls), false);
-    }
-
-    #[test]
-    /// add a known url to the hashset, without a trailing slash, expect false
-    fn add_url_to_list_of_scanned_urls_with_known_url_without_slash() {
-        let urls = RwLock::new(HashSet::<String>::new());
-        let url = "http://unknown_url";
-
-        assert_eq!(
-            urls.write()
-                .unwrap()
-                .insert("http://unknown_url/".to_string()),
-            true
-        );
-
-        assert_eq!(add_url_to_list_of_scanned_urls(url, &urls), false);
+    #[should_panic]
+    /// call initialize with a bad regex, triggering a panic
+    fn initialize_panics_on_bad_regex() {
+        let mut config = Configuration::default();
+        config.filter_regex = vec![r"(".to_string()];
+        initialize(1, &config);
     }
 }

src/utils.rs

@@ -1,9 +1,41 @@
-use crate::FeroxResult;
+use crate::{
+    config::{CONFIGURATION, PROGRESS_PRINTER},
+    FeroxError, FeroxResult,
+};
 use console::{strip_ansi_codes, style, user_attended};
 use indicatif::ProgressBar;
-use reqwest::Url;
-use reqwest::{Client, Response};
+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
 ///
@@ -19,13 +51,7 @@ use std::convert::TryInto;
 pub fn get_current_depth(target: &str) -> usize {
     log::trace!("enter: get_current_depth({})", target);
 
-    let target = if !target.ends_with('/') {
-        // target url doesn't end with a /, for the purposes of determining depth, we'll normalize
-        // all urls to end in a / and then calculate accordingly
-        format!("{}/", target)
-    } else {
-        String::from(target)
-    };
+    let target = normalize_url(target);
 
     match Url::parse(&target) {
         Ok(url) => {
@@ -88,8 +114,8 @@ pub fn get_url_path_length(url: &Url) -> u64 {
 
     let path = url.path();
 
-    let segments = if path.starts_with('/') {
-        path[1..].split_terminator('/')
+    let segments = if let Some(split) = path.strip_prefix('/') {
+        split.split_terminator('/')
     } else {
         log::trace!("exit: get_url_path_length -> 0");
         return 0;
@@ -140,7 +166,7 @@ pub fn ferox_print(msg: &str, bar: &ProgressBar) {
 pub fn format_url(
     url: &str,
     word: &str,
-    addslash: bool,
+    add_slash: bool,
     queries: &[(String, String)],
     extension: Option<&str>,
 ) -> FeroxResult<Url> {
@@ -148,11 +174,32 @@ pub fn format_url(
         "enter: format_url({}, {}, {}, {:?} {:?})",
         url,
         word,
-        addslash,
+        add_slash,
         queries,
         extension
     );
 
+    if Url::parse(&word).is_ok() {
+        // when a full url is passed in as a word to be joined to a base url using
+        // reqwest::Url::join, the result is that the word (url) completely overwrites the base
+        // url, potentially resulting in requests to places that aren't actually the target
+        // specified.
+        //
+        // in order to resolve the issue, we check if the word from the wordlist is a parsable URL
+        // and if so, don't do any further processing
+        let message = format!(
+            "word ({}) from the wordlist is actually a URL, skipping...",
+            word
+        );
+        log::warn!("{}", message);
+
+        let mut err = FeroxError::default();
+        err.message = message;
+
+        log::trace!("exit: format_url -> {}", err);
+        return Err(Box::new(err));
+    }
+
     // from reqwest::Url::join
     //   Note: a trailing slash is significant. Without it, the last path component
     //   is considered to be a “file” name to be removed to get at the “directory”
@@ -160,7 +207,11 @@ pub fn format_url(
     //
     // the transforms that occur here will need to keep this in mind, i.e. add a slash to preserve
     // the current directory sent as part of the url
-    let url = if !url.ends_with('/') {
+    let url = if word.is_empty() {
+        // v1.0.6: added during --extract-links feature inplementation to support creating urls
+        // that were extracted from response bodies, i.e. http://localhost/some/path/js/main.js
+        url.to_string()
+    } else if !url.ends_with('/') {
         format!("{}/", url)
     } else {
         url.to_string()
@@ -171,7 +222,7 @@ pub fn format_url(
     // extensions and slashes are mutually exclusive cases
     let word = if extension.is_some() {
         format!("{}.{}", word, extension.unwrap())
-    } else if addslash && !word.ends_with('/') {
+    } else if add_slash && !word.ends_with('/') {
         // -f used, and word doesn't already end with a /
         format!("{}/", word)
     } else {
@@ -217,7 +268,6 @@ pub async fn make_request(client: &Client, url: &Url) -> FeroxResult<Response> {
 
