removed errant log statements

Add statistics tracking

.github/stale.yml

@@ -1,5 +1,5 @@
 # Number of days of inactivity before an issue becomes stale
-daysUntilStale: 21
+daysUntilStale: 14
 # Number of days of inactivity before a stale issue is closed
 daysUntilClose: 7
 # Issues with these labels will never be considered stale

.rustfmt.toml

@@ -0,0 +1 @@
+reorder_modules = false

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "feroxbuster"
-version = "1.10.0"
+version = "1.11.1"
 authors = ["Ben 'epi' Risher <epibar052@gmail.com>"]
 license = "MIT"
 edition = "2018"
@@ -30,17 +30,18 @@ reqwest = { version = "0.10", features = ["socks"] }
 clap = "2.33"
 lazy_static = "1.4"
 toml = "0.5"
-serde = { version = "1.0", features = ["derive"] }
+serde = { version = "1.0", features = ["derive", "rc"] }
 serde_json = "1.0"
 uuid = { version = "0.8", features = ["v4"] }
 indicatif = "0.15"
-console = "0.13"
+console = "0.14"
 openssl = { version = "0.10", features = ["vendored"] }
 dirs = "3.0"
 regex = "1"
-crossterm = "0.18"
+crossterm = "0.19"
 rlimit = "0.5"
 ctrlc = "3.1"
+fuzzyhash = "0.2"
 
 [dev-dependencies]
 tempfile = "3.1"

README.md

@@ -22,7 +22,7 @@
   <a href="https://crates.io/crates/feroxbuster">
     <img src="https://img.shields.io/crates/v/feroxbuster?color=blue&label=version&logo=rust">
   </a>
- 
+
   <a href="https://crates.io/crates/feroxbuster">
     <img src="https://img.shields.io/crates/d/feroxbuster?label=downloads&logo=rust&color=inactive">
   </a>
@@ -45,20 +45,26 @@
 
 ## 😕 What the heck is a ferox anyway?
 
-Ferox is short for Ferric Oxide. Ferric Oxide, simply put, is rust.  The name rustbuster was taken, so I decided on a variation.  🤷	
+Ferox is short for Ferric Oxide. Ferric Oxide, simply put, is rust. The name rustbuster was taken, so I decided on a
+variation. 🤷
 
-## 🤔 What's it do tho? 
+## 🤔 What's it do tho?
 
-`feroxbuster` is a tool designed to perform [Forced Browsing](https://owasp.org/www-community/attacks/Forced_browsing).  
+`feroxbuster` is a tool designed to perform [Forced Browsing](https://owasp.org/www-community/attacks/Forced_browsing).
 
-Forced browsing is an attack where the aim is to enumerate and access resources that are not referenced by the web application, but are still accessible by an attacker.
+Forced browsing is an attack where the aim is to enumerate and access resources that are not referenced by the web
+application, but are still accessible by an attacker.
 
-`feroxbuster` uses brute force combined with a wordlist to search for unlinked content in target directories. These resources may store sensitive information about web applications and operational systems, such as source code, credentials, internal network addressing, etc...
+`feroxbuster` uses brute force combined with a wordlist to search for unlinked content in target directories. These
+resources may store sensitive information about web applications and operational systems, such as source code,
+credentials, internal network addressing, etc...
 
-This attack is also known as Predictable Resource Location, File Enumeration, Directory Enumeration, and Resource Enumeration.
+This attack is also known as Predictable Resource Location, File Enumeration, Directory Enumeration, and Resource
+Enumeration.
 
 📖 Table of Contents
 -----------------
+
 - [Installation](#-installation)
     - [Download a Release](#download-a-release)
     - [Snap Install](#snap-install)
@@ -72,13 +78,17 @@ This attack is also known as Predictable Resource Location, File Enumeration, Di
     - [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)
+- [Scan's Display Explained](#-scans-display-explained)
+    - [Discovered Resource](#discovered-resource)
+    - [Overall Scan Progress Bar](#overall-scan-progress-bar)
+    - [Directory Scan Progress Bar](#directory-scan-progress-bar)
 - [Example Usage](#-example-usage)
     - [Multiple Values](#multiple-values)
     - [Include Headers](#include-headers)
     - [IPv6, Non-recursive scan with INFO logging enabled](#ipv6-non-recursive-scan-with-info-level-logging-enabled)
     - [Read urls from STDIN; pipe only resulting urls out to another tool](#read-urls-from-stdin-pipe-only-resulting-urls-out-to-another-tool)
     - [Proxy traffic through Burp](#proxy-traffic-through-burp)
-    - [Proxy traffic through a SOCKS proxy](#proxy-traffic-through-a-socks-proxy)
+    - [Proxy traffic through a SOCKS proxy (including DNS lookups)](#proxy-traffic-through-a-socks-proxy-including-dns-lookups)
     - [Pass auth token via query parameter](#pass-auth-token-via-query-parameter)
     - [Extract Links from Response Body (new in `v1.1.0`)](#extract-links-from-response-body-new-in-v110)
     - [Limit Total Number of Concurrent Scans (new in `v1.2.0`)](#limit-total-number-of-concurrent-scans-new-in-v120)
@@ -89,18 +99,25 @@ This attack is also known as Predictable Resource Location, File Enumeration, Di
     - [Filter Response Using a Regular Expression (new in `v1.8.0`)](#filter-response-using-a-regular-expression-new-in-v180)
     - [Stop and Resume Scans (save scan's state to disk) (new in `v1.9.0`)](#stop-and-resume-scans---resume-from-file-new-in-v190)
     - [Enforce a Time Limit on Your Scan (new in `v1.10.0`)](#enforce-a-time-limit-on-your-scan-new-in-v1100)
+    - [Extract Links from robots.txt (New in `v1.10.2`)](#extract-links-from-robotstxt-new-in-v1102)
+    - [Filter Response by Similarity to A Given Page (fuzzy filter) (new in `v1.11.0`)](#filter-response-by-similarity-to-a-given-page-fuzzy-filter-new-in-v1110)
 - [Comparison w/ Similar Tools](#-comparison-w-similar-tools)
 - [Common Problems/Issues (FAQ)](#-common-problemsissues-faq)
     - [No file descriptors available](#no-file-descriptors-available)
     - [Progress bars print one line at a time](#progress-bars-print-one-line-at-a-time)
+    - [What do each of the numbers beside the URL mean?](#what-do-each-of-the-numbers-beside-the-url-mean)
+    - [Connection closed before message completed](#connection-closed-before-message-completed)
+    - [SSL Error routines:tls_process_server_certificate:certificate verify failed](#ssl-error-routinestls_process_server_certificatecertificate-verify-failed)
 
 ## 💿 Installation
 
 ### Download a Release
 
-Releases for multiple architectures can be found in the [Releases](https://github.com/epi052/feroxbuster/releases) section.  The latest release for each of the following systems can be downloaded and executed as shown below.
+Releases for multiple architectures can be found in the [Releases](https://github.com/epi052/feroxbuster/releases)
+section. The latest release for each of the following systems can be downloaded and executed as shown below.
 
 #### Linux (32 and 64-bit) & MacOS
+
 ```
 curl -sL https://raw.githubusercontent.com/epi052/feroxbuster/master/install-nix.sh | bash
 ```
@@ -129,7 +146,7 @@ Install using `snap`
 sudo snap install feroxbuster
 ```
 
-The only gotcha here is that the snap package can only read wordlists from a few specific locations. There are a few 
+The only gotcha here is that the snap package can only read wordlists from a few specific locations. There are a few
 possible solutions, of which two are shown below.
 
 If the wordlist is on the same partition as your home directory, it can be hard-linked into `~/snap/feroxbuster/common`
@@ -139,7 +156,7 @@ ln /path/to/the/wordlist ~/snap/feroxbuster/common
 ./feroxbuster -u http://localhost -w ~/snap/feroxbuster/common/wordlist
 ``` 
 
-If the wordlist is on a separate partition, hard-linking won't work.  You'll need to copy it into the snap directory.
+If the wordlist is on a separate partition, hard-linking won't work. You'll need to copy it into the snap directory.
 
 ```
 cp /path/to/the/wordlist ~/snap/feroxbuster/common
@@ -174,7 +191,8 @@ cargo install feroxbuster
 
 ### apt Install
 
-Download `feroxbuster_amd64.deb` from the [Releases](https://github.com/epi052/feroxbuster/releases) section.  After that, use your favorite package manager to install the `.deb`.
+Download `feroxbuster_amd64.deb` from the [Releases](https://github.com/epi052/feroxbuster/releases) section. After
+that, use your favorite package manager to install the `.deb`.
 
 ```
 wget -sLO https://github.com/epi052/feroxbuster/releases/latest/download/feroxbuster_amd64.deb.zip
@@ -223,7 +241,9 @@ cat targets.txt | sudo docker run --net=host --init -i feroxbuster --stdin -x js
 
 #### Mount a volume to pass in `ferox-config.toml`
 
-You've got some options available if you want to pass in a config file.  [`ferox-buster.toml`](#ferox-configtoml) can live in multiple locations and still be valid, so it's up to you how you'd like to pass it in.  Below are a few valid examples:
+You've got some options available if you want to pass in a config file.  [`ferox-buster.toml`](#ferox-configtoml) can
+live in multiple locations and still be valid, so it's up to you how you'd like to pass it in. Below are a few valid
+examples:
 
 ```
 sudo docker run --init -v $(pwd)/ferox-config.toml:/etc/feroxbuster/ferox-config.toml -it feroxbuster -u http://example.com
@@ -246,7 +266,9 @@ alias feroxbuster="sudo docker run --init -v ~/.config/feroxbuster:/root/.config
 ```
 
 ## ⚙️ Configuration
+
 ### Default Values
+
 Configuration begins with with the following built-in default values baked into the binary:
 
 - timeout: `7` seconds
@@ -264,11 +286,20 @@ Configuration begins with with the following built-in default values baked into
 
 ### Threads and Connection Limits At A High-Level
 
-This section explains how the `-t` and `-L` options work together to determine the overall aggressiveness of a scan. The combination of the two values set by these options determines how hard your target will get hit and to some extent also determines how many resources will be consumed on your local machine.
+This section explains how the `-t` and `-L` options work together to determine the overall aggressiveness of a scan. The
+combination of the two values set by these options determines how hard your target will get hit and to some extent also
+determines how many resources will be consumed on your local machine.
 
 #### A Note on Green Threads
 
-`feroxbuster` uses so-called [green threads](https://en.wikipedia.org/wiki/Green_threads) as opposed to traditional kernel/OS threads. This means (at a high-level) that the threads are implemented entirely in userspace, within a single running process. As a result, a scan with 30 green threads will appear to the OS to be a single process with no additional light-weight processes associated with it as far as the kernel is concerned. As such, there will not be any impact to process (`nproc`) limits when specifying larger values for `-t`. However, these threads will still consume file descriptors, so you will need to ensure that you have a suitable `nlimit` set when scaling up the amount of threads. More detailed documentation on setting appropriate `nlimit` values can be found in the [No File Descriptors Available](#no-file-descriptors-available) section of the FAQ
+`feroxbuster` uses so-called [green threads](https://en.wikipedia.org/wiki/Green_threads) as opposed to traditional
+kernel/OS threads. This means (at a high-level) that the threads are implemented entirely in userspace, within a single
+running process. As a result, a scan with 30 green threads will appear to the OS to be a single process with no
+additional light-weight processes associated with it as far as the kernel is concerned. As such, there will not be any
+impact to process (`nproc`) limits when specifying larger values for `-t`. However, these threads will still consume
+file descriptors, so you will need to ensure that you have a suitable `nlimit` set when scaling up the amount of
+threads. More detailed documentation on setting appropriate `nlimit` values can be found in
+the [No File Descriptors Available](#no-file-descriptors-available) section of the FAQ
 
 #### Threads and Connection Limits: The Implementation
 
@@ -277,13 +308,18 @@ This section explains how the `-t` and `-L` options work together to determine t
 
 #### Threads and Connection Limits: Examples
 
-To truly have only 30 active requests to a site at any given time, `-t 30 -L 1` is necessary. Using `-t 30 -L 2` will result in a maximum of 60 total requests being processed at any given time for that site. And so on. For a conversation on this, please see [Issue #126](https://github.com/epi052/feroxbuster/issues/126) which may provide more (or less) clarity :wink:
+To truly have only 30 active requests to a site at any given time, `-t 30 -L 1` is necessary. Using `-t 30 -L 2` will
+result in a maximum of 60 total requests being processed at any given time for that site. And so on. For a conversation
+on this, please see [Issue #126](https://github.com/epi052/feroxbuster/issues/126) which may provide more (or less)
+clarity :wink:
 
 ### ferox-config.toml
+
 After setting built-in default values, any values defined in a `ferox-config.toml` config file will override the
-built-in defaults.  
+built-in defaults.
 
 `feroxbuster` searches for `ferox-config.toml` in the following locations (in the order shown):
+
 - `/etc/feroxbuster/` (global)
 - `CONFIG_DIR/ferxobuster/` (per-user)
 - The same directory as the `feroxbuster` executable (per-user)
@@ -294,14 +330,15 @@ built-in defaults.
 > - MacOs: `$HOME/Library/Application Support` i.e. `/Users/bob/Library/Application Support`
 > - Windows: `{FOLDERID_RoamingAppData}` i.e. `C:\Users\Bob\AppData\Roaming`
 
-If more than one valid configuration file is found, each one overwrites the values found previously.  
+If more than one valid configuration file is found, each one overwrites the values found previously.
 
 If no configuration file is found, nothing happens at this stage.
 
-As an example, let's say that we prefer to use a different wordlist as our default when scanning; we can
-set the `wordlist` value in the config file to override the baked-in default.
+As an example, let's say that we prefer to use a different wordlist as our default when scanning; we can set
+the `wordlist` value in the config file to override the baked-in default.
 
 Notes of interest:
+
 - it's ok to only specify values you want to change without specifying anything else
 - variable names in `ferox-config.toml` must match their command-line counterpart
 
@@ -312,6 +349,7 @@ wordlist = "/wordlists/jhaddix/all.txt"
 ```
 
 A pre-made configuration file with examples of all available settings can be found in `ferox-config.toml.example`.
+
 ```toml
 # ferox-config.toml
 # Example configuration for feroxbuster
@@ -349,6 +387,7 @@ A pre-made configuration file with examples of all available settings can be fou
 # depth = 1
 # filter_size = [5174]
 # filter_regex = ["^ignore me$"]
+# filter_similar = ["https://somesite.com/soft404"]
 # filter_word_count = [993]
 # filter_line_count = [35, 36]
 # queries = [["name","value"], ["rick", "astley"]]
@@ -370,7 +409,9 @@ A pre-made configuration file with examples of all available settings can be fou
 ```
 
 ### Command Line Parsing
-Finally, after parsing the available config file, any options/arguments given on the commandline will override any values that were set as a built-in or config-file value.
+
+Finally, after parsing the available config file, any options/arguments given on the commandline will override any
+values that were set as a built-in or config-file value.
 
 ```
 USAGE:
@@ -404,7 +445,7 @@ OPTIONS:
     -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 (use w/ --json for JSON entries)
-    -p, --proxy <PROXY>                     Proxy to use for requests (ex: http(s)://host:port, socks5://host:port)
+    -p, --proxy <PROXY>                     Proxy to use for requests (ex: http(s)://host:port, socks5(h)://host:port)
     -Q, --query <QUERY>...                  Specify URL query parameters (ex: -Q token=stuff -Q secret=key)
     -R, --replay-codes <REPLAY_CODE>...     Status Codes to send through a Replay Proxy when found (default: --status-
                                             codes value)
@@ -423,11 +464,36 @@ OPTIONS:
     -w, --wordlist <FILE>                   Path to the wordlist
 ```
 
+## 📊 Scan's Display Explained
+
+`feroxbuster` attempts to be intuitive and easy to understand, however, if you are wondering about any of the scan's
+output and what it means, this is the section for you!  
+
+### Discovered Resource
+
+When `feroxbuster` finds a response that you haven't filtered out, it's reported above the progress bars and looks similar to what's pictured below.  
+
+The number of lines, words, and bytes shown here can be used to [filter those responses](#filter-response-by-word-count--line-count--new-in-v160)
+
+![response-bar-explained](img/response-bar-explained.png)
+
+### Overall Scan Progress Bar
+
+The top progress bar, colored yellow, tracks the overall scan status.  Its fields are described in the image below.
+
+![total-bar-explained](img/total-bar-explained.png)
+
+### Directory Scan Progress Bar
+
+All other progress bars, colored cyan, represent a scan of one particular directory and will look similar to what's below.   
+
+![dir-scan-bar-explained](img/dir-scan-bar-explained.png)
+
 ## 🧰 Example Usage
 
 ### Multiple Values
 
-Options that take multiple values are very flexible.  Consider the following ways of specifying extensions:
+Options that take multiple values are very flexible. Consider the following ways of specifying extensions:
 
 ```
 ./feroxbuster -u http://127.1 -x pdf -x js,html -x php txt json,docx
@@ -435,7 +501,8 @@ Options that take multiple values are very flexible.  Consider the following way
 
 The command above adds .pdf, .js, .html, .php, .txt, .json, and .docx to each url
 
-All of the methods above (multiple flags, space separated, comma separated, etc...) are valid and interchangeable.  The same goes for urls, headers, status codes, queries, and size filters.
+All of the methods above (multiple flags, space separated, comma separated, etc...) are valid and interchangeable. The
+same goes for urls, headers, status codes, queries, and size filters.
 
 ### Include Headers
 
@@ -461,24 +528,25 @@ cat targets | ./feroxbuster --stdin --quiet -s 200 301 302 --redirects -x js | f
 ./feroxbuster -u http://127.1 --insecure --proxy http://127.0.0.1:8080
 ```
 
-### Proxy traffic through a SOCKS proxy
+### Proxy traffic through a SOCKS proxy (including DNS lookups)
 
 ```
-./feroxbuster -u http://127.1 --proxy socks5://127.0.0.1:9050
+./feroxbuster -u http://127.1 --proxy socks5h://127.0.0.1:9050
 ```
 
-### Pass auth token via query parameter 
+### Pass auth token via query parameter
 
 ```
 ./feroxbuster -u http://127.1 --query token=0123456789ABCDEF
 ```
 
-### Extract Links from Response Body (New in `v1.1.0`) 
+### 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. 
+`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`)
@@ -493,7 +561,8 @@ Example request/response with `--extract-links` enabled:
 ./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:
+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
 
@@ -505,8 +574,8 @@ With `--extract-links`
 
 ### Limit Total Number of Concurrent Scans (new in `v1.2.0`)
 
-Limit the number of scans permitted to run at any given time.  Recursion will still identify new directories, but newly
-discovered directories can only begin scanning when the total number of active scans drops below the value passed to 
+Limit the number of scans permitted to run at any given time. Recursion will still identify new directories, but newly
+discovered directories can only begin scanning when the total number of active scans drops below the value passed to
 `--scan-limit`.
 
 ```
@@ -517,9 +586,9 @@ discovered directories can only begin scanning when the total number of active s
 
 ### Filter Response by Status Code  (new in `v1.3.0`)
 
-Version 1.3.0 included an overhaul to the filtering system which will allow for a wide array of filters to be added 
-with minimal effort. The first such filter is a Status Code Filter. As responses come back from the scanned server,
-each one is checked against a list of known filters and either displayed or not according to which filters are set.
+Version 1.3.0 included an overhaul to the filtering system which will allow for a wide array of filters to be added with
+minimal effort. The first such filter is a Status Code Filter. As responses come back from the scanned server, each one
+is checked against a list of known filters and either displayed or not according to which filters are set.
 
 ```
 ./feroxbuster -u http://127.1 --filter-status 301
@@ -533,42 +602,52 @@ Scans can be paused and resumed by pressing the ENTER key (shown below)
 
 ### Replay Responses to a Proxy based on Status Code (new in `v1.5.0`)
 
-The `--replay-proxy` and `--replay-codes` options were added as a way to only send a select few responses to a proxy.  This is in stark contrast to `--proxy` which proxies EVERY request.  
+The `--replay-proxy` and `--replay-codes` options were added as a way to only send a select few responses to a proxy.
+This is in stark contrast to `--proxy` which proxies EVERY request.
 
-Imagine you only care about proxying responses that have either the status code `200` or `302` (or you just don't want to clutter up your Burp history).  These two options will allow you to fine-tune what gets proxied and what doesn't.  
+Imagine you only care about proxying responses that have either the status code `200` or `302` (or you just don't want
+to clutter up your Burp history). These two options will allow you to fine-tune what gets proxied and what doesn't.
 
 ```
 ./feroxbuster -u http://127.1 --replay-proxy http://localhost:8080 --replay-codes 200 302 --insecure
 ```
 
-Of note: this means that for every response that matches your replay criteria, you'll end up sending the request that generated that response a second time.  Depending on the target and your engagement terms (if any), it may not make sense from a traffic generated perspective.
+Of note: this means that for every response that matches your replay criteria, you'll end up sending the request that
+generated that response a second time. Depending on the target and your engagement terms (if any), it may not make sense
+from a traffic generated perspective.
 
 ![replay-proxy-demo](img/replay-proxy-demo.gif)
 
 ### Filter Response by Word Count & Line Count  (new in `v1.6.0`)
 
-In addition to filtering on the size of a response, version 1.6.0 added the ability to filter out responses based on the number of lines and/or words contained within the response body.  This change drove a change to the information displayed to the user as well. This section will detail the new information and how to make use of it with the new filters provided.
+In addition to filtering on the size of a response, version 1.6.0 added the ability to filter out responses based on the
+number of lines and/or words contained within the response body. This change drove a change to the information displayed
+to the user as well. This section will detail the new information and how to make use of it with the new filters
+provided.
 
 Example output:
+
 ```
 200        10l        212w       38437c https://example-site.com/index.html
 ```
 
 There are five columns of output above:
+
 - column 1: status code - can be filtered with `-C|--filter-status`
 - column 2: number of lines - can be filtered with `-N|--filter-lines`
 - column 3: number of words - can be filtered with `-W|--filter-words`
 - column 4: number of bytes (overall size) - can be filtered with `-S|--filter-size`
 - column 5: url to discovered resource
 
-### Filter Response Using a Regular Expression (new in `v1.8.0`) 
+### 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.  
+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.**  
+**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
@@ -576,7 +655,8 @@ body, then that response is filtered out.
 
 ### Stop and Resume Scans (`--resume-from FILE`) (new in `v1.9.0`)
 
-Version 1.9.0 adds a few features that allow for completely stopping a scan, and resuming that same scan from a file on disk. 
+Version 1.9.0 adds a few features that allow for completely stopping a scan, and resuming that same scan from a file on
+disk.
 
 A simple `Ctrl+C` during a scan will create a file that contains information about the scan that was cancelled.
 
@@ -586,48 +666,51 @@ A simple `Ctrl+C` during a scan will create a file that contains information abo
 // example snippet of state file
 
 {
-   "scans":[
-      {
-         "id":"057016a14769414aac9a7a62707598cb",
-         "url":"https://localhost.com",
-         "scan_type":"Directory",
-         "complete":true
-      },
-      {
-         "id":"400b2323a16f43468a04ffcbbeba34c6",
-         "url":"https://localhost.com/css",
-         "scan_type":"Directory",
-         "complete":false
+  "scans": [
+    {
+      "id": "057016a14769414aac9a7a62707598cb",
+      "url": "https://localhost.com",
+      "scan_type": "Directory",
+      "complete": true
+    },
+    {
+      "id": "400b2323a16f43468a04ffcbbeba34c6",
+      "url": "https://localhost.com/css",
+      "scan_type": "Directory",
+      "complete": false
+    }
+  ],
+  "config": {
+    "wordlist": "/wordlists/seclists/Discovery/Web-Content/common.txt",
+    "...": "..."
+  },
+  "responses": [
+    {
+      "type": "response",
+      "url": "https://localhost.com/Login",
+      "path": "/Login",
+      "wildcard": false,
+      "status": 302,
+      "content_length": 0,
+      "line_count": 0,
+      "word_count": 0,
+      "headers": {
+        "content-length": "0",
+        "server": "nginx/1.16.1"
       }
-   ],
-   "config":{
-      "wordlist":"/wordlists/seclists/Discovery/Web-Content/common.txt",
-      "...":"..."
-   },
-   "responses":[
-      {
-         "type":"response",
-         "url":"https://localhost.com/Login",
-         "path":"/Login",
-         "wildcard":false,
-         "status":302,
-         "content_length":0,
-         "line_count":0,
-         "word_count":0,
-         "headers":{
-            "content-length":"0",
-            "server":"nginx/1.16.1"
-         }
-      }
-   ]
+    }
+  ]
 },
 ```
 
-Based on the example image above, the same scan can be resumed by using `feroxbuster --resume-from ferox-http_localhost-1606947491.state`.  Directories that were already complete are not rescanned, however partially complete scans are started from the beginning.  
+Based on the example image above, the same scan can be resumed by
+using `feroxbuster --resume-from ferox-http_localhost-1606947491.state`. Directories that were already complete are not
+rescanned, however partially complete scans are started from the beginning.
 
 ![resumed-scan](img/resumed-scan.gif)
 
-In order to prevent state file creation when `Ctrl+C` is pressed, you can simply add the entry below to your `ferox-config.toml`.
+In order to prevent state file creation when `Ctrl+C` is pressed, you can simply add the entry below to
+your `ferox-config.toml`.
 
 ```toml
 # ferox-config.toml
@@ -637,9 +720,12 @@ save_state = false
 
 ### Enforce a Time Limit on Your Scan (new in `v1.10.0`)
 
-Version 1.10.0 adds the ability to set a maximum runtime, or time limit, on your scan.  The usage is pretty simple: a number followed directly by a single character representing seconds, minutes, hours, or days.  `feroxbuster` refers to this combination as a time_spec.  
+Version 1.10.0 adds the ability to set a maximum runtime, or time limit, on your scan. The usage is pretty simple: a
+number followed directly by a single character representing seconds, minutes, hours, or days.  `feroxbuster` refers to
+this combination as a time_spec.
 
 Examples of possible time_specs:
+
 - `30s` - 30 seconds
 - `20m` - 20 minutes
 - `1h`  - 1 hour
@@ -649,21 +735,54 @@ A valid time_spec can be passed to `--time-limit` in order to force a shutdown a
 
 ![time-limit](img/time-limit.gif)
 
+### Extract Links from robots.txt (New in `v1.10.2`)
+
+In addition to [extracting links from the response body](#extract-links-from-response-body-new-in-v110), using
+`--extract-links` makes a request to `/robots.txt` and examines all `Allow` and `Disallow` entries. Directory entries
+are added to the scan queue, while file entries are requested and then reported if appropriate.
+
+### Filter Response by Similarity to A Given Page (fuzzy filter) (new in `v1.11.0`)
+
+Version 1.11.0 adds the ability to specify an example page for filtering pages that are similar to the given example.
+
+For example, consider a site that attempts to redirect new users to a `/register` endpoint. The `/register` page has a
+CSRF token that alters the page's response slightly with each new request (sometimes affecting overall length). This
+means that a simple line/word/char filter won't be able to filter all responses. In order to filter those redirects out,
+one could use a command like this:
+
+```
+./feroxbuster -u https://somesite.xyz --filter-similar-to https://somesite.xyz/register
+```
+
+`--filter-similar-to` requests the page passed to it via CLI (`https://somesite.xyz/register`), after which it hashes 
+the response body using the [SSDeep algorithm](https://ssdeep-project.github.io/ssdeep/index.html).  All subsequent 
+pages are hashed and compared to the original request's hash. If the comparison of the two hashes meets a certain 
+percentage of similarity (currently 95%), then that request will be filtered out.
+
+SSDeep was selected as it does a good job of identifying near-duplicate pages once content-length reaches a certain 
+size, while remaining performant.  Other algorithms were tested but resulted in huge performance hits (orders of 
+magnitude slower on requests/second).
+
+**NOTE**
+- SSDeep/`--filter-similar-to` does not do well at detecting similarity of very small responses
+  - The lack of accuracy with very small responses is considered a fair trade-off for not negatively impacting performance
+- Using a bunch of `--filter-similar-to` values **may** negatively impact performance
+
 ## 🧐 Comparison w/ Similar Tools
 
-There are quite a few similar tools for forced browsing/content discovery.  Burp Suite Pro, Dirb, Dirbuster, etc... 
-However, in my opinion, there are two that set the standard: [gobuster](https://github.com/OJ/gobuster) and 
-[ffuf](https://github.com/ffuf/ffuf).  Both are mature, feature-rich, and all-around incredible tools to use.
+There are quite a few similar tools for forced browsing/content discovery. Burp Suite Pro, Dirb, Dirbuster, etc...
+However, in my opinion, there are two that set the standard: [gobuster](https://github.com/OJ/gobuster) and
+[ffuf](https://github.com/ffuf/ffuf). Both are mature, feature-rich, and all-around incredible tools to use.
 
-So, why would you ever want to use feroxbuster over ffuf/gobuster?  In most cases, you probably won't.  ffuf in particular
-can do the vast majority of things that feroxbuster can, while still offering boatloads more functionality.  Here are
-a few of the use-cases in which feroxbuster may be a better fit:
+So, why would you ever want to use feroxbuster over ffuf/gobuster? In most cases, you probably won't. ffuf in particular
+can do the vast majority of things that feroxbuster can, while still offering boatloads more functionality. Here are a
+few of the use-cases in which feroxbuster may be a better fit:
 
 - You want a **simple** tool usage experience
 - You want to be able to run your content discovery as part of some crazy 12 command unix **pipeline extravaganza**
 - You want to scan through a **SOCKS** proxy
 - You want **auto-filtering** of Wildcard responses by default
-- You want an integrated **link extractor** to increase discovered endpoints
+- You want an integrated **link extractor/robots.txt parser** to increase discovered endpoints
 - You want **recursion** along with some other thing mentioned above (ffuf also does recursion)
 - You want a **configuration file** option for overriding built-in default values for your scans
 
@@ -692,13 +811,15 @@ a few of the use-cases in which feroxbuster may be a better fit:
 | filter out responses by regular expression (`v1.8.0`)                        | ✔ |   | ✔ |
 | save scan's state to disk (can pick up where it left off) (`v1.9.0`)         | ✔ |   |   |
 | maximum run time limit (`v1.10.0`)                                           | ✔ |   | ✔ |
+| use robots.txt to increase scan coverage (`v1.10.2`)                         | ✔ |   |   |
+| use example page's response to fuzzily filter similar pages  (`v1.11.0`)     | ✔ |   |   |
 | **huge** number of other options                                             |   |   | ✔ |
 
-Of note, there's another written-in-rust content discovery tool, [rustbuster](https://github.com/phra/rustbuster). I 
-came across rustbuster when I was naming my tool (😢). I don't have any experience using it, but it appears to 
-be able to do POST requests with an HTTP body, has SOCKS support, and has an 8.3 shortname scanner (in addition to vhost
-dns, directory, etc...).  In short, it definitely looks interesting and may be what you're looking for as it has some 
-capability I haven't seen in similar tools.  
+Of note, there's another written-in-rust content discovery tool, [rustbuster](https://github.com/phra/rustbuster). I
+came across rustbuster when I was naming my tool (😢). I don't have any experience using it, but it appears to be able
+to do POST requests with an HTTP body, has SOCKS support, and has an 8.3 shortname scanner (in addition to vhost dns,
+directory, etc...). In short, it definitely looks interesting and may be what you're looking for as it has some
+capability I haven't seen in similar tools.
 
 ## 🤯 Common Problems/Issues (FAQ)
 
@@ -708,21 +829,24 @@ Why do I get a bunch of `No file descriptors available (os error 24)` errors?
 
 ---
 
-There are a few potential causes of this error.  The simplest is that your operating system sets an open file limit that is aggressively low.  Through personal testing, I've found that `4096` is a reasonable open file limit (this will vary based on your exact setup).
+There are a few potential causes of this error. The simplest is that your operating system sets an open file limit that
+is aggressively low. Through personal testing, I've found that `4096` is a reasonable open file limit (this will vary
+based on your exact setup).
 
-There are quite a few options to solve this particular problem, of which a handful are shown below.  
+There are quite a few options to solve this particular problem, of which a handful are shown below.
 
 #### Increase the Number of Open Files
 
-We'll start by increasing the number of open files the OS allows. On my Kali install, the default was `1024`, and I know some MacOS installs use `256` 😕.
+We'll start by increasing the number of open files the OS allows. On my Kali install, the default was `1024`, and I know
+some MacOS installs use `256` 😕.
 
 ##### Edit `/etc/security/limits.conf`
 
-One option to up the limit is to edit `/etc/security/limits.conf` so that it includes the two lines below.  
+One option to up the limit is to edit `/etc/security/limits.conf` so that it includes the two lines below.
 
 - `*` represents all users
-- `hard` and `soft` indicate the hard and soft limits for the OS 
-- `nofile` is the number of open files option. 
+- `hard` and `soft` indicate the hard and soft limits for the OS
+- `nofile` is the number of open files option.
 
 ```
 /etc/security/limits.conf
@@ -743,20 +867,25 @@ ulimit -n 4096
 
 #### Additional Tweaks (may not be needed)
 
-If you still find yourself hitting the file limit with the above changes, there are a few additional tweaks that may help.  
+If you still find yourself hitting the file limit with the above changes, there are a few additional tweaks that may
+help.
 
-> This section was shamelessly stolen from this [stackoverflow answer](https://stackoverflow.com/a/3923785).  More information is included in that post and is recommended reading if you end up needing to use this section.
+> This section was shamelessly stolen from this [stackoverflow answer](https://stackoverflow.com/a/3923785). More information is included in that post and is recommended reading if you end up needing to use this section.
 
-✨ Special thanks to HTB user [@sparkla](https://www.hackthebox.eu/home/users/profile/221599) for their help with identifying these additional tweaks ✨
+✨ Special thanks to HTB user [@sparkla](https://www.hackthebox.eu/home/users/profile/221599) for their help with
+identifying these additional tweaks ✨
 
 ##### Increase the ephemeral port range, and decrease the tcp_fin_timeout.
 
-The ephermal port range defines the maximum number of outbound sockets a host can create from a particular I.P. address. The fin_timeout defines the minimum time these sockets will stay in TIME_WAIT state (unusable after being used once). Usual system defaults are
+The ephermal port range defines the maximum number of outbound sockets a host can create from a particular I.P. address.
+The fin_timeout defines the minimum time these sockets will stay in TIME_WAIT state (unusable after being used once).
+Usual system defaults are
 
 - `net.ipv4.ip_local_port_range = 32768   61000`
 - `net.ipv4.tcp_fin_timeout = 60`
 
-This basically means your system cannot consistently guarantee more than `(61000 - 32768) / 60 = 470` sockets per second.
+This basically means your system cannot consistently guarantee more than `(61000 - 32768) / 60 = 470` sockets per
+second.
 
 ```
 sudo sysctl net.ipv4.ip_local_port_range="15000 61000"
@@ -765,7 +894,9 @@ sudo sysctl net.ipv4.tcp_fin_timeout=30
 
 ##### Allow socket reuse while in a `TIME_WAIT` status
 
-This allows fast cycling of sockets in time_wait state and re-using them. Make sure to read post [Coping with the TCP TIME-WAIT](https://vincent.bernat.ch/en/blog/2014-tcp-time-wait-state-linux) from Vincent Bernat to understand the implications.
+This allows fast cycling of sockets in time_wait state and re-using them. Make sure to read
+post [Coping with the TCP TIME-WAIT](https://vincent.bernat.ch/en/blog/2014-tcp-time-wait-state-linux) from Vincent
+Bernat to understand the implications.
 
 ```
 sudo sysctl net.ipv4.tcp_tw_reuse=1 
@@ -773,13 +904,47 @@ sudo sysctl net.ipv4.tcp_tw_reuse=1
 
 ### Progress bars print one line at a time
 
-`feroxbuster` needs a terminal width of at least the size of what's being printed in order to do progress bar printing correctly.  If your width is too small, you may see output like what's shown below.
+`feroxbuster` needs a terminal width of at least the size of what's being printed in order to do progress bar printing
+correctly. If your width is too small, you may see output like what's shown below.
 
 ![small-term](img/small-term.png)
 
-If you can, simply make the terminal wider and rerun.  If you're unable to make your terminal wider
-consider using `-q` to suppress the progress bars.
+If you can, simply make the terminal wider and rerun. If you're unable to make your terminal wider consider using `-q`
+to suppress the progress bars.
 