     match client.get(url.to_owned()).send().await {
         Ok(resp) => {
-            log::debug!("requested Url: {}", resp.url());
             log::trace!("exit: make_request -> {:?}", resp);
             Ok(resp)
         }
@@ -226,6 +276,19 @@ pub async fn make_request(client: &Client, url: &Url) -> FeroxResult<Response> {
             if e.to_string().contains("operation timed out") {
                 // only warn for timeouts, while actual errors are still left as errors
                 log::warn!("Error while making request: {}", e);
+            } else if e.is_redirect() {
+                if let Some(last_redirect) = e.url() {
+                    // get where we were headed (last_redirect) and where we came from (url)
+                    let fancy_message = format!("{} !=> {}", url, last_redirect);
+
+                    let report = if let Some(msg_status) = e.status() {
+                        create_report_string(msg_status.as_str(), "-1", "-1", "-1", &fancy_message)
+                    } else {
+                        create_report_string("UNK", "-1", "-1", "-1", &fancy_message)
+                    };
+
+                    ferox_print(&report, &PROGRESS_PRINTER)
+                };
             } else {
                 log::error!("Error while making request: {}", e);
             }
@@ -234,10 +297,129 @@ pub async fn make_request(client: &Client, url: &Url) -> FeroxResult<Response> {
     }
 }
 
+/// Helper to create the standard line for output to file/terminal
+///
+/// example output:
+/// 200      127l      283w     4134c http://localhost/faq
+pub fn create_report_string(
+    status: &str,
+    line_count: &str,
+    word_count: &str,
+    content_length: &str,
+    url: &str,
+) -> String {
+    if CONFIGURATION.quiet {
+        // -q used, just need the url
+        format!("{}\n", url)
+    } else {
+        // normal printing with status and sizes
+        let color_status = status_colorizer(status);
+        format!(
+            "{} {:>8}l {:>8}w {:>8}c {}\n",
+            color_status, line_count, word_count, content_length, url
+        )
+    }
+}
+
+/// Attempts to set the soft limit for the RLIMIT_NOFILE resource
+///
+/// RLIMIT_NOFILE is the maximum number of file descriptors that can be opened by this process
+///
+/// The soft limit is the value that the kernel enforces for the corresponding resource.
+/// The hard limit acts as a ceiling for the soft limit: an unprivileged process may set only its
+/// soft limit to a value in the range from 0 up to the hard limit, and (irreversibly) lower its
+/// hard limit.
+///
+/// A child process created via fork(2) inherits its parent's resource limits. Resource limits are
+/// per-process attributes that are shared by all of the threads in a process.
+///
+/// Based on the above information, no attempt is made to restore the limit to its pre-scan value
+/// as the adjustment made here is only valid for the scan itself (and any child processes, of which
+/// there are none).
+#[cfg(not(target_os = "windows"))]
+pub fn set_open_file_limit(limit: usize) -> bool {
+    log::trace!("enter: set_open_file_limit");
+
+    if let Ok((soft, hard)) = getrlimit(Resource::NOFILE) {
+        if hard.as_usize() > limit {
+            // our default open file limit is less than the current hard limit, this means we can
+            // set the soft limit to our default
+            let new_soft_limit = Rlim::from_usize(limit);
+
+            if setrlimit(Resource::NOFILE, new_soft_limit, hard).is_ok() {
+                log::debug!("set open file descriptor limit to {}", limit);
+
+                log::trace!("exit: set_open_file_limit -> {}", true);
+                return true;
+            }
+        } else if soft != hard {
+            // hard limit is lower than our default, the next best option is to set the soft limit as
+            // high as the hard limit will allow
+            if setrlimit(Resource::NOFILE, hard, hard).is_ok() {
+                log::debug!("set open file descriptor limit to {}", limit);
+
+                log::trace!("exit: set_open_file_limit -> {}", true);
+                return true;
+            }
+        }
+    }
+
+    // failed to set a new limit, as limit adjustments are a 'nice to have', we'll just log
+    // and move along
+    log::warn!("could not set open file descriptor limit to {}", limit);
+
+    log::trace!("exit: set_open_file_limit -> {}", false);
+    false
+}
+
+/// Simple helper to abstract away adding a forward-slash to a url if not present
+///
+/// used mostly for deduplication purposes and url state tracking
+pub fn normalize_url(url: &str) -> String {
+    log::trace!("enter: normalize_url({})", url);
+
+    let normalized = if url.ends_with('/') {
+        url.to_string()
+    } else {
+        format!("{}/", url)
+    };
+
+    log::trace!("exit: normalize_url -> {}", normalized);
+    normalized
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
 
+    #[test]
+    /// set_open_file_limit with a low requested limit succeeds
+    fn utils_set_open_file_limit_with_low_requested_limit() {
+        let (_, hard) = getrlimit(Resource::NOFILE).unwrap();
+        let lower_limit = hard.as_usize() - 1;
+        assert!(set_open_file_limit(lower_limit));
+    }
+
+    #[test]
+    /// set_open_file_limit with a high requested limit succeeds
+    fn utils_set_open_file_limit_with_high_requested_limit() {
+        let (_, hard) = getrlimit(Resource::NOFILE).unwrap();
+        let higher_limit = hard.as_usize() + 1;
+        // calculate a new soft to ensure soft != hard and hit that logic branch
+        let new_soft = Rlim::from_usize(hard.as_usize() - 1);
+        setrlimit(Resource::NOFILE, new_soft, hard).unwrap();
+        assert!(set_open_file_limit(higher_limit));
+    }
+
+    #[test]
+    /// set_open_file_limit should fail when hard == soft
+    fn utils_set_open_file_limit_with_fails_when_both_limits_are_equal() {
+        let (_, hard) = getrlimit(Resource::NOFILE).unwrap();
+        // calculate a new soft to ensure soft == hard and hit the failure logic branch
+        setrlimit(Resource::NOFILE, hard, hard).unwrap();
+        assert!(!set_open_file_limit(hard.as_usize())); // returns false
+    }
+
     #[test]
     /// base url returns 1
     fn get_current_depth_base_url_returns_1() {
@@ -348,6 +530,19 @@ mod tests {
         );
     }
 
+    #[test]
+    /// word that is a fully formed url, should return an error
+    fn format_url_word_that_is_a_url() {
+        let url = format_url(
+            "http://localhost",
+            "http://schmocalhost",
+            false,
+            &Vec::new(),
+            None,
+        );
+        assert!(url.is_err());
+    }
+
     #[test]
     /// status colorizer uses red for 500s
     fn status_colorizer_uses_red_for_500s() {

tests/test_banner.rs

@@ -23,7 +23,7 @@ fn banner_prints_proxy() -> Result<(), Box<dyn std::error::Error>> {
         .pipe_stdin(file)
         .unwrap()
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("─┬─")
                 .and(predicate::str::contains("Target Url"))
@@ -43,6 +43,46 @@ fn banner_prints_proxy() -> 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 + replay proxy
+fn banner_prints_replay_proxy() -> Result<(), Box<dyn std::error::Error>> {
+    let urls = vec![
+        String::from("http://localhost"),
+        String::from("http://schmocalhost"),
+    ];
+    let (tmp_dir, file) = setup_tmp_directory(&urls, "wordlist")?;
+
+    Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--stdin")
+        .arg("--wordlist")
+        .arg(file.as_os_str())
+        .arg("--replay-proxy")
+        .arg("http://127.0.0.1:8081")
+        .pipe_stdin(file)
+        .unwrap()
+        .assert()
+        .success()
+        .stderr(
+            predicate::str::contains("─┬─")
+                .and(predicate::str::contains("Target Url"))
+                .and(predicate::str::contains("http://localhost"))
+                .and(predicate::str::contains("http://schmocalhost"))
+                .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("Replay Proxy"))
+                .and(predicate::str::contains("http://127.0.0.1:8081"))
+                .and(predicate::str::contains("─┴─")),
+        );
+
+    teardown_tmp_directory(tmp_dir);
+    Ok(())
+}
+
 #[test]
 /// test allows non-existent wordlist to trigger the banner printing to stderr
 /// expect to see all mandatory prints + multiple headers
@@ -56,7 +96,7 @@ fn banner_prints_headers() -> Result<(), Box<dyn std::error::Error>> {
         .arg("-H")
         .arg("mostuff:mothings")
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("─┬─")
                 .and(predicate::str::contains("Target Url"))
@@ -77,17 +117,25 @@ fn banner_prints_headers() -> Result<(), Box<dyn std::error::Error>> {
 #[test]
 /// test allows non-existent wordlist to trigger the banner printing to stderr
 /// expect to see all mandatory prints + multiple size filters
-fn banner_prints_size_filters() -> Result<(), Box<dyn std::error::Error>> {
+fn banner_prints_filter_sizes() {
     Command::cargo_bin("feroxbuster")
         .unwrap()
         .arg("--url")
         .arg("http://localhost")
         .arg("-S")
         .arg("789456123")
-        .arg("--sizefilter")
+        .arg("--filter-size")
         .arg("44444444")
+        .arg("-N")
+        .arg("678")
+        .arg("--filter-lines")
+        .arg("679")
+        .arg("-W")
+        .arg("93")
+        .arg("--filter-words")
+        .arg("94")
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("─┬─")
                 .and(predicate::str::contains("Target Url"))
@@ -98,11 +146,16 @@ fn banner_prints_size_filters() -> Result<(), Box<dyn std::error::Error>> {
                 .and(predicate::str::contains("Timeout (secs)"))
                 .and(predicate::str::contains("User-Agent"))
                 .and(predicate::str::contains("Size Filter"))
+                .and(predicate::str::contains("Word Count Filter"))
+                .and(predicate::str::contains("Line Count Filter"))
                 .and(predicate::str::contains("789456123"))
                 .and(predicate::str::contains("44444444"))
+                .and(predicate::str::contains("93"))
+                .and(predicate::str::contains("94"))
+                .and(predicate::str::contains("678"))
+                .and(predicate::str::contains("679"))
                 .and(predicate::str::contains("─┴─")),
         );
-    Ok(())
 }
 