 ### What do each of the numbers beside the URL mean?
 
-Please refer to [this section](#filter-response-by-word-count--line-count--new-in-v160) where each number's meaning and how to use it to filter responses is discussed.
+Please refer to [this section](#filter-response-by-word-count--line-count--new-in-v160) where each number's meaning and
+how to use it to filter responses is discussed.
+
+### Connection closed before message completed
+
+The error in question can be boiled down to 'networking stuff'. `feroxbuster`
+uses [reqwest](https://docs.rs/reqwest/latest/) which uses [hyper](https://docs.rs/hyper/latest/hyper/) to make requests
+to the server. [This issue report](https://github.com/hyperium/hyper/issues/2136#issuecomment-589345238) to the hyper
+project explains what is happening (quoted below to save you a click). This isn't a bug so much as it's a
+target-specific tuning issue. When lowering the `-t` value, the error doesn't occur (or happens much less frequently).
+
+This isn't a bug. Simply slow down the scan. A `-t` value of 50 was chosen as a sane default that's still quite fast out
+of the box. However, network related errors may occur when the client and/or server become over-saturated.
+The [Threads and Connection Limits At A High-Level](#threads-and-connection-limits-at-a-high-level) section details how
+to accomplish per-target tuning.
+
+> This is just due to the racy nature of networking.
+>
+> hyper has a connection pool of idle connections, and it selected one to send your request. Most of the time, hyper will receive the server's FIN and drop the dead connection from its pool. But occasionally, a connection will be selected from the pool and written to at the same time the server is deciding to close the connection. Since hyper already wrote some of the request, it can't really retry it automatically on a new connection, since the server may have acted already.
+
+### SSL Error routines:tls_process_server_certificate:certificate verify failed
+
+In the event you see an error similar to
+
+![self-signed](img/insecure.png)
+
+```
+error trying to connect: error:1416F086:SSL routines:tls_process_server_certificate:certificate verify failed:ssl/statem/statem_clnt.c:1913: (self signed certificate)
+```
+
+You just need to add the `-k|--insecure` flag to your command.
+
+`feroxbuster` rejects self-signed certs and other "insecure" certificates/site configurations by default. You can choose
+to scan these services anyway by telling `feroxbuster` to ignore insecure server certs.

build.rs

@@ -5,6 +5,12 @@ use clap::Shell;
 include!("src/parser.rs");
 
 fn main() {
+    println!("cargo:rerun-if-env-changed=src/parser.rs");
+
+    if std::env::var("DOCS_RS").is_ok() {
+        return; // only build when we're not generating docs
+    }
+
     let outdir = "shell_completions";
 
     let mut app = initialize();

ferox-config.toml.example

@@ -33,6 +33,7 @@
 # depth = 1
 # filter_size = [5174]
 # filter_regex = ["^ignore me$"]
+# filter_similar = ["https://somesite.com/soft404"]
 # filter_word_count = [993]
 # filter_line_count = [35, 36]
 # queries = [["name","value"], ["rick", "astley"]]

shell_completions/_feroxbuster

@@ -25,8 +25,8 @@ _feroxbuster() {
 '--depth=[Maximum recursion depth, a depth of 0 is infinite recursion (default: 4)]' \
 '-T+[Number of seconds before a request times out (default: 7)]' \
 '--timeout=[Number of seconds before a request times out (default: 7)]' \
-'-p+[Proxy to use for requests (ex: http(s)://host:port, socks5://host:port)]' \
-'--proxy=[Proxy to use for requests (ex: http(s)://host:port, socks5://host:port)]' \
+'-p+[Proxy to use for requests (ex: http(s)://host:port, socks5(h)://host:port)]' \
+'--proxy=[Proxy to use for requests (ex: http(s)://host:port, socks5(h)://host:port)]' \
 '-P+[Send only unfiltered requests through a Replay Proxy, instead of all requests]' \
 '--replay-proxy=[Send only unfiltered requests through a Replay Proxy, instead of all requests]' \
 '*-R+[Status Codes to send through a Replay Proxy when found (default: --status-codes value)]' \
@@ -55,6 +55,7 @@ _feroxbuster() {
 '*--filter-lines=[Filter out messages of a particular line count (ex: -N 20 -N 31,30)]' \
 '*-C+[Filter out status codes (deny list) (ex: -C 200 -C 401)]' \
 '*--filter-status=[Filter out status codes (deny list) (ex: -C 200 -C 401)]' \
+'*--filter-similar-to=[Filter out pages that are similar to the given page (ex. --filter-similar-to http://site.xyz/soft404)]' \
 '-L+[Limit total number of concurrent scans (default: 0, i.e. no limit)]' \
 '--scan-limit=[Limit total number of concurrent scans (default: 0, i.e. no limit)]' \
 '--time-limit=[Limit total run time of all scans (ex: --time-limit 10m)]' \

shell_completions/_feroxbuster.ps1

@@ -30,8 +30,8 @@ Register-ArgumentCompleter -Native -CommandName 'feroxbuster' -ScriptBlock {
             [CompletionResult]::new('--depth', 'depth', [CompletionResultType]::ParameterName, 'Maximum recursion depth, a depth of 0 is infinite recursion (default: 4)')
             [CompletionResult]::new('-T', 'T', [CompletionResultType]::ParameterName, 'Number of seconds before a request times out (default: 7)')
             [CompletionResult]::new('--timeout', 'timeout', [CompletionResultType]::ParameterName, 'Number of seconds before a request times out (default: 7)')
-            [CompletionResult]::new('-p', 'p', [CompletionResultType]::ParameterName, 'Proxy to use for requests (ex: http(s)://host:port, socks5://host:port)')
-            [CompletionResult]::new('--proxy', 'proxy', [CompletionResultType]::ParameterName, 'Proxy to use for requests (ex: http(s)://host:port, socks5://host:port)')
+            [CompletionResult]::new('-p', 'p', [CompletionResultType]::ParameterName, 'Proxy to use for requests (ex: http(s)://host:port, socks5(h)://host:port)')
+            [CompletionResult]::new('--proxy', 'proxy', [CompletionResultType]::ParameterName, 'Proxy to use for requests (ex: http(s)://host:port, socks5(h)://host:port)')
             [CompletionResult]::new('-P', 'P', [CompletionResultType]::ParameterName, 'Send only unfiltered requests through a Replay Proxy, instead of all requests')
             [CompletionResult]::new('--replay-proxy', 'replay-proxy', [CompletionResultType]::ParameterName, 'Send only unfiltered requests through a Replay Proxy, instead of all requests')
             [CompletionResult]::new('-R', 'R', [CompletionResultType]::ParameterName, 'Status Codes to send through a Replay Proxy when found (default: --status-codes value)')
@@ -60,6 +60,7 @@ Register-ArgumentCompleter -Native -CommandName 'feroxbuster' -ScriptBlock {
             [CompletionResult]::new('--filter-lines', 'filter-lines', [CompletionResultType]::ParameterName, 'Filter out messages of a particular line count (ex: -N 20 -N 31,30)')
             [CompletionResult]::new('-C', 'C', [CompletionResultType]::ParameterName, 'Filter out status codes (deny list) (ex: -C 200 -C 401)')
             [CompletionResult]::new('--filter-status', 'filter-status', [CompletionResultType]::ParameterName, 'Filter out status codes (deny list) (ex: -C 200 -C 401)')
+            [CompletionResult]::new('--filter-similar-to', 'filter-similar-to', [CompletionResultType]::ParameterName, 'Filter out pages that are similar to the given page (ex. --filter-similar-to http://site.xyz/soft404)')
             [CompletionResult]::new('-L', 'L', [CompletionResultType]::ParameterName, 'Limit total number of concurrent scans (default: 0, i.e. no limit)')
             [CompletionResult]::new('--scan-limit', 'scan-limit', [CompletionResultType]::ParameterName, 'Limit total number of concurrent scans (default: 0, i.e. no limit)')
             [CompletionResult]::new('--time-limit', 'time-limit', [CompletionResultType]::ParameterName, 'Limit total run time of all scans (ex: --time-limit 10m)')

shell_completions/feroxbuster.bash

@@ -20,7 +20,7 @@ _feroxbuster() {
 
     case "${cmd}" in
         feroxbuster)
-            opts=" -v -q -D -r -k -n -f -e -h -V -w -u -t -d -T -p -P -R -s -o -a -x -H -Q -S -X -W -N -C -L  --verbosity --quiet --json --dont-filter --redirects --insecure --no-recursion --add-slash --stdin --extract-links --help --version --wordlist --url --threads --depth --timeout --proxy --replay-proxy --replay-codes --status-codes --output --resume-from --debug-log --user-agent --extensions --headers --query --filter-size --filter-regex --filter-words --filter-lines --filter-status --scan-limit --time-limit  "
+            opts=" -v -q -D -r -k -n -f -e -h -V -w -u -t -d -T -p -P -R -s -o -a -x -H -Q -S -X -W -N -C -L  --verbosity --quiet --json --dont-filter --redirects --insecure --no-recursion --add-slash --stdin --extract-links --help --version --wordlist --url --threads --depth --timeout --proxy --replay-proxy --replay-codes --status-codes --output --resume-from --debug-log --user-agent --extensions --headers --query --filter-size --filter-regex --filter-words --filter-lines --filter-status --filter-similar-to --scan-limit --time-limit  "
             if [[ ${cur} == -* || ${COMP_CWORD} -eq 1 ]] ; then
                 COMPREPLY=( $(compgen -W "${opts}" -- "${cur}") )
                 return 0
@@ -187,6 +187,10 @@ _feroxbuster() {
                     COMPREPLY=($(compgen -f "${cur}"))
                     return 0
                     ;;
+                --filter-similar-to)
+                    COMPREPLY=($(compgen -f "${cur}"))
+                    return 0
+                    ;;
                 --scan-limit)
                     COMPREPLY=($(compgen -f "${cur}"))
                     return 0

shell_completions/feroxbuster.fish

@@ -3,7 +3,7 @@ complete -c feroxbuster -n "__fish_use_subcommand" -s u -l url -d 'The target UR
 complete -c feroxbuster -n "__fish_use_subcommand" -s t -l threads -d 'Number of concurrent threads (default: 50)'
 complete -c feroxbuster -n "__fish_use_subcommand" -s d -l depth -d 'Maximum recursion depth, a depth of 0 is infinite recursion (default: 4)'
 complete -c feroxbuster -n "__fish_use_subcommand" -s T -l timeout -d 'Number of seconds before a request times out (default: 7)'
-complete -c feroxbuster -n "__fish_use_subcommand" -s p -l proxy -d 'Proxy to use for requests (ex: http(s)://host:port, socks5://host:port)'
+complete -c feroxbuster -n "__fish_use_subcommand" -s p -l proxy -d 'Proxy to use for requests (ex: http(s)://host:port, socks5(h)://host:port)'
 complete -c feroxbuster -n "__fish_use_subcommand" -s P -l replay-proxy -d 'Send only unfiltered requests through a Replay Proxy, instead of all requests'
 complete -c feroxbuster -n "__fish_use_subcommand" -s R -l replay-codes -d 'Status Codes to send through a Replay Proxy when found (default: --status-codes value)'
 complete -c feroxbuster -n "__fish_use_subcommand" -s s -l status-codes -d 'Status Codes to include (allow list) (default: 200 204 301 302 307 308 401 403 405)'
@@ -19,6 +19,7 @@ complete -c feroxbuster -n "__fish_use_subcommand" -s X -l filter-regex -d 'Filt
 complete -c feroxbuster -n "__fish_use_subcommand" -s W -l filter-words -d 'Filter out messages of a particular word count (ex: -W 312 -W 91,82)'
 complete -c feroxbuster -n "__fish_use_subcommand" -s N -l filter-lines -d 'Filter out messages of a particular line count (ex: -N 20 -N 31,30)'
 complete -c feroxbuster -n "__fish_use_subcommand" -s C -l filter-status -d 'Filter out status codes (deny list) (ex: -C 200 -C 401)'
+complete -c feroxbuster -n "__fish_use_subcommand" -l filter-similar-to -d 'Filter out pages that are similar to the given page (ex. --filter-similar-to http://site.xyz/soft404)'
 complete -c feroxbuster -n "__fish_use_subcommand" -s L -l scan-limit -d 'Limit total number of concurrent scans (default: 0, i.e. no limit)'
 complete -c feroxbuster -n "__fish_use_subcommand" -l time-limit -d 'Limit total run time of all scans (ex: --time-limit 10m)'
 complete -c feroxbuster -n "__fish_use_subcommand" -s v -l verbosity -d 'Increase verbosity level (use -vv or more for greater effect. [CAUTION] 4 -v\'s is probably too much)'

src/banner.rs

@@ -1,9 +1,13 @@
-use crate::config::{Configuration, CONFIGURATION};
-use crate::utils::{make_request, status_colorizer};
+use crate::{
+    config::{Configuration, CONFIGURATION},
+    statistics::StatCommand,
+    utils::{make_request, status_colorizer},
+};
 use console::{style, Emoji};
 use reqwest::{Client, Url};
 use serde_json::Value;
 use std::io::Write;
+use tokio::sync::mpsc::UnboundedSender;
 
 /// macro helper to abstract away repetitive string formatting
 macro_rules! format_banner_entry_helper {
@@ -67,8 +71,13 @@ enum UpdateStatus {
 /// 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);
+async fn needs_update(
+    client: &Client,
+    url: &str,
+    bin_version: &str,
+    tx_stats: UnboundedSender<StatCommand>,
+) -> UpdateStatus {
+    log::trace!("enter: needs_update({:?}, {}, {:?})", client, url, tx_stats);
 
     let unknown = UpdateStatus::Unknown;
 
@@ -81,7 +90,7 @@ async fn needs_update(client: &Client, url: &str, bin_version: &str) -> UpdateSt
         }
     };
 
-    if let Ok(response) = make_request(&client, &api_url).await {
+    if let Ok(response) = make_request(&client, &api_url, tx_stats.clone()).await {
         let body = response.text().await.unwrap_or_default();
 
         let json_response: Value = serde_json::from_str(&body).unwrap_or_default();
@@ -137,8 +146,13 @@ fn format_emoji(emoji: &str) -> String {
 /// Prints the banner to stdout.
 ///
 /// Only prints those settings which are either always present, or passed in by the user.
-pub async fn initialize<W>(targets: &[String], config: &Configuration, version: &str, mut writer: W)
-where
+pub async fn initialize<W>(
+    targets: &[String],
+    config: &Configuration,
+    version: &str,
+    mut writer: W,
+    tx_stats: UnboundedSender<StatCommand>,
+) where
     W: Write,
 {
     let artwork = format!(
@@ -150,7 +164,7 @@ by Ben "epi" Risher {}                 ver: {}"#,
         Emoji("🤓", &format!("{:<2}", "\u{0020}")),
         version
     );
-    let status = needs_update(&CONFIGURATION.client, UPDATE_URL, version).await;
+    let status = needs_update(&CONFIGURATION.client, UPDATE_URL, version, tx_stats).await;
 
     let top = "───────────────────────────┬──────────────────────";
     let addl_section = "──────────────────────────────────────────────────";
@@ -305,6 +319,17 @@ by Ben "epi" Risher {}                 ver: {}"#,
         }
     }
 
+    if !config.filter_similar.is_empty() {
+        for filter in &config.filter_similar {
+            writeln!(
+                &mut writer,
+                "{}",
+                format_banner_entry!(format_emoji("💢"), "Similarity Filter", filter)
+            )
+            .unwrap_or_default(); // 💢
+        }
+    }
+
     for filter in &config.filter_word_count {
         writeln!(
             &mut writer,
@@ -423,41 +448,19 @@ by Ben "epi" Risher {}                 ver: {}"#,
         .unwrap_or_default(); // 🤪
     }
 
-    match config.verbosity {
+    let volume = ["🔈", "🔉", "🔊", "📢"];
+    if let 1..=4 = config.verbosity {
         //speaker medium volume (increasing with verbosity to loudspeaker)
-        1 => {
-            writeln!(
-                &mut writer,
-                "{}",
-                format_banner_entry!(format_emoji("🔈"), "Verbosity", config.verbosity)
+        writeln!(
+            &mut writer,
+            "{}",
+            format_banner_entry!(
+                format_emoji(volume[config.verbosity as usize - 1]),
+                "Verbosity",
+                config.verbosity
             )
-            .unwrap_or_default(); // 🔈
-        }
-        2 => {
-            writeln!(
-                &mut writer,
-                "{}",
-                format_banner_entry!(format_emoji("🔉"), "Verbosity", config.verbosity)
-            )
-            .unwrap_or_default(); // 🔉
-        }
-        3 => {
-            writeln!(
-                &mut writer,
-                "{}",
-                format_banner_entry!(format_emoji("🔊"), "Verbosity", config.verbosity)
-            )
-            .unwrap_or_default(); // 🔊
-        }
-        4 => {
-            writeln!(
-                &mut writer,
-                "{}",
-                format_banner_entry!(format_emoji("📢"), "Verbosity", config.verbosity)
-            )
-            .unwrap_or_default(); // 📢
-        }
-        _ => {}
+        )
+        .unwrap_or_default();
     }
 
     if config.add_slash {
@@ -547,31 +550,40 @@ by Ben "epi" Risher {}                 ver: {}"#,
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::VERSION;
+    use crate::{FeroxChannel, VERSION};
     use httpmock::Method::GET;
     use httpmock::MockServer;
     use std::fs::read_to_string;
     use std::io::stderr;
     use std::time::Duration;
     use tempfile::NamedTempFile;
+    use tokio::sync::mpsc;
 
     #[tokio::test(core_threads = 1)]
     /// test to hit no execution of targets for loop in banner
     async fn banner_intialize_without_targets() {
         let config = Configuration::default();
-        initialize(&[], &config, VERSION, stderr()).await;
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
+
+        initialize(&[], &config, VERSION, stderr(), tx).await;
     }
 
     #[tokio::test(core_threads = 1)]
     /// test to hit no execution of statuscode for loop in banner
     async fn banner_intialize_without_status_codes() {
-        let mut config = Configuration::default();
-        config.status_codes = vec![];
+        let config = Configuration {
+            status_codes: vec![],
+            ..Default::default()
+        };
+
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
+
         initialize(
             &[String::from("http://localhost")],
             &config,
             VERSION,
             stderr(),
+            tx,
         )
         .await;
     }
@@ -579,13 +591,19 @@ mod tests {
     #[tokio::test(core_threads = 1)]
     /// test to hit an empty config file
     async fn banner_intialize_without_config_file() {
-        let mut config = Configuration::default();
-        config.config = String::new();
+        let config = Configuration {
+            config: String::new(),
+            ..Default::default()
+        };
+
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
+
         initialize(
             &[String::from("http://localhost")],
             &config,
             VERSION,
             stderr(),
+            tx,
         )
         .await;
     }
@@ -593,13 +611,19 @@ mod tests {
     #[tokio::test(core_threads = 1)]
     /// test to hit an empty config file
     async fn banner_intialize_without_queries() {
-        let mut config = Configuration::default();
-        config.queries = vec![(String::new(), String::new())];
+        let config = Configuration {
+            queries: vec![(String::new(), String::new())],
+            ..Default::default()
+        };
+
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
+
         initialize(
             &[String::from("http://localhost")],
             &config,
             VERSION,
             stderr(),
+            tx,
         )
         .await;
     }
@@ -609,11 +633,14 @@ mod tests {
     async fn banner_intialize_with_mismatched_version() {
         let config = Configuration::default();
         let file = NamedTempFile::new().unwrap();
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
+
         initialize(
             &[String::from("http://localhost")],
             &config,
             "mismatched-version",
             &file,
+            tx,
         )
         .await;
         let contents = read_to_string(file.path()).unwrap();
@@ -625,7 +652,9 @@ mod tests {
     #[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;
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
+
+        let result = needs_update(&CONFIGURATION.client, &"", VERSION, tx).await;
         assert!(matches!(result, UpdateStatus::Unknown));
     }
 
@@ -639,7 +668,9 @@ mod tests {
             then.status(200).body("{\"tag_name\":\"v1.1.0\"}");
         });
 
-        let result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.1.0").await;
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
+
+        let result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.1.0", tx).await;
 
         assert_eq!(mock.hits(), 1);
         assert!(matches!(result, UpdateStatus::UpToDate));
@@ -655,7 +686,9 @@ mod tests {
             then.status(200).body("{\"tag_name\":\"v1.1.0\"}");
         });
 
-        let result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.0.1").await;
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
+
+        let result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.0.1", tx).await;
 
         assert_eq!(mock.hits(), 1);
         assert!(matches!(result, UpdateStatus::OutOfDate));
@@ -673,7 +706,9 @@ mod tests {
                 .delay(Duration::from_secs(8));
         });
 
-        let result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.0.1").await;
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
+
+        let result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.0.1", tx).await;
 
         assert_eq!(mock.hits(), 1);
         assert!(matches!(result, UpdateStatus::Unknown));
@@ -689,7 +724,9 @@ mod tests {
             then.status(200).body("not json");
         });
 
-        let result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.0.1").await;
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
+
+        let result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.0.1", tx).await;
 
         assert_eq!(mock.hits(), 1);
         assert!(matches!(result, UpdateStatus::Unknown));
@@ -706,7 +743,9 @@ mod tests {
                 .body("{\"no tag_name\": \"doesn't exist\"}");
         });
 
-        let result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.0.1").await;
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
+
+        let result = needs_update(&CONFIGURATION.client, &srv.url("/latest"), "1.0.1", tx).await;
 
         assert_eq!(mock.hits(), 1);
         assert!(matches!(result, UpdateStatus::Unknown));

src/config.rs

@@ -1,18 +1,23 @@
-use crate::scan_manager::resume_scan;
-use crate::utils::{module_colorizer, status_colorizer};
-use crate::{client, parser, progress};
-use crate::{FeroxSerialize, DEFAULT_CONFIG_NAME, DEFAULT_STATUS_CODES, DEFAULT_WORDLIST, VERSION};
+use crate::{
+    client, parser,
+    progress::{add_bar, BarType},
+    scan_manager::resume_scan,
+    utils::{module_colorizer, status_colorizer},
+    FeroxSerialize, DEFAULT_CONFIG_NAME, DEFAULT_STATUS_CODES, DEFAULT_WORDLIST, VERSION,
+};
 use clap::{value_t, ArgMatches};
 use indicatif::{MultiProgress, ProgressBar, ProgressDrawTarget};
 use lazy_static::lazy_static;
 use reqwest::{Client, StatusCode};
 use serde::{Deserialize, 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;
+use std::{
+    collections::HashMap,
+    env::{current_dir, current_exe},
+    fs::read_to_string,
+    path::PathBuf,
+};
 
 lazy_static! {
     /// Global configuration state
@@ -22,7 +27,7 @@ lazy_static! {
     pub static ref PROGRESS_BAR: MultiProgress = MultiProgress::with_draw_target(ProgressDrawTarget::stdout());
 
     /// Global progress bar that is only used for printing messages that don't jack up other bars
-    pub static ref PROGRESS_PRINTER: ProgressBar = progress::add_bar("", 0, true, false);
+    pub static ref PROGRESS_PRINTER: ProgressBar = add_bar("", 0, BarType::Hidden);
 }
 
 /// macro helper to abstract away repetitive configuration updates
@@ -80,7 +85,7 @@ fn report_and_exit(err: &str) -> ! {
 pub struct Configuration {
     #[serde(rename = "type", default = "serialized_type")]
     /// Name of this type of struct, used for serialization, i.e. `{"type":"configuration"}`
-    kind: String,
+    pub kind: String,
 
     /// Path to the wordlist
     #[serde(default = "wordlist")]
@@ -90,11 +95,11 @@ pub struct Configuration {
     #[serde(default)]
     pub config: String,
 
-    /// Proxy to use for requests (ex: http(s)://host:port, socks5://host:port)
+    /// Proxy to use for requests (ex: http(s)://host:port, socks5(h)://host:port)
     #[serde(default)]
     pub proxy: String,
 
-    /// Replay Proxy to use for requests (ex: http(s)://host:port, socks5://host:port)
+    /// Replay Proxy to use for requests (ex: http(s)://host:port, socks5(h)://host:port)
     #[serde(default)]
     pub replay_proxy: String,
 
@@ -223,6 +228,10 @@ pub struct Configuration {
     #[serde(default)]
     pub resumed: bool,
 
+    /// Resume scan from this file
+    #[serde(default)]
+    pub resume_from: String,
+
     /// Whether or not a scan's current state should be saved when user presses Ctrl+C
     ///
     /// Not configurable from CLI; can only be set from a config file
@@ -233,6 +242,10 @@ pub struct Configuration {
     /// non-negative integer and the next character is either s, m, h, or d (case insensitive)
     #[serde(default)]
     pub time_limit: String,
+
+    /// Filter out response bodies that meet a certain threshold of similarity
+    #[serde(default)]
+    pub filter_similar: Vec<String>,
 }
 
 // functions timeout, threads, status_codes, user_agent, wordlist, save_state, and depth are used to provide
@@ -320,6 +333,7 @@ impl Default for Configuration {
             debug_log: String::new(),
             target_url: String::new(),
             time_limit: String::new(),
+            resume_from: String::new(),
             replay_proxy: String::new(),
             queries: Vec::new(),
             extensions: Vec::new(),
@@ -328,6 +342,7 @@ impl Default for Configuration {
             filter_line_count: Vec::new(),
             filter_word_count: Vec::new(),
             filter_status: Vec::new(),
+            filter_similar: Vec::new(),
             headers: HashMap::new(),
             depth: depth(),
             threads: threads(),
@@ -359,6 +374,7 @@ impl Configuration {
     /// - **insecure**: `false` (don't be insecure, i.e. don't allow invalid certs)
     /// - **extensions**: `None`
     /// - **filter_size**: `None`
+    /// - **filter_similar**: `None`
     /// - **filter_regex**: `None`
     /// - **filter_word_count**: `None`
     /// - **filter_line_count**: `None`
@@ -395,8 +411,10 @@ impl Configuration {
     pub fn new() -> Self {
         // when compiling for test, we want to eliminate the runtime dependency of the parser
         if cfg!(test) {
-            let mut test_config = Configuration::default();
-            test_config.save_state = false; // don't clutter up junk when testing
+            let test_config = Configuration {
+                save_state: false, // don't clutter up junk when testing
+                ..Default::default()
+            };
             return test_config;
         }
 
@@ -509,6 +527,7 @@ impl Configuration {
         update_config_if_present!(&mut config.output, args, "output", String);
         update_config_if_present!(&mut config.debug_log, args, "debug_log", String);
         update_config_if_present!(&mut config.time_limit, args, "time_limit", String);
+        update_config_if_present!(&mut config.resume_from, args, "resume_from", String);
 
         if let Some(arg) = args.values_of("status_codes") {
             config.status_codes = arg
@@ -552,6 +571,10 @@ impl Configuration {
             config.filter_regex = arg.map(|val| val.to_string()).collect();
         }
 
+        if let Some(arg) = args.values_of("filter_similar") {
+            config.filter_similar = arg.map(|val| val.to_string()).collect();
+        }
+
         if let Some(arg) = args.values_of("filter_size") {
             config.filter_size = arg
                 .map(|size| {
@@ -760,6 +783,11 @@ impl Configuration {
             new.filter_regex,
             Vec::<String>::new()
         );
+        update_if_not_default!(
+            &mut conf.filter_similar,
+            new.filter_similar,
+            Vec::<String>::new()
+        );
         update_if_not_default!(
             &mut conf.filter_word_count,
             new.filter_word_count,
@@ -779,6 +807,7 @@ impl Configuration {
         update_if_not_default!(&mut conf.scan_limit, new.scan_limit, 0);
         update_if_not_default!(&mut conf.replay_proxy, new.replay_proxy, "");
         update_if_not_default!(&mut conf.debug_log, new.debug_log, "");
+        update_if_not_default!(&mut conf.resume_from, new.resume_from, "");
         update_if_not_default!(&mut conf.json, new.json, false);
 
         update_if_not_default!(&mut conf.timeout, new.timeout, timeout());
@@ -878,6 +907,7 @@ mod tests {
             time_limit = "10m"
             output = "/some/otherpath"
             debug_log = "/yet/anotherpath"
+            resume_from = "/some/state/file"
             redirects = true
             insecure = true
             extensions = ["html", "php", "js"]
@@ -893,6 +923,7 @@ mod tests {
             depth = 1
             filter_size = [4120]
             filter_regex = ["^ignore me$"]
+            filter_similar = ["https://somesite.com/soft404"]
             filter_word_count = [994, 992]
             filter_line_count = [34]
             filter_status = [201]
@@ -911,6 +942,7 @@ mod tests {
         assert_eq!(config.proxy, String::new());
         assert_eq!(config.target_url, String::new());
         assert_eq!(config.time_limit, String::new());
+        assert_eq!(config.resume_from, String::new());
         assert_eq!(config.debug_log, String::new());
         assert_eq!(config.config, String::new());
         assert_eq!(config.replay_proxy, String::new());
@@ -936,6 +968,7 @@ mod tests {
         assert_eq!(config.extensions, Vec::<String>::new());
         assert_eq!(config.filter_size, Vec::<u64>::new());
         assert_eq!(config.filter_regex, Vec::<String>::new());
+        assert_eq!(config.filter_similar, Vec::<String>::new());
         assert_eq!(config.filter_word_count, Vec::<usize>::new());
         assert_eq!(config.filter_line_count, Vec::<usize>::new());
         assert_eq!(config.filter_status, Vec::<u16>::new());
@@ -1103,6 +1136,13 @@ mod tests {
         assert_eq!(config.filter_regex, vec!["^ignore me$"]);
     }
 
+    #[test]
+    /// parse the test config and see that the value parsed is correct
+    fn config_reads_filter_similar() {
+        let config = setup_config_test();
+        assert_eq!(config.filter_similar, vec!["https://somesite.com/soft404"]);
+    }
+
     #[test]
     /// parse the test config and see that the value parsed is correct
     fn config_reads_filter_size() {
@@ -1145,6 +1185,13 @@ mod tests {
         assert_eq!(config.time_limit, "10m");
     }
 
+    #[test]
+    /// parse the test config and see that the value parsed is correct
+    fn config_reads_resume_from() {
+        let config = setup_config_test();
+        assert_eq!(config.resume_from, "/some/state/file");
+    }
+
     #[test]
     /// parse the test config and see that the values parsed are correct
     fn config_reads_headers() {

src/extractor.rs

@@ -1,17 +1,37 @@
-use crate::FeroxResponse;
+use crate::{
+    client,
+    config::{Configuration, CONFIGURATION},
+    scanner::SCANNED_URLS,
+    statistics::{
+        StatCommand::{self, UpdateUsizeField},
+        StatField::{LinksExtracted, TotalExpected},
+    },
+    utils::{format_url, make_request},
+    FeroxResponse,
+};
 use lazy_static::lazy_static;
 use regex::Regex;
 use reqwest::Url;
 use std::collections::HashSet;
+use tokio::sync::mpsc::UnboundedSender;
 
 /// 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,}|)))(?:"|')"#;
 
+/// Regular expression to pull url paths from robots.txt
+///
+/// ref: https://developers.google.com/search/reference/robots_txt
+const ROBOTS_TXT_REGEX: &str =
+    r#"(?m)^ *(Allow|Disallow): *(?P<url_path>[a-zA-Z0-9._/?#@!&'()+,;%=-]+?)$"#; // multi-line (?m)
+
 lazy_static! {
     /// `LINKFINDER_REGEX` as a regex::Regex type
-    static ref REGEX: Regex = Regex::new(LINKFINDER_REGEX).unwrap();
+    static ref LINKS_REGEX: Regex = Regex::new(LINKFINDER_REGEX).unwrap();
+
+    /// `ROBOTS_TXT_REGEX` as a regex::Regex type
+    static ref ROBOTS_REGEX: Regex = Regex::new(ROBOTS_TXT_REGEX).unwrap();
 }
 
 /// Iterate over a given path, return a list of every sub-path found
@@ -83,14 +103,21 @@ fn add_link_to_set_of_links(link: &str, url: &Url, links: &mut HashSet<String>)
 ///         - homepage/assets/img/
 ///         - homepage/assets/
 ///         - homepage/
-pub async fn get_links(response: &FeroxResponse) -> HashSet<String> {
-    log::trace!("enter: get_links({})", response.url().as_str());
+pub async fn get_links(
+    response: &FeroxResponse,
+    tx_stats: UnboundedSender<StatCommand>,
+) -> HashSet<String> {
+    log::trace!(
+        "enter: get_links({}, {:?})",
+        response.url().as_str(),
+        tx_stats
+    );
 
     let mut links = HashSet::<String>::new();
 
     let body = response.text();
 
-    for capture in REGEX.captures_iter(&body) {
+    for capture in LINKS_REGEX.captures_iter(&body) {
         // remove single & double quotes from both ends of the capture
         // capture[0] is the entire match, additional capture groups start at [1]
         let link = capture[0].trim_matches(|c| c == '\'' || c == '"');
@@ -105,27 +132,14 @@ pub async fn get_links(response: &FeroxResponse) -> HashSet<String> {
                     continue;
                 }
 
-                for sub_path in get_sub_paths_from_path(absolute.path()) {
-                    // take a url fragment like homepage/assets/img/icons/handshake.svg and
-                    // incrementally add
-                    //     - homepage/assets/img/icons/
-                    //     - homepage/assets/img/
-                    //     - homepage/assets/
-                    //     - homepage/
-                    log::debug!("Adding {} to {:?}", sub_path, links);
-                    add_link_to_set_of_links(&sub_path, &response.url(), &mut links);
-                }
+                add_all_sub_paths(absolute.path(), &response, &mut links);
             }
             Err(e) => {
                 // this is the expected error that happens when we try to parse a url fragment
                 //     ex: Url::parse("/login") -> Err("relative URL without a base")
                 // while this is technically an error, these are good results for us
                 if e.to_string().contains("relative URL without a base") {
-                    for sub_path in get_sub_paths_from_path(link) {
-                        // incrementally save all sub-paths that led to the relative url's resource
-                        log::debug!("Adding {} to {:?}", sub_path, links);
-                        add_link_to_set_of_links(&sub_path, &response.url(), &mut links);
-                    }
+                    add_all_sub_paths(link, &response, &mut links);
                 } else {
                     // unexpected error has occurred
                     log::error!("Could not parse given url: {}", e);
@@ -134,7 +148,193 @@ pub async fn get_links(response: &FeroxResponse) -> HashSet<String> {
         }
     }
 
+    let multiplier = CONFIGURATION.extensions.len().max(1);
+
+    update_stat!(tx_stats, UpdateUsizeField(LinksExtracted, links.len()));
+    update_stat!(
+        tx_stats,
+        UpdateUsizeField(TotalExpected, links.len() * multiplier)
+    );
+
     log::trace!("exit: get_links -> {:?}", links);
+
+    links
+}
+
+/// take a url fragment like homepage/assets/img/icons/handshake.svg and
+/// incrementally add
+///     - homepage/assets/img/icons/
+///     - homepage/assets/img/
+///     - homepage/assets/
+///     - homepage/
+fn add_all_sub_paths(url_path: &str, response: &FeroxResponse, mut links: &mut HashSet<String>) {
+    log::trace!(
+        "enter: add_all_sub_paths({}, {}, {:?})",
+        url_path,
+        response,
+        links
+    );
+
+    for sub_path in get_sub_paths_from_path(url_path) {
+        log::debug!("Adding {} to {:?}", sub_path, links);
+        add_link_to_set_of_links(&sub_path, &response.url(), &mut links);
+    }
+
+    log::trace!("exit: add_all_sub_paths");
+}
+
+/// Wrapper around link extraction logic
+/// currently used in two places:
+///   - links from response bodys
+///   - links from robots.txt responses
+///
+/// general steps taken:
+///   - create a new Url object based on cli options/args
+///   - check if the new Url has already been seen/scanned -> None
+///   - make a request to the new Url ? -> Some(response) : None
+pub async fn request_feroxresponse_from_new_link(
+    url: &str,
+    tx_stats: UnboundedSender<StatCommand>,
+) -> Option<FeroxResponse> {
+    log::trace!(
+        "enter: request_feroxresponse_from_new_link({}, {:?})",
+        url,
+        tx_stats
+    );
+
+    // create a url based on the given command line options, return None on error
+    let new_url = match format_url(
+        &url,
+        &"",
+        CONFIGURATION.add_slash,
+        &CONFIGURATION.queries,
+        None,
+        tx_stats.clone(),
+    ) {
+        Ok(url) => url,
+        Err(_) => {
+            log::trace!("exit: request_feroxresponse_from_new_link -> None");
+            return None;
+        }
+    };
+
+    if SCANNED_URLS.get_scan_by_url(&new_url.to_string()).is_some() {
+        //we've seen the url before and don't need to scan again
+        log::trace!("exit: request_feroxresponse_from_new_link -> None");
+        return None;
+    }
+
+    // make the request and store the response
+    let new_response = match make_request(&CONFIGURATION.client, &new_url, tx_stats).await {
+        Ok(resp) => resp,
+        Err(_) => {
+            log::trace!("exit: request_feroxresponse_from_new_link -> None");
+            return None;
+        }
+    };
+
+    let new_ferox_response = FeroxResponse::from(new_response, true).await;
+
+    log::trace!(
+        "exit: request_feroxresponse_from_new_link -> {:?}",
+        new_ferox_response
+    );
+    Some(new_ferox_response)
+}
+
+/// helper function that simply requests /robots.txt on the given url's base url
+///
+/// example:
+///     http://localhost/api/users -> http://localhost/robots.txt
+///     
+/// The length of the given path has no effect on what's requested; it's always
+/// base url + /robots.txt
+pub async fn request_robots_txt(
+    base_url: &str,
+    config: &Configuration,
+    tx_stats: UnboundedSender<StatCommand>,
+) -> Option<FeroxResponse> {
+    log::trace!(
+        "enter: get_robots_file({}, CONFIGURATION, {:?})",
+        base_url,
+        tx_stats
+    );
+
+    // more often than not, domain/robots.txt will redirect to www.domain/robots.txt or something
+    // similar; to account for that, create a client that will follow redirects, regardless of
+    // what the user specified for the scanning client. Other than redirects, it will respect
+    // all other user specified settings
+    let follow_redirects = true;
+
+    let proxy = if config.proxy.is_empty() {
+        None
+    } else {
+        Some(config.proxy.as_str())
+    };
+
+    let client = client::initialize(
+        config.timeout,
+        &config.user_agent,
+        follow_redirects,
+        config.insecure,
+        &config.headers,
+        proxy,
+    );
+
+    if let Ok(mut url) = Url::parse(base_url) {
+        url.set_path("/robots.txt"); // overwrite existing path with /robots.txt
+
+        if let Ok(response) = make_request(&client, &url, tx_stats).await {
+            let ferox_response = FeroxResponse::from(response, true).await;
+
+            log::trace!("exit: get_robots_file -> {}", ferox_response);
+            return Some(ferox_response);
+        }
+    }
+
+    None
+}
+
+/// Entry point to perform link extraction from robots.txt
+///
+/// `base_url` can have paths and subpaths, however robots.txt will be requested from the
+/// root of the url
+/// given the url:
+///     http://localhost/stuff/things
+/// this function requests:
+///     http://localhost/robots.txt
+pub async fn extract_robots_txt(
+    base_url: &str,
+    config: &Configuration,
+    tx_stats: UnboundedSender<StatCommand>,
+) -> HashSet<String> {
+    log::trace!(
+        "enter: extract_robots_txt({}, CONFIGURATION, {:?})",
+        base_url,
+        tx_stats
+    );
+    let mut links = HashSet::new();
+
+    if let Some(response) = request_robots_txt(&base_url, &config, tx_stats.clone()).await {
+        for capture in ROBOTS_REGEX.captures_iter(response.text.as_str()) {
+            if let Some(new_path) = capture.name("url_path") {
+                if let Ok(mut new_url) = Url::parse(base_url) {
+                    new_url.set_path(new_path.as_str());
+                    add_all_sub_paths(new_url.path(), &response, &mut links);
+                }
+            }
+        }
+    }
+
+    let multiplier = CONFIGURATION.extensions.len().max(1);
+
+    update_stat!(tx_stats, UpdateUsizeField(LinksExtracted, links.len()));
+    update_stat!(
+        tx_stats,
+        UpdateUsizeField(TotalExpected, links.len() * multiplier)
+    );
+
+    log::trace!("exit: extract_robots_txt -> {:?}", links);
     links
 }
 
@@ -142,9 +342,11 @@ pub async fn get_links(response: &FeroxResponse) -> HashSet<String> {
 mod tests {
     use super::*;
     use crate::utils::make_request;
+    use crate::FeroxChannel;
     use httpmock::Method::GET;
     use httpmock::MockServer;
     use reqwest::Client;
+    use tokio::sync::mpsc;
 
     #[test]
     /// extract sub paths from the given url fragment; expect 4 sub paths and that all are
@@ -254,16 +456,42 @@ mod tests {
 
         let client = Client::new();
         let url = Url::parse(&srv.url("/some-path")).unwrap();
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
 