 #[test]
@@ -118,7 +171,7 @@ fn banner_prints_queries() -> Result<(), Box<dyn std::error::Error>> {
         .arg("--query")
         .arg("stuff=things")
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("─┬─")
                 .and(predicate::str::contains("Target Url"))
@@ -147,7 +200,7 @@ fn banner_prints_status_codes() -> Result<(), Box<dyn std::error::Error>> {
         .arg("-s")
         .arg("201,301,401")
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("─┬─")
                 .and(predicate::str::contains("Target Url"))
@@ -163,6 +216,37 @@ fn banner_prints_status_codes() -> 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 + replay codes
+fn banner_prints_replay_codes() -> Result<(), Box<dyn std::error::Error>> {
+    Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg("http://localhost")
+        .arg("--replay-codes")
+        .arg("200,302")
+        .arg("--replay-proxy")
+        .arg("http://localhost:8081")
+        .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("Timeout (secs)"))
+                .and(predicate::str::contains("User-Agent"))
+                .and(predicate::str::contains("Replay Proxy"))
+                .and(predicate::str::contains("http://localhost:8081"))
+                .and(predicate::str::contains("Replay Proxy Codes"))
+                .and(predicate::str::contains("[200, 302]"))
+                .and(predicate::str::contains("─┴─")),
+        );
+    Ok(())
+}
+
 #[test]
 /// test allows non-existent wordlist to trigger the banner printing to stderr
 /// expect to see all mandatory prints + output file
@@ -174,7 +258,7 @@ fn banner_prints_output_file() -> Result<(), Box<dyn std::error::Error>> {
         .arg("--output")
         .arg("/super/cool/path")
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("─┬─")
                 .and(predicate::str::contains("Target Url"))
@@ -201,7 +285,7 @@ fn banner_prints_insecure() -> Result<(), Box<dyn std::error::Error>> {
         .arg("http://localhost")
         .arg("-k")
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("─┬─")
                 .and(predicate::str::contains("Target Url"))
@@ -228,7 +312,7 @@ fn banner_prints_redirects() -> Result<(), Box<dyn std::error::Error>> {
         .arg("http://localhost")
         .arg("-r")
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("─┬─")
                 .and(predicate::str::contains("Target Url"))
@@ -258,7 +342,7 @@ fn banner_prints_extensions() -> Result<(), Box<dyn std::error::Error>> {
         .arg("--extensions")
         .arg("pdf")
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("─┬─")
                 .and(predicate::str::contains("Target Url"))
@@ -277,15 +361,15 @@ fn banner_prints_extensions() -> Result<(), Box<dyn std::error::Error>> {
 
 #[test]
 /// test allows non-existent wordlist to trigger the banner printing to stderr
-/// expect to see all mandatory prints + dontfilter
-fn banner_prints_dontfilter() -> Result<(), Box<dyn std::error::Error>> {
+/// expect to see all mandatory prints + dont_filter
+fn banner_prints_dont_filter() -> Result<(), Box<dyn std::error::Error>> {
     Command::cargo_bin("feroxbuster")
         .unwrap()
         .arg("--url")
         .arg("http://localhost")
-        .arg("--dontfilter")
+        .arg("--dont-filter")
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("─┬─")
                 .and(predicate::str::contains("Target Url"))
@@ -312,7 +396,7 @@ fn banner_prints_verbosity_one() -> Result<(), Box<dyn std::error::Error>> {
         .arg("http://localhost")
         .arg("-v")
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("─┬─")
                 .and(predicate::str::contains("Target Url"))
@@ -339,7 +423,7 @@ fn banner_prints_verbosity_two() -> Result<(), Box<dyn std::error::Error>> {
         .arg("http://localhost")
         .arg("-vv")
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("─┬─")
                 .and(predicate::str::contains("Target Url"))
@@ -366,7 +450,7 @@ fn banner_prints_verbosity_three() -> Result<(), Box<dyn std::error::Error>> {
         .arg("http://localhost")
         .arg("-vvv")
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("─┬─")
                 .and(predicate::str::contains("Target Url"))
@@ -393,7 +477,7 @@ fn banner_prints_verbosity_four() -> Result<(), Box<dyn std::error::Error>> {
         .arg("http://localhost")
         .arg("-vvvv")
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("─┬─")
                 .and(predicate::str::contains("Target Url"))
@@ -420,7 +504,7 @@ fn banner_prints_add_slash() -> Result<(), Box<dyn std::error::Error>> {
         .arg("http://localhost")
         .arg("-f")
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("─┬─")
                 .and(predicate::str::contains("Target Url"))
@@ -448,7 +532,7 @@ fn banner_prints_infinite_depth() -> Result<(), Box<dyn std::error::Error>> {
         .arg("--depth")
         .arg("0")
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("─┬─")
                 .and(predicate::str::contains("Target Url"))
@@ -476,7 +560,7 @@ fn banner_prints_recursion_depth() -> Result<(), Box<dyn std::error::Error>> {
         .arg("--depth")
         .arg("343214")
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("─┬─")
                 .and(predicate::str::contains("Target Url"))
@@ -503,7 +587,7 @@ fn banner_prints_no_recursion() -> Result<(), Box<dyn std::error::Error>> {
         .arg("http://localhost")
         .arg("-n")
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("─┬─")
                 .and(predicate::str::contains("Target Url"))
@@ -522,7 +606,7 @@ fn banner_prints_no_recursion() -> Result<(), Box<dyn std::error::Error>> {
 