-        let response = make_request(&client, &url).await.unwrap();
+        let response = make_request(&client, &url, tx.clone()).await.unwrap();
 
         let ferox_response = FeroxResponse::from(response, true).await;
 
-        let links = get_links(&ferox_response).await;
+        let links = get_links(&ferox_response, tx).await;
 
         assert!(links.is_empty());
 
         assert_eq!(mock.hits(), 1);
         Ok(())
     }
+
+    #[tokio::test(core_threads = 1)]
+    /// test that /robots.txt is correctly requested given a base url (happy path)
+    async fn request_robots_txt_with_and_without_proxy() {
+        let srv = MockServer::start();
+
+        let mock = srv.mock(|when, then| {
+            when.method(GET).path("/robots.txt");
+            then.status(200).body("this is a test");
+        });
+
+        let mut config = Configuration::default();
+
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
+
+        request_robots_txt(&srv.url("/api/users/stuff/things"), &config, tx.clone()).await;
+
+        // note: the proxy doesn't actually do anything other than hit a different code branch
+        // in this unit test; it would however have an effect on an integration test
+        config.proxy = srv.url("/ima-proxy");
+
+        request_robots_txt(&srv.url("/api/different/path"), &config, tx).await;
+
+        assert_eq!(mock.hits(), 2);
+    }
 }

src/filters.rs

@@ -1,6 +1,7 @@
 use crate::config::CONFIGURATION;
 use crate::utils::get_url_path_length;
-use crate::FeroxResponse;
+use crate::{FeroxResponse, FeroxSerialize};
+use fuzzyhash::FuzzyHash;
 use regex::Regex;
 use std::any::Any;
 use std::fmt::Debug;
@@ -282,6 +283,44 @@ impl PartialEq for RegexFilter {
     }
 }
 
+/// Simple implementor of FeroxFilter; used to filter out responses based on the similarity of a
+/// Response body with a known response; specified using --filter-similar-to
+#[derive(Default, Debug, PartialEq)]
+pub struct SimilarityFilter {
+    /// Response's body to be used for comparison for similarity
+    pub text: String,
+
+    /// Percentage of similarity at which a page is determined to be a near-duplicate of another
+    pub threshold: u32,
+}
+
+/// implementation of FeroxFilter for SimilarityFilter
+impl FeroxFilter for SimilarityFilter {
+    /// Check `FeroxResponse::text` against what was requested from the site passed in via
+    /// --filter-similar-to
+    fn should_filter_response(&self, response: &FeroxResponse) -> bool {
+        let other = FuzzyHash::new(&response.text);
+
+        if let Ok(result) = FuzzyHash::compare(&self.text, &other.to_string()) {
+            return result >= self.threshold;
+        }
+
+        // couldn't hash the response, don't filter
+        log::warn!("Could not hash body from {}", response.as_str());
+        false
+    }
+
+    /// Compare one SimilarityFilter to another
+    fn box_eq(&self, other: &dyn Any) -> bool {
+        other.downcast_ref::<Self>().map_or(false, |a| self == a)
+    }
+
+    /// Return self as Any for dynamic dispatch purposes
+    fn as_any(&self) -> &dyn Any {
+        self
+    }
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
@@ -419,4 +458,56 @@ mod tests {
 
         assert!(filter.should_filter_response(&resp));
     }
+
+    #[test]
+    /// a few simple tests for similarity filter
+    fn similarity_filter_is_accurate() {
+        let mut resp = FeroxResponse {
+            text: String::from("sitting"),
+            wildcard: false,
+            url: Url::parse("http://localhost/stuff").unwrap(),
+            content_length: 100,
+            word_count: 50,
+            line_count: 25,
+            headers: reqwest::header::HeaderMap::new(),
+            status: reqwest::StatusCode::OK,
+        };
+
+        let mut filter = SimilarityFilter {
+            text: FuzzyHash::new("kitten").to_string(),
+            threshold: 95,
+        };
+
+        // kitten/sitting is 57% similar, so a threshold of 95 should not be filtered
+        assert!(!filter.should_filter_response(&resp));
+
+        resp.text = String::new();
+        filter.text = String::new();
+        filter.threshold = 100;
+
+        // two empty strings are the same, however ssdeep doesn't accept empty strings, expect false
+        assert!(!filter.should_filter_response(&resp));
+
+        resp.text = String::from("some data to hash for the purposes of running a test");
+        filter.text =
+            FuzzyHash::new("some data to hash for the purposes of running a te").to_string();
+        filter.threshold = 17;
+
+        assert!(filter.should_filter_response(&resp));
+    }
+
+    #[test]
+    /// just a simple test to increase code coverage by hitting as_any and the inner value
+    fn similarity_filter_as_any() {
+        let filter = SimilarityFilter {
+            text: String::from("stuff"),
+            threshold: 95,
+        };
+
+        assert_eq!(filter.text, "stuff");
+        assert_eq!(
+            *filter.as_any().downcast_ref::<SimilarityFilter>().unwrap(),
+            filter
+        );
+    }
 }

src/heuristics.rs

@@ -2,6 +2,7 @@ use crate::{
     config::{CONFIGURATION, PROGRESS_PRINTER},
     filters::WildcardFilter,
     scanner::should_filter_response,
+    statistics::StatCommand,
     utils::{ferox_print, format_url, get_url_path_length, make_request, status_colorizer},
     FeroxResponse,
 };
@@ -40,12 +41,14 @@ pub async fn wildcard_test(
     target_url: &str,
     bar: ProgressBar,
     tx_term: UnboundedSender<FeroxResponse>,
+    tx_stats: UnboundedSender<StatCommand>,
 ) -> Option<WildcardFilter> {
     log::trace!(
-        "enter: wildcard_test({:?}, {:?}, {:?})",
+        "enter: wildcard_test({:?}, {:?}, {:?}, {:?})",
         target_url,
         bar,
-        tx_term
+        tx_term,
+        tx_stats
     );
 
     if CONFIGURATION.dont_filter {
@@ -54,10 +57,14 @@ pub async fn wildcard_test(
         return None;
     }
 
-    let tx_clone_one = tx_term.clone();
-    let tx_clone_two = tx_term.clone();
+    let tx_term_mwcr1 = tx_term.clone();
+    let tx_term_mwcr2 = tx_term.clone();
+    let tx_stats_mwcr1 = tx_stats.clone();
+    let tx_stats_mwcr2 = tx_stats.clone();
 
-    if let Some(ferox_response) = make_wildcard_request(&target_url, 1, tx_clone_one).await {
+    if let Some(ferox_response) =
+        make_wildcard_request(&target_url, 1, tx_term_mwcr1, tx_stats_mwcr1).await
+    {
         bar.inc(1);
 
         // found a wildcard response
@@ -72,7 +79,9 @@ 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, tx_clone_two).await {
+        if let Some(resp_two) =
+            make_wildcard_request(&target_url, 3, tx_term_mwcr2, tx_stats_mwcr2).await
+        {
             bar.inc(1);
 
             let wc2_length = resp_two.content_length();
@@ -138,12 +147,14 @@ async fn make_wildcard_request(
     target_url: &str,
     length: usize,
     tx_file: UnboundedSender<FeroxResponse>,
+    tx_stats: UnboundedSender<StatCommand>,
 ) -> Option<FeroxResponse> {
     log::trace!(
-        "enter: make_wildcard_request({}, {}, {:?})",
+        "enter: make_wildcard_request({}, {}, {:?}, {:?})",
         target_url,
         length,
-        tx_file
+        tx_file,
+        tx_stats,
     );
 
     let unique_str = unique_string(length);
@@ -154,6 +165,7 @@ async fn make_wildcard_request(
         CONFIGURATION.add_slash,
         &CONFIGURATION.queries,
         None,
+        tx_stats.clone(),
     ) {
         Ok(url) => url,
         Err(e) => {
@@ -163,7 +175,13 @@ async fn make_wildcard_request(
         }
     };
 
-    match make_request(&CONFIGURATION.client, &nonexistent.to_owned()).await {
+    match make_request(
+        &CONFIGURATION.client,
+        &nonexistent.to_owned(),
+        tx_stats.clone(),
+    )
+    .await
+    {
         Ok(response) => {
             if CONFIGURATION
                 .status_codes
@@ -174,7 +192,7 @@ async fn make_wildcard_request(
                 ferox_response.wildcard = true;
 
                 if !CONFIGURATION.quiet
-                    && !should_filter_response(&ferox_response)
+                    && !should_filter_response(&ferox_response, tx_stats.clone())
                     && tx_file.send(ferox_response.clone()).is_err()
                 {
                     return None;
@@ -190,6 +208,7 @@ async fn make_wildcard_request(
             return None;
         }
     }
+
     log::trace!("exit: make_wildcard_request -> None");
     None
 }
@@ -199,8 +218,15 @@ async fn make_wildcard_request(
 /// In the event that no sites can be reached, the program will exit.
 ///
 /// Any urls that are found to be alive are returned to the caller.
-pub async fn connectivity_test(target_urls: &[String]) -> Vec<String> {
-    log::trace!("enter: connectivity_test({:?})", target_urls);
+pub async fn connectivity_test(
+    target_urls: &[String],
+    tx_stats: UnboundedSender<StatCommand>,
+) -> Vec<String> {
+    log::trace!(
+        "enter: connectivity_test({:?}, {:?})",
+        target_urls,
+        tx_stats
+    );
 
     let mut good_urls = vec![];
 
@@ -211,6 +237,7 @@ pub async fn connectivity_test(target_urls: &[String]) -> Vec<String> {
             CONFIGURATION.add_slash,
             &CONFIGURATION.queries,
             None,
+            tx_stats.clone(),
         ) {
             Ok(url) => url,
             Err(e) => {
@@ -219,7 +246,7 @@ pub async fn connectivity_test(target_urls: &[String]) -> Vec<String> {
             }
         };
 
-        match make_request(&CONFIGURATION.client, &request).await {
+        match make_request(&CONFIGURATION.client, &request, tx_stats.clone()).await {
             Ok(_) => {
                 good_urls.push(target_url.to_owned());
             }

src/lib.rs

@@ -1,3 +1,4 @@
+pub mod utils;
 pub mod banner;
 pub mod client;
 pub mod config;
@@ -10,7 +11,7 @@ pub mod progress;
 pub mod reporter;
 pub mod scan_manager;
 pub mod scanner;
-pub mod utils;
+pub mod statistics;
 
 use crate::utils::{get_url_path_length, status_colorizer};
 use console::{style, Color};
@@ -51,6 +52,9 @@ pub const VERSION: &str = env!("CARGO_PKG_VERSION");
 /// Maximum number of file descriptors that can be opened during a scan
 pub const DEFAULT_OPEN_FILE_LIMIT: usize = 8192;
 
+/// Default value used to determine near-duplicate web pages (equivalent to 95%)
+pub const SIMILARITY_THRESHOLD: u32 = 95;
+
 /// Default wordlist to use when `-w|--wordlist` isn't specified and not `wordlist` isn't set
 /// in a [ferox-config.toml](constant.DEFAULT_CONFIG_NAME.html) config file.
 ///

src/main.rs

@@ -1,20 +1,29 @@
 use crossterm::event::{self, Event, KeyCode};
-use feroxbuster::progress::add_bar;
 use feroxbuster::{
     banner,
     config::{CONFIGURATION, PROGRESS_BAR, PROGRESS_PRINTER},
-    heuristics, logger, reporter,
+    extractor::{extract_robots_txt, request_feroxresponse_from_new_link},
+    heuristics, logger,
+    progress::{add_bar, BarType},
+    reporter,
     scan_manager::{self, PAUSE_SCAN},
-    scanner::{self, scan_url, RESPONSES, SCANNED_URLS},
+    scanner::{self, scan_url, send_report, RESPONSES, SCANNED_URLS},
+    statistics::{
+        self,
+        StatCommand::{self, CreateBar, LoadStats, UpdateUsizeField},
+        StatField::InitialTargets,
+        Stats,
+    },
+    update_stat,
     utils::{ferox_print, get_current_depth, module_colorizer, status_colorizer},
     FeroxError, FeroxResponse, FeroxResult, FeroxSerialize, SLEEP_DURATION, VERSION,
 };
 #[cfg(not(target_os = "windows"))]
 use feroxbuster::{utils::set_open_file_limit, DEFAULT_OPEN_FILE_LIMIT};
 use futures::StreamExt;
-use std::convert::TryInto;
 use std::{
     collections::HashSet,
+    convert::TryInto,
     fs::File,
     io::{stderr, BufRead, BufReader},
     process,
@@ -97,11 +106,20 @@ fn get_unique_words_from_wordlist(path: &str) -> FeroxResult<Arc<HashSet<String>
 
 /// Determine whether it's a single url scan or urls are coming from stdin, then scan as needed
 async fn scan(
-    targets: Vec<String>,
+    mut targets: Vec<String>,
+    stats: Arc<Stats>,
     tx_term: UnboundedSender<FeroxResponse>,
     tx_file: UnboundedSender<FeroxResponse>,
+    tx_stats: UnboundedSender<StatCommand>,
 ) -> FeroxResult<()> {
-    log::trace!("enter: scan({:?}, {:?}, {:?})", targets, tx_term, tx_file);
+    log::trace!(
+        "enter: scan({:?}, {:?}, {:?}, {:?}, {:?})",
+        targets,
+        stats,
+        tx_term,
+        tx_file,
+        tx_stats
+    );
     // cloning an Arc is cheap (it's basically a pointer into the heap)
     // so that will allow for cheap/safe sharing of a single wordlist across multi-target scans
     // as well as additional directories found as part of recursion
@@ -110,14 +128,32 @@ async fn scan(
             .await??;
 
     if words.len() == 0 {
-        let mut err = FeroxError::default();
-        err.message = format!("Did not find any words in {}", CONFIGURATION.wordlist);
+        let err = FeroxError {
+            message: format!("Did not find any words in {}", CONFIGURATION.wordlist),
+        };
+
         return Err(Box::new(err));
     }
 
-    scanner::initialize(words.len(), &CONFIGURATION);
+    scanner::initialize(words.len(), &CONFIGURATION, tx_stats.clone()).await;
+
+    // at this point, the stat thread's progress bar can be created; things that needed to happen
+    // first:
+    // - banner gets printed
+    // - scanner initialized (this sent expected requests per directory to the stats thread, which
+    //   having been set, makes it so the progress bar doesn't flash as full before anything has
+    //   even happened
+    update_stat!(tx_stats, CreateBar);
 
     if CONFIGURATION.resumed {
+        update_stat!(tx_stats, LoadStats(CONFIGURATION.resume_from.clone()));
+
+        if let Ok(responses) = RESPONSES.responses.read() {
+            for response in responses.iter() {
+                PROGRESS_PRINTER.println(response.as_str());
+            }
+        }
+
         if let Ok(scans) = SCANNED_URLS.scans.lock() {
             for scan in scans.iter() {
                 if let Ok(locked_scan) = scan.lock() {
@@ -126,18 +162,47 @@ async fn scan(
                         let pb = add_bar(
                             &locked_scan.url,
                             words.len().try_into().unwrap_or_default(),
-                            false,
-                            true,
+                            BarType::Message,
                         );
                         pb.finish();
                     }
                 }
             }
         }
+    }
 
-        if let Ok(responses) = RESPONSES.responses.read() {
-            for response in responses.iter() {
-                PROGRESS_PRINTER.println(response.as_str());
+    if CONFIGURATION.extract_links {
+        for target in targets.clone() {
+            // modifying the targets vector, so we can't have a reference to it while we borrow
+            // it as mutable; thus the clone
+            let robots_links = extract_robots_txt(&target, &CONFIGURATION, tx_stats.clone()).await;
+
+            for robot_link in robots_links {
+                // create a url based on the given command line options, continue on error
+                let ferox_response = match request_feroxresponse_from_new_link(
+                    &robot_link,
+                    tx_stats.clone(),
+                )
+                .await
+                {
+                    Some(resp) => resp,
+                    None => continue,
+                };
+
+                if ferox_response.is_file() {
+                    SCANNED_URLS.add_file_scan(&robot_link, stats.clone());
+                    send_report(tx_term.clone(), ferox_response);
+                } else {
+                    let (unknown, _) = SCANNED_URLS.add_directory_scan(&robot_link, stats.clone());
+
+                    if !unknown {
+                        // known directory; can skip (unlikely)
+                        continue;
+                    }
+
+                    // unknown directory; add to targets for scanning
+                    targets.push(robot_link);
+                }
             }
         }
     }
@@ -148,10 +213,21 @@ async fn scan(
         let word_clone = words.clone();
         let term_clone = tx_term.clone();
         let file_clone = tx_file.clone();
+        let tx_stats_clone = tx_stats.clone();
+        let stats_clone = stats.clone();
 
         let task = tokio::spawn(async move {
             let base_depth = get_current_depth(&target);
-            scan_url(&target, word_clone, base_depth, term_clone, file_clone).await;
+            scan_url(
+                &target,
+                word_clone,
+                base_depth,
+                stats_clone,
+                term_clone,
+                file_clone,
+                tx_stats_clone,
+            )
+            .await;
         });
 
         tasks.push(task);
@@ -220,11 +296,16 @@ async fn wrapped_main() {
         PROGRESS_BAR.join().unwrap();
     });
 
+    let (stats, tx_stats, stats_handle) = statistics::initialize();
+
     if !CONFIGURATION.time_limit.is_empty() {
         // --time-limit value not an empty string, need to kick off the thread that enforces
         // the limit
+
+        let max_time_stats = stats.clone();
+
         tokio::spawn(async move {
-            scan_manager::start_max_time_thread(&CONFIGURATION.time_limit).await
+            scan_manager::start_max_time_thread(&CONFIGURATION.time_limit, max_time_stats).await
         });
     }
 
@@ -238,8 +319,13 @@ async fn wrapped_main() {
 
     let save_output = !CONFIGURATION.output.is_empty(); // was -o used?
 