 #[test]
 /// test allows non-existent wordlist to trigger the banner printing to stderr
-/// expect to see only the error of could not connect
+/// expect to see nothing
 fn banner_doesnt_print() -> Result<(), Box<dyn std::error::Error>> {
     Command::cargo_bin("feroxbuster")
         .unwrap()
@@ -530,9 +614,170 @@ fn banner_doesnt_print() -> Result<(), Box<dyn std::error::Error>> {
         .arg("http://localhost")
         .arg("-q")
         .assert()
-        .failure()
-        .stderr(predicate::str::contains(
-            "ERROR heuristics::connectivity_test Could not connect to any target provided",
-        ));
+        .success()
+        .stderr(predicate::str::is_empty());
     Ok(())
 }
+
+#[test]
+/// test allows non-existent wordlist to trigger the banner printing to stderr
+/// expect to see all mandatory prints + extract-links
+fn banner_prints_extract_links() -> Result<(), Box<dyn std::error::Error>> {
+    Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg("http://localhost")
+        .arg("-e")
+        .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("Extract Links"))
+                .and(predicate::str::contains("true"))
+                .and(predicate::str::contains("─┴─")),
+        );
+    Ok(())
+}
+
+#[test]
+/// test allows non-existent wordlist to trigger the banner printing to stderr
+/// expect to see all mandatory prints + scan-limit
+fn banner_prints_scan_limit() -> Result<(), Box<dyn std::error::Error>> {
+    Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg("http://localhost")
+        .arg("-L")
+        .arg("4")
+        .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("Concurrent Scan Limit"))
+                .and(predicate::str::contains("│ 4"))
+                .and(predicate::str::contains("─┴─")),
+        );
+    Ok(())
+}
+
+#[test]
+/// test allows non-existent wordlist to trigger the banner printing to stderr
+/// expect to see all mandatory prints + filter-status
+fn banner_prints_filter_status() -> Result<(), Box<dyn std::error::Error>> {
+    Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg("http://localhost")
+        .arg("-C")
+        .arg("200")
+        .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("Status Code Filters"))
+                .and(predicate::str::contains("│ [200]"))
+                .and(predicate::str::contains("─┴─")),
+        );
+    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")
+        .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("─┴─")),
+        );
+}

tests/test_config.rs

@@ -18,7 +18,7 @@ fn read_in_config_file_for_settings() -> Result<(), Box<dyn std::error::Error>>
         .arg(file.as_os_str())
         .arg("-vvvv")
         .assert()
-        .failure()
+        .success()
         .stderr(predicate::str::contains("│ 37"));
 
     teardown_tmp_directory(tmp_dir);

tests/test_extractor.rs

@@ -0,0 +1,229 @@
+mod utils;
+use assert_cmd::prelude::*;
+use httpmock::Method::GET;
+use httpmock::{Mock, MockServer};
+use predicates::prelude::*;
+use std::process::Command;
+use utils::{setup_tmp_directory, teardown_tmp_directory};
+
+#[test]
+/// send a request to a page that contains a relative link, --extract-links should find the link
+/// and make a request to the new link
+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_two = Mock::new()
+        .expect_method(GET)
+        .expect_path("/homepage/assets/img/icons/handshake.svg")
+        .return_status(200)
+        .create_on(&srv);
+
+    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")
+            .and(predicate::str::contains("200"))
+            .and(predicate::str::contains(
+                "/homepage/assets/img/icons/handshake.svg",
+            )),
+    );
+
+    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock_two.times_called(), 1);
+    teardown_tmp_directory(tmp_dir);
+    Ok(())
+}
+
+#[test]
+/// send a request to a page that contains an absolute link to another domain, scanner should not
+/// follow
+fn extractor_finds_absolute_url_to_different_domain() -> 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("\"http://localhost/homepage/assets/img/icons/handshake.svg\"")
+        .create_on(&srv);
+
+    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")
+            .and(predicate::str::contains("200"))
+            .and(predicate::str::contains(
+                "/homepage/assets/img/icons/handshake.svg",
+            ))
+            .not(),
+    );
+
+    assert_eq!(mock.times_called(), 1);
+    teardown_tmp_directory(tmp_dir);
+    Ok(())
+}
+
+#[test]
+/// send a request to a page that contains a relative link, should follow
+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_two = Mock::new()
+        .expect_method(GET)
+        .expect_path("/homepage/assets/img/icons/handshake.svg")
+        .return_status(200)
+        .create_on(&srv);
+
+    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")
+            .and(predicate::str::contains("200"))
+            .and(predicate::str::contains(
+                "/homepage/assets/img/icons/handshake.svg",
+            )),
+    );
+
+    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock_two.times_called(), 1);
+    teardown_tmp_directory(tmp_dir);
+    Ok(())
+}
+
+#[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() {
+    let srv = MockServer::start();
+    let (tmp_dir, file) =
+        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_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_three = Mock::new()
+        .expect_method(GET)
+        .expect_path("/homepage/assets/img/icons/handshake.svg")
+        .return_status(200)
+        .create_on(&srv);
+
+    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")
+            .and(predicate::str::contains("200"))
+            .and(predicate::str::contains(
+                "/homepage/assets/img/icons/handshake.svg",
+            )),
+    );
+
+    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock_two.times_called(), 1);
+    assert!(mock_three.times_called() <= 2); // todo: sometimes this is 2 instead of 1
+                                             // the expectation is one, suggesting a race condition... investigate and fix
+    teardown_tmp_directory(tmp_dir);
+}
+
+#[test]
+/// send a request to a page that contains an absolute link that leads to a page with a filter_size
+/// that should filter it out, expect not to see the second response reported
+fn extractor_finds_filtered_content() -> Result<(), Box<dyn std::error::Error>> {
+    let srv = MockServer::start();
+    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_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 cmd = Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg(srv.url("/"))
+        .arg("--wordlist")
+        .arg(file.as_os_str())
+        .arg("--extract-links")
+        .arg("--filter-size")
+        .arg("18")
+        .unwrap();
+
+    cmd.assert().success().stdout(
+        predicate::str::contains("/LICENSE")
+            .and(predicate::str::contains("200"))
+            .and(predicate::str::contains(
+                "/homepage/assets/img/icons/handshake.svg",
+            ))
+            .not(),
+    );
+
+    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock_two.times_called(), 1);
+    teardown_tmp_directory(tmp_dir);
+    Ok(())
+}

tests/test_filters.rs

@@ -0,0 +1,204 @@
+mod utils;
+use assert_cmd::prelude::*;
+use httpmock::Method::GET;
+use httpmock::{Mock, MockServer};
+use predicates::prelude::*;
+use std::process::Command;
+use utils::{setup_tmp_directory, teardown_tmp_directory};
+
+#[test]
+/// create a FeroxResponse that should elicit a true from
+/// StatusCodeFilter::should_filter_response
+fn filters_status_code_should_filter_response() {
+    let srv = MockServer::start();
+    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_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 cmd = Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg(srv.url("/"))
+        .arg("--wordlist")
+        .arg(file.as_os_str())
+        .arg("-vvvv")
+        .arg("--filter-status")
+        .arg("302")
+        .unwrap();
+
+    cmd.assert().success().stdout(
+        predicate::str::contains("/LICENSE")
+            .not()
+            .and(predicate::str::contains("302"))
+            .not()
+            .and(predicate::str::contains("14c"))
+            .not()
+            .and(predicate::str::contains("/file.js"))
+            .and(predicate::str::contains("200"))
+            .and(predicate::str::contains("34c")),
+    );
+
+    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock_two.times_called(), 1);
+    teardown_tmp_directory(tmp_dir);
+}
+
+#[test]
+/// create a FeroxResponse that should elicit a true from
+/// LinesFilter::should_filter_response
+fn filters_lines_should_filter_response() {
+    let srv = MockServer::start();
+    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_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 cmd = Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg(srv.url("/"))
+        .arg("--wordlist")
+        .arg(file.as_os_str())
+        .arg("--filter-lines")
+        .arg("2")
+        .unwrap();
+
+    cmd.assert().success().stdout(
+        predicate::str::contains("/LICENSE")
+            .and(predicate::str::contains("302"))
+            .and(predicate::str::contains("14"))
+            .and(predicate::str::contains("/file.js"))
+            .not()
+            .and(predicate::str::contains("200"))
+            .not()
+            .and(predicate::str::contains("2l"))
+            .not(),
+    );
+
+    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock_two.times_called(), 1);
+    teardown_tmp_directory(tmp_dir);
+}
+
+#[test]
+/// create a FeroxResponse that should elicit a true from
+/// WordsFilter::should_filter_response
+fn filters_words_should_filter_response() {
+    let srv = MockServer::start();
+    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_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 cmd = Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg(srv.url("/"))
+        .arg("--wordlist")
+        .arg(file.as_os_str())
+        .arg("--filter-words")
+        .arg("13")
+        .unwrap();
+
+    cmd.assert().success().stdout(
+        predicate::str::contains("/LICENSE")
+            .and(predicate::str::contains("302"))
+            .and(predicate::str::contains("14"))
+            .and(predicate::str::contains("/file.js"))
+            .not()
+            .and(predicate::str::contains("200"))
+            .not()
+            .and(predicate::str::contains("13w"))
+            .not(),
+    );
+
+    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock_two.times_called(), 1);
+    teardown_tmp_directory(tmp_dir);
+}
+
+#[test]
+/// create a FeroxResponse that should elicit a true from
+/// SizeFilter::should_filter_response
+fn filters_size_should_filter_response() {
+    let srv = MockServer::start();
+    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_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 cmd = Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg(srv.url("/"))
+        .arg("--wordlist")
+        .arg(file.as_os_str())
+        .arg("--filter-size")
+        .arg("56")
+        .unwrap();
+
+    cmd.assert().success().stdout(
+        predicate::str::contains("/LICENSE")
+            .and(predicate::str::contains("302"))
+            .and(predicate::str::contains("14"))
+            .and(predicate::str::contains("/file.js"))
+            .not()
+            .and(predicate::str::contains("200"))
+            .not()
+            .and(predicate::str::contains("56c"))
+            .not(),
+    );
+
+    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock_two.times_called(), 1);
+    teardown_tmp_directory(tmp_dir);
+}