+    if CONFIGURATION.save_state {
+        // start the ctrl+c handler
+        scan_manager::initialize(stats.clone());
+    }
+
     let (tx_term, tx_file, term_handle, file_handle) =
-        reporter::initialize(&CONFIGURATION.output, save_output);
+        reporter::initialize(&CONFIGURATION.output, save_output, tx_stats.clone());
 
     // get targets from command line or stdin
     let targets = match get_targets().await {
@@ -247,27 +333,62 @@ async fn wrapped_main() {
         Err(e) => {
             // should only happen in the event that there was an error reading from stdin
             log::error!("{} {}", module_colorizer("main::get_targets"), e);
-            clean_up(tx_term, term_handle, tx_file, file_handle, save_output).await;
+            clean_up(
+                tx_term,
+                term_handle,
+                tx_file,
+                file_handle,
+                tx_stats,
+                stats_handle,
+                save_output,
+            )
+            .await;
             return;
         }
     };
 
+    update_stat!(tx_stats, UpdateUsizeField(InitialTargets, targets.len()));
+
     if !CONFIGURATION.quiet {
         // only print banner if -q isn't used
         let std_stderr = stderr(); // std::io::stderr
-        banner::initialize(&targets, &CONFIGURATION, &VERSION, std_stderr).await;
+        banner::initialize(
+            &targets,
+            &CONFIGURATION,
+            &VERSION,
+            std_stderr,
+            tx_stats.clone(),
+        )
+        .await;
     }
 
     // discard non-responsive targets
-    let live_targets = heuristics::connectivity_test(&targets).await;
+    let live_targets = heuristics::connectivity_test(&targets, tx_stats.clone()).await;
 
     if live_targets.is_empty() {
-        clean_up(tx_term, term_handle, tx_file, file_handle, save_output).await;
+        clean_up(
+            tx_term,
+            term_handle,
+            tx_file,
+            file_handle,
+            tx_stats,
+            stats_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 {
+    match scan(
+        live_targets,
+        stats,
+        tx_term.clone(),
+        tx_file.clone(),
+        tx_stats.clone(),
+    )
+    .await
+    {
         Ok(_) => {
             log::info!("All scans complete!");
         }
@@ -276,12 +397,30 @@ async fn wrapped_main() {
                 &format!("{} while scanning: {}", status_colorizer("Error"), e),
                 &PROGRESS_PRINTER,
             );
-            clean_up(tx_term, term_handle, tx_file, file_handle, save_output).await;
+            clean_up(
+                tx_term,
+                term_handle,
+                tx_file,
+                file_handle,
+                tx_stats,
+                stats_handle,
+                save_output,
+            )
+            .await;
             process::exit(1);
         }
     };
 
-    clean_up(tx_term, term_handle, tx_file, file_handle, save_output).await;
+    clean_up(
+        tx_term,
+        term_handle,
+        tx_file,
+        file_handle,
+        tx_stats,
+        stats_handle,
+        save_output,
+    )
+    .await;
 
     log::trace!("exit: main");
 }
@@ -293,14 +432,18 @@ async fn clean_up(
     term_handle: JoinHandle<()>,
     tx_file: UnboundedSender<FeroxResponse>,
     file_handle: Option<JoinHandle<()>>,
+    tx_stats: UnboundedSender<StatCommand>,
+    stats_handle: JoinHandle<()>,
     save_output: bool,
 ) {
     log::trace!(
-        "enter: clean_up({:?}, {:?}, {:?}, {:?}, {})",
+        "enter: clean_up({:?}, {:?}, {:?}, {:?}, {:?}, {:?}, {})",
         tx_term,
         term_handle,
         tx_file,
         file_handle,
+        tx_stats,
+        stats_handle,
         save_output
     );
 
@@ -335,6 +478,10 @@ async fn clean_up(
         log::trace!("done awaiting file output handler's receiver");
     }
 
+    log::trace!("tx_stats: {:?}", tx_stats);
+    update_stat!(tx_stats, StatCommand::Exit); // send exit command and await the end of the future
+    stats_handle.await.unwrap_or_default();
+
     // mark all scans complete so the terminal input handler will exit cleanly
     SCAN_COMPLETE.store(true, Ordering::Relaxed);
 
@@ -349,11 +496,6 @@ fn main() {
     // setup logging based on the number of -v's used
     logger::initialize(CONFIGURATION.verbosity);
 
-    if CONFIGURATION.save_state {
-        // start the ctrl+c handler
-        scan_manager::initialize();
-    }
-
     // this function uses rlimit, which is not supported on windows
     #[cfg(not(target_os = "windows"))]
     set_open_file_limit(DEFAULT_OPEN_FILE_LIMIT);

src/parser.rs

@@ -77,7 +77,7 @@ pub fn initialize() -> App<'static, 'static> {
                 .takes_value(true)
                 .value_name("PROXY")
                 .help(
-                    "Proxy to use for requests (ex: http(s)://host:port, socks5://host:port)",
+                    "Proxy to use for requests (ex: http(s)://host:port, socks5(h)://host:port)",
                 ),
         )
         .arg(
@@ -301,6 +301,17 @@ pub fn initialize() -> App<'static, 'static> {
                     "Filter out status codes (deny list) (ex: -C 200 -C 401)",
                 ),
         )
+        .arg(
+            Arg::with_name("filter_similar")
+                .long("filter-similar-to")
+                .value_name("UNWANTED_PAGE")
+                .takes_value(true)
+                .multiple(true)
+                .use_delimiter(true)
+                .help(
+                    "Filter out pages that are similar to the given page (ex. --filter-similar-to http://site.xyz/soft404)",
+                ),
+        )
         .arg(
             Arg::with_name("extract_links")
                 .short("e")

src/progress.rs

@@ -1,22 +1,42 @@
 use crate::config::{CONFIGURATION, PROGRESS_BAR};
 use indicatif::{ProgressBar, ProgressStyle};
 
+/// Types of ProgressBars that can be added to `PROGRESS_BAR`
+pub enum BarType {
+    /// no template used / not visible
+    Hidden,
+
+    /// normal directory status bar (reqs/sec shown)
+    Default,
+
+    /// similar to `Default`, except `-` is used in place of line/word/char count
+    Message,
+
+    /// bar used to show overall scan metrics
+    Total,
+}
+
 /// Add an [indicatif::ProgressBar](https://docs.rs/indicatif/latest/indicatif/struct.ProgressBar.html)
 /// to the global [PROGRESS_BAR](../config/struct.PROGRESS_BAR.html)
-pub fn add_bar(prefix: &str, length: u64, hidden: bool, hide_per_sec: bool) -> ProgressBar {
-    let style = if hidden || CONFIGURATION.quiet {
-        ProgressStyle::default_bar().template("")
-    } else if hide_per_sec {
-        ProgressStyle::default_bar()
-            .template(&format!(
+pub fn add_bar(prefix: &str, length: u64, bar_type: BarType) -> ProgressBar {
+    let mut style = ProgressStyle::default_bar().progress_chars("#>-");
+
+    style = if CONFIGURATION.quiet {
+        style.template("")
+    } else {
+        match bar_type {
+            BarType::Hidden => style.template(""),
+            BarType::Default => style.template(
+                "[{bar:.cyan/blue}] - {elapsed:<4} {pos:>7}/{len:7} {per_sec:7} {prefix}",
+            ),
+            BarType::Message => style.template(&format!(
                 "[{{bar:.cyan/blue}}] - {{elapsed:<4}} {{pos:>7}}/{{len:7}} {:7} {{prefix}}",
                 "-"
-            ))
-            .progress_chars("#>-")
-    } else {
-        ProgressStyle::default_bar()
-            .template("[{bar:.cyan/blue}] - {elapsed:<4} {pos:>7}/{len:7} {per_sec:7} {prefix}")
-            .progress_chars("#>-")
+            )),
+            BarType::Total => {
+                style.template("[{bar:.yellow/blue}] - {elapsed:<4} {pos:>7}/{len:7} {eta:7} {msg}")
+            }
+        }
     };
 
     let progress_bar = PROGRESS_BAR.add(ProgressBar::new(length));
@@ -35,16 +55,19 @@ mod tests {
     #[test]
     /// hit all code branches for add_bar
     fn add_bar_with_all_configurations() {
-        let p1 = add_bar("prefix", 2, true, false); // hidden
-        let p2 = add_bar("prefix", 2, false, true); // no per second field
-        let p3 = add_bar("prefix", 2, false, false); // normal bar
+        let p1 = add_bar("prefix", 2, BarType::Hidden); // hidden
+        let p2 = add_bar("prefix", 2, BarType::Message); // no per second field
+        let p3 = add_bar("prefix", 2, BarType::Default); // normal bar
+        let p4 = add_bar("prefix", 2, BarType::Total); // totals bar
 
         p1.finish();
         p2.finish();
         p3.finish();
+        p4.finish();
 
         assert!(p1.is_finished());
         assert!(p2.is_finished());
         assert!(p3.is_finished());
+        assert!(p4.is_finished());
     }
 }

src/reporter.rs

@@ -1,13 +1,19 @@
 use crate::{
     config::{CONFIGURATION, PROGRESS_PRINTER},
     scanner::RESPONSES,
+    statistics::{
+        StatCommand::{self, UpdateUsizeField},
+        StatField::ResourcesDiscovered,
+    },
     utils::{ferox_print, make_request, open_file},
     FeroxChannel, FeroxResponse, FeroxSerialize,
 };
 use console::strip_ansi_codes;
-use std::io::Write;
-use std::sync::{Arc, Once, RwLock};
-use std::{fs, io};
+use std::{
+    fs, io,
+    io::Write,
+    sync::{Arc, Once, RwLock},
+};
 use tokio::sync::mpsc::{self, UnboundedReceiver, UnboundedSender};
 use tokio::task::JoinHandle;
 
@@ -42,27 +48,35 @@ pub fn get_cached_file_handle(filename: &str) -> Option<Arc<RwLock<io::BufWriter
 pub fn initialize(
     output_file: &str,
     save_output: bool,
+    tx_stats: UnboundedSender<StatCommand>,
 ) -> (
     UnboundedSender<FeroxResponse>,
     UnboundedSender<FeroxResponse>,
     JoinHandle<()>,
     Option<JoinHandle<()>>,
 ) {
-    log::trace!("enter: initialize({}, {})", output_file, save_output);
+    log::trace!(
+        "enter: initialize({}, {}, {:?})",
+        output_file,
+        save_output,
+        tx_stats
+    );
 
     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();
+    let stats_clone = tx_stats.clone();
 
-    let term_reporter =
-        tokio::spawn(async move { spawn_terminal_reporter(rx_rpt, file_clone, save_output).await });
+    let term_reporter = tokio::spawn(async move {
+        spawn_terminal_reporter(rx_rpt, file_clone, stats_clone, save_output).await
+    });
 
     let file_reporter = if save_output {
         // -o used, need to spawn the thread for writing to disk
         let file_clone = output_file.to_string();
         Some(tokio::spawn(async move {
-            spawn_file_reporter(rx_file, &file_clone).await
+            spawn_file_reporter(rx_file, tx_stats, &file_clone).await
         }))
     } else {
         None
@@ -85,12 +99,14 @@ pub fn initialize(
 async fn spawn_terminal_reporter(
     mut resp_chan: UnboundedReceiver<FeroxResponse>,
     file_chan: UnboundedSender<FeroxResponse>,
+    tx_stats: UnboundedSender<StatCommand>,
     save_output: bool,
 ) {
     log::trace!(
-        "enter: spawn_terminal_reporter({:?}, {:?}, {})",
+        "enter: spawn_terminal_reporter({:?}, {:?}, {:?}, {})",
         resp_chan,
         file_chan,
+        tx_stats,
         save_output
     );
 
@@ -105,6 +121,8 @@ async fn spawn_terminal_reporter(
             // print to stdout
             ferox_print(&resp.as_str(), &PROGRESS_PRINTER);
 
+            update_stat!(tx_stats, UpdateUsizeField(ResourcesDiscovered, 1));
+
             if save_output {
                 // -o used, need to send the report to be written out to disk
                 match file_chan.send(resp.clone()) {
@@ -122,7 +140,13 @@ async fn spawn_terminal_reporter(
         if CONFIGURATION.replay_client.is_some() && should_process_response {
             // replay proxy specified/client created and this response's status code is one that
             // should be replayed
-            match make_request(CONFIGURATION.replay_client.as_ref().unwrap(), &resp.url()).await {
+            match make_request(
+                CONFIGURATION.replay_client.as_ref().unwrap(),
+                &resp.url(),
+                tx_stats.clone(),
+            )
+            .await
+            {
                 Ok(_) => {}
                 Err(e) => {
                     log::error!("{}", e);
@@ -151,6 +175,7 @@ async fn spawn_terminal_reporter(
 /// the given reporting criteria
 async fn spawn_file_reporter(
     mut report_channel: UnboundedReceiver<FeroxResponse>,
+    tx_stats: UnboundedSender<StatCommand>,
     output_file: &str,
 ) {
     let buffered_file = match get_cached_file_handle(&CONFIGURATION.output) {
@@ -173,6 +198,8 @@ async fn spawn_file_reporter(
         safe_file_write(&response, buffered_file.clone(), CONFIGURATION.json);
     }
 
+    update_stat!(tx_stats, StatCommand::Save);
+
     log::trace!("exit: spawn_file_reporter");
 }
 

src/scan_manager.rs

@@ -1,11 +1,11 @@
-use crate::config::Configuration;
-use crate::reporter::safe_file_write;
-use crate::utils::open_file;
 use crate::{
-    config::{CONFIGURATION, PROGRESS_PRINTER},
+    config::{Configuration, CONFIGURATION, PROGRESS_PRINTER},
     parser::TIMESPEC_REGEX,
-    progress,
-    scanner::{NUMBER_OF_REQUESTS, RESPONSES, SCANNED_URLS},
+    progress::{add_bar, BarType},
+    reporter::safe_file_write,
+    scanner::{RESPONSES, SCANNED_URLS},
+    statistics::Stats,
+    utils::open_file,
     FeroxResponse, FeroxSerialize, SLEEP_DURATION,
 };
 use console::style;
@@ -16,18 +16,16 @@ use serde::{
     Deserialize, Deserializer, Serialize, Serializer,
 };
 use serde_json::Value;
-use std::collections::HashMap;
 use std::{
     cmp::PartialEq,
+    collections::HashMap,
     fmt,
     fs::File,
     io::BufReader,
-    sync::{Arc, Mutex, RwLock},
-    time::{SystemTime, UNIX_EPOCH},
-};
-use std::{
     io::{stderr, Write},
     sync::atomic::{AtomicBool, AtomicUsize, Ordering},
+    sync::{Arc, Mutex, RwLock},
+    time::{SystemTime, UNIX_EPOCH},
 };
 use tokio::{task::JoinHandle, time};
 use uuid::Uuid;
@@ -75,6 +73,9 @@ pub struct FeroxScan {
     /// The type of scan
     pub scan_type: ScanType,
 
+    /// Number of requests to populate the progress bar with
+    pub num_requests: u64,
+
     /// Whether or not this scan has completed
     pub complete: bool,
 
@@ -95,6 +96,7 @@ impl Default for FeroxScan {
             id: new_id,
             task: None,
             complete: false,
+            num_requests: 0,
             url: String::new(),
             progress_bar: None,
             scan_type: ScanType::File,
@@ -125,8 +127,7 @@ impl FeroxScan {
         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, false);
+            let pb = add_bar(&self.url, self.num_requests, BarType::Default);
 
             pb.reset_elapsed();
 
@@ -137,14 +138,19 @@ impl FeroxScan {
     }
 
     /// 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))
+    pub fn new(
+        url: &str,
+        scan_type: ScanType,
+        num_requests: u64,
+        pb: Option<ProgressBar>,
+    ) -> Arc<Mutex<Self>> {
+        Arc::new(Mutex::new(Self {
+            url: url.to_string(),
+            scan_type,
+            num_requests,
+            progress_bar: pb,
+            ..Default::default()
+        }))
     }
 
     /// Mark the scan as complete and stop the scan's progress bar
@@ -187,6 +193,7 @@ impl Serialize for FeroxScan {
         state.serialize_field("url", &self.url)?;
         state.serialize_field("scan_type", &self.scan_type)?;
         state.serialize_field("complete", &self.complete)?;
+        state.serialize_field("num_requests", &self.num_requests)?;
 
         state.end()
     }
@@ -229,6 +236,11 @@ impl<'de> Deserialize<'de> for FeroxScan {
                         scan.url = url.to_string();
                     }
                 }
+                "num_requests" => {
+                    if let Some(num_requests) = value.as_u64() {
+                        scan.num_requests = num_requests;
+                    }
+                }
                 _ => {}
             }
         }
@@ -438,15 +450,17 @@ impl 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>>) {
+    fn add_scan(
+        &self,
+        url: &str,
+        scan_type: ScanType,
+        stats: Arc<Stats>,
+    ) -> (bool, Arc<Mutex<FeroxScan>>) {
+        let num_requests = stats.expected_per_scan.load(Ordering::Relaxed) as u64;
+
         let bar = match scan_type {
             ScanType::Directory => {
-                let progress_bar = progress::add_bar(
-                    &url,
-                    NUMBER_OF_REQUESTS.load(Ordering::Relaxed),
-                    false,
-                    false,
-                );
+                let progress_bar = add_bar(&url, num_requests, BarType::Default);
 
                 progress_bar.reset_elapsed();
 
@@ -455,7 +469,7 @@ impl FeroxScans {
             ScanType::File => None,
         };
 
-        let ferox_scan = FeroxScan::new(&url, scan_type, bar);
+        let ferox_scan = FeroxScan::new(&url, scan_type, num_requests, bar);
 
         // If the set did not contain the scan, true is returned.
         // If the set did contain the scan, false is returned.
@@ -469,8 +483,12 @@ impl FeroxScans {
     /// 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)
+    pub fn add_directory_scan(
+        &self,
+        url: &str,
+        stats: Arc<Stats>,
+    ) -> (bool, Arc<Mutex<FeroxScan>>) {
+        self.add_scan(&url, ScanType::Directory, stats)
     }
 
     /// Given a url, create a new `FeroxScan` and add it to `FeroxScans` as a File Scan
@@ -478,8 +496,8 @@ impl FeroxScans {
     /// 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)
+    pub fn add_file_scan(&self, url: &str, stats: Arc<Stats>) -> (bool, Arc<Mutex<FeroxScan>>) {
+        self.add_scan(&url, ScanType::File, stats)
     }
 }
 
@@ -575,6 +593,9 @@ pub struct FeroxState {
 
     /// Known responses
     responses: &'static FeroxResponses,
+
+    /// Gathered statistics
+    statistics: Arc<Stats>,
 }
 
 /// FeroxSerialize implementation for FeroxState
@@ -594,7 +615,7 @@ impl FeroxSerialize for FeroxState {
 /// that representation to seconds and then wait for those seconds to elapse.  Once that period
 /// of time has elapsed, kill all currently running scans and dump a state file to disk that can
 /// be used to resume any unfinished scan.
-pub async fn start_max_time_thread(time_spec: &str) {
+pub async fn start_max_time_thread(time_spec: &str, stats: Arc<Stats>) {
     log::trace!("enter: start_max_time_thread({})", time_spec);
 
     // as this function has already made it through the parser, which calls is_match on
@@ -624,9 +645,9 @@ pub async fn start_max_time_thread(time_spec: &str) {
         log::trace!("exit: start_max_time_thread");
 
         #[cfg(test)]
-        panic!();
+        panic!(stats);
         #[cfg(not(test))]
-        sigint_handler();
+        sigint_handler(stats);
     }
 
     log::error!(
@@ -636,8 +657,8 @@ pub async fn start_max_time_thread(time_spec: &str) {
 }
 
 /// Writes the current state of the program to disk (if save_state is true) and then exits
-fn sigint_handler() {
-    log::trace!("enter: sigint_handler");
+fn sigint_handler(stats: Arc<Stats>) {
+    log::trace!("enter: sigint_handler({:?})", stats);
 
     let ts = SystemTime::now()
         .duration_since(UNIX_EPOCH)
@@ -669,6 +690,7 @@ fn sigint_handler() {
         config: &CONFIGURATION,
         scans: &SCANNED_URLS,
         responses: &RESPONSES,
+        statistics: stats,
     };
 
     let state_file = open_file(&filename);
@@ -682,10 +704,12 @@ fn sigint_handler() {
 }
 
 /// Initialize the ctrl+c handler that saves scan state to disk
-pub fn initialize() {
-    log::trace!("enter: initialize");
+pub fn initialize(stats: Arc<Stats>) {
+    log::trace!("enter: initialize({:?})", stats);
 
-    let result = ctrlc::set_handler(sigint_handler);
+    let result = ctrlc::set_handler(move || {
+        sigint_handler(stats.clone());
+    });
 
     if result.is_err() {
         log::error!("Could not set Ctrl+c handler");
@@ -795,8 +819,9 @@ mod tests {
     /// 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 stats = Arc::new(Stats::new());
         let url = "http://unknown_url";
-        let (result, _scan) = urls.add_scan(url, ScanType::Directory);
+        let (result, _scan) = urls.add_scan(url, ScanType::Directory, stats);
         assert_eq!(result, true);
     }
 
@@ -806,11 +831,13 @@ mod tests {
         let urls = FeroxScans::default();
         let pb = ProgressBar::new(1);
         let url = "http://unknown_url/";
-        let scan = FeroxScan::new(url, ScanType::Directory, Some(pb));
+        let stats = Arc::new(Stats::new());
+
+        let scan = FeroxScan::new(url, ScanType::Directory, pb.length(), Some(pb));
 
         assert_eq!(urls.insert(scan), true);
 
-        let (result, _scan) = urls.add_scan(url, ScanType::Directory);
+        let (result, _scan) = urls.add_scan(url, ScanType::Directory, stats);
 
         assert_eq!(result, false);
     }
@@ -820,7 +847,8 @@ mod tests {
     fn abort_stops_progress_bar() {
         let pb = ProgressBar::new(1);
         let url = "http://unknown_url/";
-        let scan = FeroxScan::new(url, ScanType::Directory, Some(pb));
+
+        let scan = FeroxScan::new(url, ScanType::Directory, pb.length(), Some(pb));
 
         assert_eq!(
             scan.lock()
@@ -850,11 +878,13 @@ mod tests {
     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);
+        let stats = Arc::new(Stats::new());
+
+        let scan = FeroxScan::new(url, ScanType::File, 0, None);
 
         assert_eq!(urls.insert(scan), true);
 
-        let (result, _scan) = urls.add_scan(url, ScanType::File);
+        let (result, _scan) = urls.add_scan(url, ScanType::File, stats);
 
         assert_eq!(result, false);
     }
@@ -867,8 +897,8 @@ mod tests {
         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));
+        let scan = FeroxScan::new(url, ScanType::Directory, pb.length(), Some(pb));
+        let scan_two = FeroxScan::new(url_two, ScanType::Directory, pb_two.length(), Some(pb_two));
 
         scan_two.lock().unwrap().finish(); // one complete, one incomplete
 
@@ -881,8 +911,8 @@ mod tests {
     /// 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);
+        let scan = FeroxScan::new(url, ScanType::Directory, 0, None);
+        let scan_two = FeroxScan::new(url, ScanType::Directory, 0, None);
 
         assert!(!scan.lock().unwrap().eq(&scan_two.lock().unwrap()));
 
@@ -941,9 +971,9 @@ mod tests {
     #[test]
     /// given a FeroxScan, test that it serializes into the proper JSON entry
     fn ferox_scan_serialize() {
-        let fs = FeroxScan::new("https://spiritanimal.com", ScanType::Directory, None);
+        let fs = FeroxScan::new("https://spiritanimal.com", ScanType::Directory, 0, None);
         let fs_json = format!(
-            r#"{{"id":"{}","url":"https://spiritanimal.com","scan_type":"Directory","complete":false}}"#,
+            r#"{{"id":"{}","url":"https://spiritanimal.com","scan_type":"Directory","complete":false,"num_requests":0}}"#,
             fs.lock().unwrap().id
         );
         assert_eq!(
@@ -955,10 +985,10 @@ mod tests {
     #[test]
     /// given a FeroxScans, test that it serializes into the proper JSON entry
     fn ferox_scans_serialize() {
-        let ferox_scan = FeroxScan::new("https://spiritanimal.com", ScanType::Directory, None);
+        let ferox_scan = FeroxScan::new("https://spiritanimal.com", ScanType::Directory, 0, None);
         let ferox_scans = FeroxScans::default();
         let ferox_scans_json = format!(
-            r#"[{{"id":"{}","url":"https://spiritanimal.com","scan_type":"Directory","complete":false}}]"#,
+            r#"[{{"id":"{}","url":"https://spiritanimal.com","scan_type":"Directory","complete":false,"num_requests":0}}]"#,
             ferox_scan.lock().unwrap().id
         );
         ferox_scans.scans.lock().unwrap().push(ferox_scan);
@@ -1009,10 +1039,12 @@ mod tests {
     #[test]
     /// test FeroxSerialize implementation of FeroxState
     fn feroxstates_feroxserialize_implementation() {
-        let ferox_scan = FeroxScan::new("https://spiritanimal.com", ScanType::Directory, None);
+        let ferox_scan = FeroxScan::new("https://spiritanimal.com", ScanType::Directory, 0, None);
         let saved_id = ferox_scan.lock().unwrap().id.clone();
         SCANNED_URLS.insert(ferox_scan);
 
+        let stats = Arc::new(Stats::new());
+
         let json_response = r#"{"type":"response","url":"https://nerdcore.com/css","path":"/css","wildcard":true,"status":301,"content_length":173,"line_count":10,"word_count":16,"headers":{"server":"nginx/1.16.1"}}"#;
         let response: FeroxResponse = serde_json::from_str(json_response).unwrap();
         RESPONSES.insert(response);
@@ -1021,6 +1053,7 @@ mod tests {
             scans: &SCANNED_URLS,
             responses: &RESPONSES,
             config: &CONFIGURATION,
+            statistics: stats,
         };
 
         let expected_strs = predicates::str::contains("scans: FeroxScans").and(
@@ -1035,11 +1068,11 @@ mod tests {
 
         let json_state = ferox_state.as_json();
         let expected = format!(
-            r#"{{"scans":[{{"id":"{}","url":"https://spiritanimal.com","scan_type":"Directory","complete":false}}],"config":{{"type":"configuration","wordlist":"/usr/share/seclists/Discovery/Web-Content/raft-medium-directories.txt","config":"","proxy":"","replay_proxy":"","target_url":"","status_codes":[200,204,301,302,307,308,401,403,405],"replay_codes":[200,204,301,302,307,308,401,403,405],"filter_status":[],"threads":50,"timeout":7,"verbosity":0,"quiet":false,"json":false,"output":"","debug_log":"","user_agent":"feroxbuster/{}","redirects":false,"insecure":false,"extensions":[],"headers":{{}},"queries":[],"no_recursion":false,"extract_links":false,"add_slash":false,"stdin":false,"depth":4,"scan_limit":0,"filter_size":[],"filter_line_count":[],"filter_word_count":[],"filter_regex":[],"dont_filter":false,"resumed":false,"save_state":false,"time_limit":""}},"responses":[{{"type":"response","url":"https://nerdcore.com/css","path":"/css","wildcard":true,"status":301,"content_length":173,"line_count":10,"word_count":16,"headers":{{"server":"nginx/1.16.1"}}}}]}}"#,
+            r#"{{"scans":[{{"id":"{}","url":"https://spiritanimal.com","scan_type":"Directory","complete":false,"num_requests":0}}],"config":{{"type":"configuration","wordlist":"/usr/share/seclists/Discovery/Web-Content/raft-medium-directories.txt","config":"","proxy":"","replay_proxy":"","target_url":"","status_codes":[200,204,301,302,307,308,401,403,405],"replay_codes":[200,204,301,302,307,308,401,403,405],"filter_status":[],"threads":50,"timeout":7,"verbosity":0,"quiet":false,"json":false,"output":"","debug_log":"","user_agent":"feroxbuster/{}","redirects":false,"insecure":false,"extensions":[],"headers":{{}},"queries":[],"no_recursion":false,"extract_links":false,"add_slash":false,"stdin":false,"depth":4,"scan_limit":0,"filter_size":[],"filter_line_count":[],"filter_word_count":[],"filter_regex":[],"dont_filter":false,"resumed":false,"resume_from":"","save_state":false,"time_limit":"","filter_similar":[]}},"responses":[{{"type":"response","url":"https://nerdcore.com/css","path":"/css","wildcard":true,"status":301,"content_length":173,"line_count":10,"word_count":16,"headers":{{"server":"nginx/1.16.1"}}}}]"#,
             saved_id, VERSION
         );
-
-        assert!(predicates::str::similar(expected).eval(&json_state));
+        println!("{}\n{}", expected, json_state);
+        assert!(predicates::str::contains(expected).eval(&json_state));
     }
 
     #[should_panic]
@@ -1049,8 +1082,9 @@ mod tests {
     async fn start_max_time_thread_panics_after_delay() {
         let now = time::Instant::now();
         let delay = time::Duration::new(3, 0);
+        let stats = Arc::new(Stats::new());
 
-        start_max_time_thread("3s").await;
+        start_max_time_thread("3s", stats).await;
 
         assert!(now.elapsed() > delay);
     }
@@ -1061,9 +1095,10 @@ mod tests {
     async fn start_max_time_thread_returns_immediately_with_too_large_input() {
         let now = time::Instant::now();
         let delay = time::Duration::new(1, 0);
+        let stats = Arc::new(Stats::new());
 
         // pub const MAX: usize = usize::MAX; // 18_446_744_073_709_551_615usize
-        start_max_time_thread("18446744073709551616m").await; // can't fit in dest u64
+        start_max_time_thread("18446744073709551616m", stats).await; // can't fit in dest u64
 
         assert!(now.elapsed() < delay); // assuming function call will take less than 1second
     }

src/scanner.rs

@@ -1,19 +1,25 @@
+use crate::statistics::Stats;
 use crate::{
     config::{Configuration, CONFIGURATION},
-    extractor::get_links,
+    extractor::{get_links, request_feroxresponse_from_new_link},
     filters::{
-        FeroxFilter, LinesFilter, RegexFilter, SizeFilter, StatusCodeFilter, WildcardFilter,
-        WordsFilter,
+        FeroxFilter, LinesFilter, RegexFilter, SimilarityFilter, SizeFilter, StatusCodeFilter,
+        WildcardFilter, WordsFilter,
     },
     heuristics,
     scan_manager::{FeroxResponses, FeroxScans, PAUSE_SCAN},
+    statistics::{
+        StatCommand::{self, UpdateF64Field, UpdateUsizeField},
+        StatField::{DirScanTimes, ExpectedPerScan, TotalScans, WildcardsFiltered},
+    },
     utils::{format_url, get_current_depth, make_request},
-    FeroxChannel, FeroxResponse,
+    FeroxChannel, FeroxResponse, SIMILARITY_THRESHOLD,
 };
 use futures::{
     future::{BoxFuture, FutureExt},
     stream, StreamExt,
 };
+use fuzzyhash::FuzzyHash;
 use lazy_static::lazy_static;
 use regex::Regex;
 use reqwest::Url;
@@ -23,8 +29,9 @@ use std::{
     collections::HashSet,
     convert::TryInto,
     ops::Deref,
-    sync::atomic::{AtomicU64, AtomicUsize, Ordering},
+    sync::atomic::{AtomicUsize, Ordering},
     sync::{Arc, RwLock},
+    time::Instant,
 };
 use tokio::{
     sync::{
@@ -34,12 +41,13 @@ use tokio::{
     task::JoinHandle,
 };
 
-/// Single atomic number that gets incremented once, used to track first scan vs. all others
+/// Single atomic number that gets incremented at least once, used to track first scan(s) vs. all
+/// others found during recursion
+///
+/// -u means this will be incremented once
+/// --stdin means this will be incremented by the number of targets passed via STDIN
 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
     pub static ref SCANNED_URLS: FeroxScans = FeroxScans::default();
@@ -97,33 +105,41 @@ fn spawn_recursion_handler(
     mut recursion_channel: UnboundedReceiver<String>,
     wordlist: Arc<HashSet<String>>,
     base_depth: usize,
+    stats: Arc<Stats>,
     tx_term: UnboundedSender<FeroxResponse>,
     tx_file: UnboundedSender<FeroxResponse>,
+    tx_stats: UnboundedSender<StatCommand>,
 ) -> BoxFuture<'static, Vec<JoinHandle<()>>> {
     log::trace!(
-        "enter: spawn_recursion_handler({:?}, wordlist[{} words...], {}, {:?}, {:?})",
+        "enter: spawn_recursion_handler({:?}, wordlist[{} words...], {}, {:?}, {:?}, {:?}, {:?})",
         recursion_channel,
         wordlist.len(),
         base_depth,
+        stats,
         tx_term,
-        tx_file
+        tx_file,
+        tx_stats
     );
 
     let boxed_future = async move {
         let mut scans = vec![];
 
         while let Some(resp) = recursion_channel.recv().await {
-            let (unknown, _) = SCANNED_URLS.add_directory_scan(&resp);
+            let (unknown, _) = SCANNED_URLS.add_directory_scan(&resp, stats.clone());
 
             if !unknown {
                 // not unknown, i.e. we've seen the url before and don't need to scan again
                 continue;
             }
 
+            update_stat!(tx_stats, UpdateUsizeField(TotalScans, 1));
+
             log::info!("received {} on recursion channel", resp);
 
             let term_clone = tx_term.clone();
             let file_clone = tx_file.clone();
+            let tx_stats_clone = tx_stats.clone();
+            let stats_clone = stats.clone();
             let resp_clone = resp.clone();
             let list_clone = wordlist.clone();
 
@@ -132,8 +148,10 @@ fn spawn_recursion_handler(
                     resp_clone.to_owned().as_str(),
                     list_clone,
                     base_depth,
+                    stats_clone,
                     term_clone,
                     file_clone,
+                    tx_stats_clone,
                 )
                 .await
             });
@@ -154,12 +172,18 @@ fn spawn_recursion_handler(
 ///
 /// If any extensions were passed to the program, each extension will add a
 /// (base_url + word + ext) Url to the vector
-fn create_urls(target_url: &str, word: &str, extensions: &[String]) -> Vec<Url> {
+fn create_urls(
+    target_url: &str,
+    word: &str,
+    extensions: &[String],
+    tx_stats: UnboundedSender<StatCommand>,
+) -> Vec<Url> {
     log::trace!(
-        "enter: create_urls({}, {}, {:?})",
+        "enter: create_urls({}, {}, {:?}, {:?})",
         target_url,
         word,
-        extensions
+        extensions,
+        tx_stats
     );
 
     let mut urls = vec![];
@@ -170,6 +194,7 @@ fn create_urls(target_url: &str, word: &str, extensions: &[String]) -> Vec<Url>
         CONFIGURATION.add_slash,
         &CONFIGURATION.queries,
         None,
+        tx_stats.clone(),
     ) {
         urls.push(url); // default request, i.e. no extension
     }
@@ -181,6 +206,7 @@ fn create_urls(target_url: &str, word: &str, extensions: &[String]) -> Vec<Url>
             CONFIGURATION.add_slash,
             &CONFIGURATION.queries,
             Some(ext),
+            tx_stats.clone(),
         ) {
             urls.push(url); // any extensions passed in
         }
@@ -280,7 +306,7 @@ async fn try_recursion(
         "enter: try_recursion({}, {}, {:?})",
         response,
         base_depth,
-        transmitter
+        transmitter,
     );
 
     if !reached_max_depth(response.url(), base_depth, CONFIGURATION.depth)
@@ -324,12 +350,18 @@ async fn 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 {
+pub fn should_filter_response(
+    response: &FeroxResponse,
+    tx_stats: UnboundedSender<StatCommand>,
+) -> bool {
     match FILTERS.read() {
         Ok(filters) => {
             for filter in filters.iter() {
                 // wildcard.should_filter goes here
                 if filter.should_filter_response(&response) {
+                    if filter.as_any().downcast_ref::<WildcardFilter>().is_some() {
+                        update_stat!(tx_stats, UpdateUsizeField(WildcardsFiltered, 1))
+                    }
                     return true;
                 }
             }
@@ -350,22 +382,31 @@ async fn make_requests(
     target_url: &str,
     word: &str,
     base_depth: usize,
+    stats: Arc<Stats>,
     dir_chan: UnboundedSender<String>,
     report_chan: UnboundedSender<FeroxResponse>,
+    tx_stats: UnboundedSender<StatCommand>,
 ) {
     log::trace!(
-        "enter: make_requests({}, {}, {}, {:?}, {:?})",
+        "enter: make_requests({}, {}, {}, {:?}, {:?}, {:?}, {:?})",
         target_url,
         word,
         base_depth,
+        stats,
         dir_chan,
-        report_chan
+        report_chan,
+        tx_stats
     );
 
-    let urls = create_urls(&target_url, &word, &CONFIGURATION.extensions);
+    let urls = create_urls(
+        &target_url,
+        &word,
+        &CONFIGURATION.extensions,
+        tx_stats.clone(),
+    );
 
     for url in urls {
-        if let Ok(response) = make_request(&CONFIGURATION.client, &url).await {
+        if let Ok(response) = make_request(&CONFIGURATION.client, &url, tx_stats.clone()).await {
             // response came back without error, convert it to FeroxResponse
             let ferox_response = FeroxResponse::from(response, true).await;
 
@@ -377,41 +418,26 @@ async fn make_requests(
             // purposefully doing recursion before filtering. the thought process is that
             // even though this particular url is filtered, subsequent urls may not
 
-            if should_filter_response(&ferox_response) {
+            if should_filter_response(&ferox_response, tx_stats.clone()) {
                 continue;
             }
 
             if CONFIGURATION.extract_links && !ferox_response.status().is_redirection() {
-                let new_links = get_links(&ferox_response).await;
+                let new_links = get_links(&ferox_response, tx_stats.clone()).await;
 
                 for new_link in new_links {
-                    // create a url based on the given command line options, continue on error
-                    let new_url = match format_url(
+                    let mut new_ferox_response = match request_feroxresponse_from_new_link(
                         &new_link,
-                        &"",
-                        CONFIGURATION.add_slash,
-                        &CONFIGURATION.queries,
-                        None,
-                    ) {
-                        Ok(url) => url,
-                        Err(_) => continue,
+                        tx_stats.clone(),
+                    )
+                    .await
+                    {
+                        Some(resp) => resp,
+                        None => continue,
                     };
 
-                    if SCANNED_URLS.get_scan_by_url(&new_url.to_string()).is_some() {
-                        //we've seen the url before and don't need to scan again
-                        continue;
-                    }
-
-                    // make the request and store the response
-                    let new_response = match make_request(&CONFIGURATION.client, &new_url).await {
-                        Ok(resp) => resp,
-                        Err(_) => continue,
-                    };
-
-                    let mut new_ferox_response = FeroxResponse::from(new_response, true).await;
-
                     // filter if necessary
-                    if should_filter_response(&new_ferox_response) {
+                    if should_filter_response(&new_ferox_response, tx_stats.clone()) {
                         continue;
                     }
 
@@ -419,7 +445,8 @@ async fn make_requests(
                         // very likely a file, simply request and report
                         log::debug!("Singular extraction: {}", new_ferox_response);
 
-                        SCANNED_URLS.add_file_scan(&new_url.to_string());
+                        SCANNED_URLS
+                            .add_file_scan(&new_ferox_response.url().to_string(), stats.clone());
 
                         send_report(report_chan.clone(), new_ferox_response);
 
@@ -452,7 +479,7 @@ async fn make_requests(
 }
 
 /// Simple helper to send a `FeroxResponse` over the tx side of an `mpsc::unbounded_channel`
-fn send_report(report_sender: UnboundedSender<FeroxResponse>, response: FeroxResponse) {
+pub fn send_report(report_sender: UnboundedSender<FeroxResponse>, response: FeroxResponse) {
     log::trace!("enter: send_report({:?}, {}", report_sender, response);
 
     match report_sender.send(response) {
@@ -472,28 +499,36 @@ pub async fn scan_url(
     target_url: &str,
     wordlist: Arc<HashSet<String>>,
     base_depth: usize,
+    stats: Arc<Stats>,
     tx_term: UnboundedSender<FeroxResponse>,
     tx_file: UnboundedSender<FeroxResponse>,
+    tx_stats: UnboundedSender<StatCommand>,
 ) {
     log::trace!(
-        "enter: scan_url({:?}, wordlist[{} words...], {}, {:?}, {:?})",
+        "enter: scan_url({:?}, wordlist[{} words...], {}, {:?}, {:?}, {:?}, {:?})",
         target_url,
         wordlist.len(),
         base_depth,
+        stats,
         tx_term,
-        tx_file
+        tx_file,
+        tx_stats
     );
 
     log::info!("Starting scan against: {}", target_url);
 