tests/test_heuristics.rs

@@ -19,11 +19,9 @@ fn test_single_target_cannot_connect() -> Result<(), Box<dyn std::error::Error>>
         .arg("--wordlist")
         .arg(file.as_os_str())
         .assert()
-        .failure()
-        .stderr(
-            predicate::str::contains("Could not connect to any target provided")
-                .and(predicate::str::contains("ERROR"))
-                .and(predicate::str::contains("heuristics::connectivity_test")),
+        .success()
+        .stdout(
+            predicate::str::contains("Could not connect to http://fjdksafjkdsajfkdsajkfdsajkfsdjkdsfdsafdsafdsajkr3l2ajfdskafdsjk, skipping...", )
         );
 
     teardown_tmp_directory(tmp_dir);
@@ -47,11 +45,9 @@ fn test_two_targets_cannot_connect() -> Result<(), Box<dyn std::error::Error>> {
         .pipe_stdin(file)
         .unwrap()
         .assert()
-        .failure()
-        .stderr(
-            predicate::str::contains("Could not connect to any target provided")
-                .and(predicate::str::contains("ERROR"))
-                .and(predicate::str::contains("heuristics::connectivity_test")),
+        .success()
+        .stdout(
+            predicate::str::contains("Could not connect to http://fjdksafjkdsajfkdsajkfdsajkfsdjkdsfdsafdsafdsajkr3l2ajfdskafdsjk, skipping...", )
         );
 
     teardown_tmp_directory(tmp_dir);
@@ -115,7 +111,7 @@ fn test_static_wildcard_request_found() -> Result<(), Box<dyn std::error::Error>
         .arg(srv.url("/"))
         .arg("--wordlist")
         .arg(file.as_os_str())
-        .arg("--addslash")
+        .arg("--add-slash")
         .unwrap();
 
     teardown_tmp_directory(tmp_dir);
@@ -133,9 +129,9 @@ fn test_static_wildcard_request_found() -> Result<(), Box<dyn std::error::Error>
 
 #[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()
@@ -158,7 +154,7 @@ fn test_dynamic_wildcard_request_found() -> Result<(), Box<dyn std::error::Error
         .arg(srv.url("/"))
         .arg("--wordlist")
         .arg(file.as_os_str())
-        .arg("--addslash")
+        .arg("--add-slash")
         .arg("--output")
         .arg(outfile.as_os_str())
         .unwrap();
@@ -170,36 +166,24 @@ 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(())
 }
 
 #[test]
-/// uses dontfilter, so the normal wildcard test should never happen
-fn heuristics_static_wildcard_request_with_dontfilter() -> Result<(), Box<dyn std::error::Error>> {
+/// uses dont_filter, so the normal wildcard test should never happen
+fn heuristics_static_wildcard_request_with_dont_filter() -> Result<(), Box<dyn std::error::Error>> {
     let srv = MockServer::start();
     let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist")?;
 
@@ -216,7 +200,7 @@ fn heuristics_static_wildcard_request_with_dontfilter() -> Result<(), Box<dyn st
         .arg(srv.url("/"))
         .arg("--wordlist")
         .arg(file.as_os_str())
-        .arg("--dontfilter")
+        .arg("--dont-filter")
         .unwrap();
 
     teardown_tmp_directory(tmp_dir);
@@ -227,9 +211,9 @@ fn heuristics_static_wildcard_request_with_dontfilter() -> Result<(), Box<dyn st
 
 #[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)
@@ -251,7 +235,7 @@ fn heuristics_wildcard_test_with_two_static_wildcards() -> Result<(), Box<dyn st
         .arg(srv.url("/"))
         .arg("--wordlist")
         .arg(file.as_os_str())
-        .arg("--addslash")
+        .arg("--add-slash")
         .unwrap();
 
     teardown_tmp_directory(tmp_dir);
@@ -269,7 +253,6 @@ 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(())
 }
 
 #[test]
@@ -299,7 +282,7 @@ fn heuristics_wildcard_test_with_two_static_wildcards_with_quiet_enabled(
         .arg(srv.url("/"))
         .arg("--wordlist")
         .arg(file.as_os_str())
-        .arg("--addslash")
+        .arg("--add-slash")
         .arg("-q")
         .unwrap();
 
@@ -314,10 +297,9 @@ fn heuristics_wildcard_test_with_two_static_wildcards_with_quiet_enabled(
 
 #[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()
@@ -340,7 +322,7 @@ fn heuristics_wildcard_test_with_two_static_wildcards_and_output_to_file(
         .arg(srv.url("/"))
         .arg("--wordlist")
         .arg(file.as_os_str())
-        .arg("--addslash")
+        .arg("--add-slash")
         .arg("--output")
         .arg(outfile.as_os_str())
         .unwrap();
@@ -354,10 +336,6 @@ 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")
@@ -372,8 +350,6 @@ 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(())
 }
 
 #[test]
@@ -406,7 +382,7 @@ fn heuristics_wildcard_test_with_redirect_as_response_code(
         .arg(srv.url("/"))
         .arg("--wordlist")
         .arg(file.as_os_str())
-        .arg("--addslash")
+        .arg("--add-slash")
         .arg("--output")
         .arg(outfile.as_os_str())
         .unwrap();

tests/test_main.rs

@@ -25,10 +25,8 @@ fn main_use_root_owned_file_as_wordlist() -> Result<(), Box<dyn std::error::Erro
         .arg("/etc/shadow")
         .arg("-vvvv")
         .assert()
-        .success()
-        .stderr(predicate::str::contains(
-            "ERROR main::get_unique_words_from_wordlist Permission denied (os error 13)",
-        ));
+        .failure()
+        .stdout(predicate::str::contains("Permission denied (os error 13)"));
 
     // connectivity test hits it once
     assert_eq!(mock.times_called(), 1);
@@ -57,9 +55,7 @@ fn main_use_empty_wordlist() -> Result<(), Box<dyn std::error::Error>> {
         .arg("-vvvv")
         .assert()
         .failure()
-        .stderr(predicate::str::contains(
-            "ERROR main::scan Did not find any words in",
-        ));
+        .stdout(predicate::str::contains("Did not find any words in"));
 
     assert_eq!(mock.times_called(), 1);
 
@@ -83,11 +79,9 @@ fn main_use_empty_stdin_targets() -> Result<(), Box<dyn std::error::Error>> {
         .pipe_stdin(file)
         .unwrap()
         .assert()
-        .failure()
+        .success()
         .stderr(
             predicate::str::contains("Could not connect to any target provided")
-                .and(predicate::str::contains("ERROR"))
-                .and(predicate::str::contains("heuristics::connectivity_test"))
                 .and(predicate::str::contains("Target Url"))
                 .not(), // no target url found
         );

tests/test_scanner.rs

@@ -327,7 +327,8 @@ fn scanner_single_request_quiet_scan() -> Result<(), Box<dyn std::error::Error>>
 }
 
 #[test]
-/// send single valid request, get back a 301 without a Location header, expect false
+/// send single valid request, get back a 301 without a Location header
+/// expect response_is_directory to return false when called
 fn scanner_single_request_returns_301_without_location_header(
 ) -> Result<(), Box<dyn std::error::Error>> {
     let srv = MockServer::start();
@@ -336,6 +337,7 @@ fn scanner_single_request_returns_301_without_location_header(
     let mock = Mock::new()
         .expect_method(GET)
         .expect_path("/LICENSE")
+        .return_body("this is a test")
         .return_status(301)
         .create_on(&srv);
 
@@ -345,17 +347,16 @@ fn scanner_single_request_returns_301_without_location_header(
         .arg(srv.url("/"))
         .arg("--wordlist")
         .arg(file.as_os_str())
-        .arg("-T")
+        .arg("--timeout")
         .arg("5")
-        .arg("-a")
+        .arg("--user-agent")
         .arg("some-user-agent-string")
         .unwrap();
 
     cmd.assert().success().stdout(
         predicate::str::contains(srv.url("/LICENSE"))
             .and(predicate::str::contains("301"))
-            .and(predicate::str::contains("14"))
-            .not(),
+            .and(predicate::str::contains("14")),
     );
 
     assert_eq!(mock.times_called(), 1);
@@ -401,7 +402,7 @@ fn scanner_single_request_scan_with_filtered_result() -> Result<(), Box<dyn std:
             .and(predicate::str::contains("20"))
             .and(predicate::str::contains("ignored"))
             .not()
-            .and(predicate::str::contains("14"))
+            .and(predicate::str::contains(" 14 "))
             .not(),
     );
 
@@ -410,3 +411,179 @@ fn scanner_single_request_scan_with_filtered_result() -> Result<(), Box<dyn std:
     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 = Mock::new()
+        .expect_method(GET)
+        .expect_path("/LICENSE")
+        .return_status(200)
+        .return_body("this is a test")
+        .create_on(&srv);
+
+    let mock_two = Mock::new()
+        .expect_method(GET)
+        .expect_path("/LICENSE")
+        .return_status(200)
+        .return_body("this is a test")
+        .create_on(&proxy);
+
+    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("14")),
+        )
+        .stderr(predicate::str::contains("Replay Proxy Codes"));
+
+    assert_eq!(mock.times_called(), 1);
+    assert_eq!(mock_two.times_called(), 1);
+    teardown_tmp_directory(tmp_dir);
+    Ok(())
+}
+
+#[test]
+/// 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 (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 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.times_called(), 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 = Mock::new()
+        .expect_method(GET)
+        .expect_path("/LICENSE")
+        .return_status(200)
+        .return_body("this is a test")
+        .create_on(&srv);
+
+    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.times_called(), 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 = Mock::new()
+        .expect_method(GET)
+        .expect_path("/LICENSE")
+        .return_status(200)
+        .return_body("this is a not a test")
+        .create_on(&srv);
+
+    let filtered_mock = Mock::new()
+        .expect_method(GET)
+        .expect_path("/ignored")
+        .return_status(200)
+        .return_body("this is a test\nThat rug really tied the room together")
+        .create_on(&srv);
+
+    let cmd = Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg(srv.url("/"))
+        .arg("--wordlist")
+        .arg(file.as_os_str())
+        .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("20"))
+            .and(predicate::str::contains("ignored"))
+            .not()
+            .and(predicate::str::contains(" 14 "))
+            .not(),
+    );
+
+    assert_eq!(mock.times_called(), 1);
+    assert_eq!(filtered_mock.times_called(), 1);
+    teardown_tmp_directory(tmp_dir);
+}