+    let scan_timer = Instant::now();
+
     let (tx_dir, rx_dir): FeroxChannel<String> = mpsc::unbounded_channel();
 
-    if CALL_COUNT.load(Ordering::Relaxed) == 0 {
+    if CALL_COUNT.load(Ordering::Relaxed) < stats.initial_targets.load(Ordering::Relaxed) {
         CALL_COUNT.fetch_add(1, Ordering::Relaxed);
 
+        update_stat!(tx_stats, UpdateUsizeField(TotalScans, 1));
+
         // this protection allows us to add the first scanned url to SCANNED_URLS
         // from within the scan_url function instead of the recursion handler
-        SCANNED_URLS.add_directory_scan(&target_url);
+        SCANNED_URLS.add_directory_scan(&target_url, stats.clone());
     }
 
     let ferox_scan = match SCANNED_URLS.get_scan_by_url(&target_url) {
@@ -524,28 +559,39 @@ pub async fn scan_url(
     // Arc clones to be passed around to the various scans
     let wildcard_bar = progress_bar.clone();
     let heuristics_term_clone = tx_term.clone();
+    let heuristics_stats_clone = tx_stats.clone();
     let recurser_term_clone = tx_term.clone();
     let recurser_file_clone = tx_file.clone();
+    let recurser_stats_clone = tx_stats.clone();
     let recurser_words = wordlist.clone();
     let looping_words = wordlist.clone();
+    let looping_stats = stats.clone();
 
     let recurser = tokio::spawn(async move {
         spawn_recursion_handler(
             rx_dir,
             recurser_words,
             base_depth,
+            stats.clone(),
             recurser_term_clone,
             recurser_file_clone,
+            recurser_stats_clone,
         )
         .await
     });
 
     // add any wildcard filters to `FILTERS`
-    let filter =
-        match heuristics::wildcard_test(&target_url, wildcard_bar, heuristics_term_clone).await {
-            Some(f) => Box::new(f),
-            None => Box::new(WildcardFilter::default()),
-        };
+    let filter = match heuristics::wildcard_test(
+        &target_url,
+        wildcard_bar,
+        heuristics_term_clone,
+        heuristics_stats_clone,
+    )
+    .await
+    {
+        Some(f) => Box::new(f),
+        None => Box::new(WildcardFilter::default()),
+    };
 
     add_filter_to_list_of_ferox_filters(filter, FILTERS.clone());
 
@@ -554,8 +600,10 @@ pub async fn scan_url(
         .map(|word| {
             let txd = tx_dir.clone();
             let txr = tx_term.clone();
+            let txs = tx_stats.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
+            let lst = looping_stats.clone();
             (
                 tokio::spawn(async move {
                     if PAUSE_SCAN.load(Ordering::Acquire) {
@@ -566,7 +614,7 @@ pub async fn scan_url(
                         // todo change to true when issue #107 is resolved
                         SCANNED_URLS.pause(false).await;
                     }
-                    make_requests(&tgt, &word, base_depth, txd, txr).await
+                    make_requests(&tgt, &word, base_depth, lst, txd, txr, txs).await
                 }),
                 pb,
             )
@@ -587,6 +635,11 @@ pub async fn scan_url(
     producers.await;
     log::trace!("done awaiting scan producers");
 
+    update_stat!(
+        tx_stats,
+        UpdateF64Field(DirScanTimes, scan_timer.elapsed().as_secs_f64())
+    );
+
     // drop the current permit so the semaphore will allow another scan to proceed
     drop(permit);
 
@@ -608,8 +661,17 @@ pub async fn scan_url(
 
 /// Perform steps necessary to run scans that only need to be performed once (warming up the
 /// engine, as it were)
-pub fn initialize(num_words: usize, config: &Configuration) {
-    log::trace!("enter: initialize({}, {:?})", num_words, config,);
+pub async fn initialize(
+    num_words: usize,
+    config: &Configuration,
+    tx_stats: UnboundedSender<StatCommand>,
+) {
+    log::trace!(
+        "enter: initialize({}, {:?}, {:?})",
+        num_words,
+        config,
+        tx_stats
+    );
 
     // number of requests only needs to be calculated once, and then can be reused
     let num_reqs_expected: u64 = if config.extensions.is_empty() {
@@ -619,7 +681,11 @@ pub fn initialize(num_words: usize, config: &Configuration) {
         total.try_into().unwrap()
     };
 
-    NUMBER_OF_REQUESTS.store(num_reqs_expected, Ordering::Relaxed);
+    // tell Stats object about the number of expected requests
+    update_stat!(
+        tx_stats,
+        UpdateUsizeField(ExpectedPerScan, num_reqs_expected as usize)
+    );
 
     // add any status code filters to `FILTERS` (-C|--filter-status)
     for code_filter in &config.filter_status {
@@ -679,6 +745,36 @@ pub fn initialize(num_words: usize, config: &Configuration) {
         add_filter_to_list_of_ferox_filters(boxed_filter, FILTERS.clone());
     }
 
+    // add any similarity filters to `FILTERS` (--filter-similar-to)
+    for similarity_filter in &config.filter_similar {
+        // url as-is based on input, ignores user-specified url manipulation options (add-slash etc)
+        if let Ok(url) = format_url(
+            &similarity_filter,
+            &"",
+            false,
+            &Vec::new(),
+            None,
+            tx_stats.clone(),
+        ) {
+            // attempt to request the given url
+            if let Ok(resp) = make_request(&CONFIGURATION.client, &url, tx_stats.clone()).await {
+                // if successful, create a filter based on the response's body
+                let fr = FeroxResponse::from(resp, true).await;
+
+                // hash the response body and store the resulting hash in the filter object
+                let hash = FuzzyHash::new(&fr.text()).to_string();
+
+                let filter = SimilarityFilter {
+                    text: hash,
+                    threshold: SIMILARITY_THRESHOLD,
+                };
+
+                let boxed_filter = Box::new(filter);
+                add_filter_to_list_of_ferox_filters(boxed_filter, FILTERS.clone());
+            }
+        }
+    }
+
     if config.scan_limit == 0 {
         // scan_limit == 0 means no limit should be imposed... however, scoping the Semaphore
         // permit is tricky, so as a workaround, we'll add a ridiculous number of permits to
@@ -696,14 +792,16 @@ mod tests {
     #[test]
     /// sending url + word without any extensions should get back one url with the joined word
     fn create_urls_no_extension_returns_base_url_with_word() {
-        let urls = create_urls("http://localhost", "turbo", &[]);
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
+        let urls = create_urls("http://localhost", "turbo", &[], tx);
         assert_eq!(urls, [Url::parse("http://localhost/turbo").unwrap()])
     }
 
     #[test]
     /// sending url + word + 1 extension should get back two urls, one base and one with extension
     fn create_urls_one_extension_returns_two_urls() {
-        let urls = create_urls("http://localhost", "turbo", &[String::from("js")]);
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
+        let urls = create_urls("http://localhost", "turbo", &[String::from("js")], tx);
         assert_eq!(
             urls,
             [
@@ -741,8 +839,10 @@ mod tests {
             vec![base, js, php, pdf, tar],
         ];
 
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
+
         for (i, ext_set) in ext_vec.into_iter().enumerate() {
-            let urls = create_urls("http://localhost", "turbo", &ext_set);
+            let urls = create_urls("http://localhost", "turbo", &ext_set, tx.clone());
             assert_eq!(urls, expected[i]);
         }
     }
@@ -787,12 +887,15 @@ mod tests {
         assert!(result);
     }
 
-    #[test]
+    #[tokio::test(core_threads = 1)]
     #[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);
+    async fn initialize_panics_on_bad_regex() {
+        let config = Configuration {
+            filter_regex: vec![r"(".to_string()],
+            ..Default::default()
+        };
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
+        initialize(1, &config, tx).await;
     }
 }

src/statistics.rs

@@ -0,0 +1,793 @@
+use crate::{
+    config::CONFIGURATION,
+    progress::{add_bar, BarType},
+    reporter::{get_cached_file_handle, safe_file_write},
+    FeroxChannel, FeroxSerialize,
+};
+use console::style;
+use indicatif::ProgressBar;
+use reqwest::StatusCode;
+use serde::{Deserialize, Serialize};
+use std::{
+    fs::File,
+    io::BufReader,
+    sync::{
+        atomic::{AtomicUsize, Ordering},
+        Arc, Mutex,
+    },
+    time::Instant,
+};
+use tokio::{
+    sync::mpsc::{self, UnboundedReceiver, UnboundedSender},
+    task::JoinHandle,
+};
+
+/// Wrapper `Atomic*.fetch_add` to save me from writing Ordering::Relaxed a bajillion times
+///
+/// default is to increment by 1, second arg can be used to increment by a different value
+macro_rules! atomic_increment {
+    ($metric:expr) => {
+        $metric.fetch_add(1, Ordering::Relaxed);
+    };
+
+    ($metric:expr, $value:expr) => {
+        $metric.fetch_add($value, Ordering::Relaxed);
+    };
+}
+
+/// Wrapper around `Atomic*.load` to save me from writing Ordering::Relaxed a bajillion times
+macro_rules! atomic_load {
+    ($metric:expr) => {
+        $metric.load(Ordering::Relaxed);
+    };
+}
+
+/// Data collection of statistics related to a scan
+#[derive(Default, Deserialize, Debug, Serialize)]
+pub struct Stats {
+    #[serde(rename = "type")]
+    /// Name of this type of struct, used for serialization, i.e. `{"type":"statistics"}`
+    kind: String,
+
+    /// tracker for number of timeouts seen by the client
+    timeouts: AtomicUsize,
+
+    /// tracker for total number of requests sent by the client
+    requests: AtomicUsize,
+
+    /// tracker for total number of requests expected to send if the scan runs to completion
+    ///
+    /// Note: this is a per-scan expectation; `expected_requests * current # of scans` would be
+    /// indicative of the current expectation at any given time, but is a moving target.  
+    pub expected_per_scan: AtomicUsize,
+
+    /// tracker for accumulating total number of requests expected (i.e. as a new scan is started
+    /// this value should increase by `expected_requests`
+    total_expected: AtomicUsize,
+
+    /// tracker for total number of errors encountered by the client
+    errors: AtomicUsize,
+
+    /// tracker for overall number of 2xx status codes seen by the client
+    successes: AtomicUsize,
+
+    /// tracker for overall number of 3xx status codes seen by the client
+    redirects: AtomicUsize,
+
+    /// tracker for overall number of 4xx status codes seen by the client
+    client_errors: AtomicUsize,
+
+    /// tracker for overall number of 5xx status codes seen by the client
+    server_errors: AtomicUsize,
+
+    /// tracker for number of scans performed, this directly equates to number of directories
+    /// recursed into and affects the total number of expected requests
+    total_scans: AtomicUsize,
+
+    /// tracker for initial number of requested targets
+    pub initial_targets: AtomicUsize,
+
+    /// tracker for number of links extracted when `--extract-links` is used; sources are
+    /// response bodies and robots.txt as of v1.11.0
+    links_extracted: AtomicUsize,
+
+    /// tracker for overall number of 200s seen by the client
+    status_200s: AtomicUsize,
+
+    /// tracker for overall number of 301s seen by the client
+    status_301s: AtomicUsize,
+
+    /// tracker for overall number of 302s seen by the client
+    status_302s: AtomicUsize,
+
+    /// tracker for overall number of 401s seen by the client
+    status_401s: AtomicUsize,
+
+    /// tracker for overall number of 403s seen by the client
+    status_403s: AtomicUsize,
+
+    /// tracker for overall number of 429s seen by the client
+    status_429s: AtomicUsize,
+
+    /// tracker for overall number of 500s seen by the client
+    status_500s: AtomicUsize,
+
+    /// tracker for overall number of 503s seen by the client
+    status_503s: AtomicUsize,
+
+    /// tracker for overall number of 504s seen by the client
+    status_504s: AtomicUsize,
+
+    /// tracker for overall number of 508s seen by the client
+    status_508s: AtomicUsize,
+
+    /// tracker for overall number of wildcard urls filtered out by the client
+    wildcards_filtered: AtomicUsize,
+
+    /// tracker for overall number of all filtered responses
+    responses_filtered: AtomicUsize,
+
+    /// tracker for number of files found
+    resources_discovered: AtomicUsize,
+
+    /// tracker for number of errors triggered during URL formatting
+    url_format_errors: AtomicUsize,
+
+    /// tracker for number of errors triggered by the `reqwest::RedirectPolicy`
+    redirection_errors: AtomicUsize,
+
+    /// tracker for number of errors related to the connecting
+    connection_errors: AtomicUsize,
+
+    /// tracker for number of errors related to the request used
+    request_errors: AtomicUsize,
+
+    /// tracker for each directory's total scan time in seconds as a float
+    directory_scan_times: Mutex<Vec<f64>>,
+
+    /// tracker for total runtime
+    total_runtime: Mutex<Vec<f64>>,
+}
+
+/// FeroxSerialize implementation for Stats
+impl FeroxSerialize for Stats {
+    /// Simply return debug format of Stats to satisfy as_str
+    fn as_str(&self) -> String {
+        String::new()
+    }
+
+    /// Simple call to produce a JSON string using the given Stats object
+    fn as_json(&self) -> String {
+        serde_json::to_string(&self).unwrap_or_default()
+    }
+}
+
+/// implementation of statistics data collection struct
+impl Stats {
+    /// Small wrapper for default to set `kind` to "statistics" and `total_runtime` to have at least
+    /// one value
+    pub fn new() -> Self {
+        Self {
+            kind: String::from("statistics"),
+            total_runtime: Mutex::new(vec![0.0]),
+            ..Default::default()
+        }
+    }
+
+    /// increment `requests` field by one
+    fn add_request(&self) {
+        atomic_increment!(self.requests);
+    }
+
+    /// given an `Instant` update total runtime
+    fn update_runtime(&self, seconds: f64) {
+        if let Ok(mut runtime) = self.total_runtime.lock() {
+            runtime[0] = seconds;
+        }
+    }
+
+    /// save an instance of `Stats` to disk after updating the total runtime for the scan
+    fn save(&self, seconds: f64) {
+        let buffered_file = match get_cached_file_handle(&CONFIGURATION.output) {
+            Some(file) => file,
+            None => {
+                return;
+            }
+        };
+
+        self.update_runtime(seconds);
+
+        safe_file_write(self, buffered_file, CONFIGURATION.json);
+    }
+
+    /// Inspect the given `StatError` and increment the appropriate fields
+    ///
+    /// Implies incrementing:
+    ///     - requests
+    ///     - errors
+    pub fn add_error(&self, error: StatError) {
+        self.add_request();
+        atomic_increment!(self.errors);
+
+        match error {
+            StatError::Timeout => {
+                atomic_increment!(self.timeouts);
+            }
+            StatError::Status403 => {
+                atomic_increment!(self.status_403s);
+                atomic_increment!(self.client_errors);
+            }
+            StatError::UrlFormat => {
+                atomic_increment!(self.url_format_errors);
+            }
+            StatError::Redirection => {
+                atomic_increment!(self.redirection_errors);
+            }
+            StatError::Connection => {
+                atomic_increment!(self.connection_errors);
+            }
+            StatError::Request => {
+                atomic_increment!(self.request_errors);
+            }
+            StatError::Other => {
+                atomic_increment!(self.errors);
+            }
+        }
+    }
+
+    /// Inspect the given `StatusCode` and increment the appropriate fields
+    ///
+    /// Implies incrementing:
+    ///     - requests
+    ///     - status_403s (when code is 403)
+    ///     - errors (when code is [45]xx)
+    fn add_status_code(&self, status: StatusCode) {
+        self.add_request();
+
+        if status.is_success() {
+            atomic_increment!(self.successes);
+        } else if status.is_redirection() {
+            atomic_increment!(self.redirects);
+        } else if status.is_client_error() {
+            atomic_increment!(self.client_errors);
+        } else if status.is_server_error() {
+            atomic_increment!(self.server_errors);
+        }
+
+        match status {
+            StatusCode::FORBIDDEN => {
+                atomic_increment!(self.status_403s);
+            }
+            StatusCode::OK => {
+                atomic_increment!(self.status_200s);
+            }
+            StatusCode::MOVED_PERMANENTLY => {
+                atomic_increment!(self.status_301s);
+            }
+            StatusCode::FOUND => {
+                atomic_increment!(self.status_302s);
+            }
+            StatusCode::UNAUTHORIZED => {
+                atomic_increment!(self.status_401s);
+            }
+            StatusCode::TOO_MANY_REQUESTS => {
+                atomic_increment!(self.status_429s);
+            }
+            StatusCode::INTERNAL_SERVER_ERROR => {
+                atomic_increment!(self.status_500s);
+            }
+            StatusCode::SERVICE_UNAVAILABLE => {
+                atomic_increment!(self.status_503s);
+            }
+            StatusCode::GATEWAY_TIMEOUT => {
+                atomic_increment!(self.status_504s);
+            }
+            StatusCode::LOOP_DETECTED => {
+                atomic_increment!(self.status_508s);
+            }
+            _ => {} // other status codes ignored for stat gathering
+        }
+    }
+
+    /// Update a `Stats` field of type f64
+    fn update_f64_field(&self, field: StatField, value: f64) {
+        if let StatField::DirScanTimes = field {
+            if let Ok(mut locked_times) = self.directory_scan_times.lock() {
+                locked_times.push(value);
+            }
+        }
+    }
+
+    /// Update a `Stats` field of type usize
+    fn update_usize_field(&self, field: StatField, value: usize) {
+        match field {
+            StatField::ExpectedPerScan => {
+                atomic_increment!(self.expected_per_scan, value);
+            }
+            StatField::TotalScans => {
+                let multiplier = CONFIGURATION.extensions.len().max(1);
+
+                atomic_increment!(self.total_scans, value);
+                atomic_increment!(
+                    self.total_expected,
+                    value * self.expected_per_scan.load(Ordering::Relaxed) * multiplier
+                );
+            }
+            StatField::TotalExpected => {
+                atomic_increment!(self.total_expected, value);
+            }
+            StatField::LinksExtracted => {
+                atomic_increment!(self.links_extracted, value);
+            }
+            StatField::WildcardsFiltered => {
+                atomic_increment!(self.wildcards_filtered, value);
+                atomic_increment!(self.responses_filtered, value);
+            }
+            StatField::ResponsesFiltered => {
+                atomic_increment!(self.responses_filtered, value);
+            }
+            StatField::ResourcesDiscovered => {
+                atomic_increment!(self.resources_discovered, value);
+            }
+            StatField::InitialTargets => {
+                atomic_increment!(self.initial_targets, value);
+            }
+            _ => {} // f64 fields
+        }
+    }
+
+    /// Merge a given `Stats` object from a json entry written to disk when handling a Ctrl+c
+    ///
+    /// This is only ever called when resuming a scan from disk
+    pub fn merge_from(&self, filename: &str) {
+        if let Ok(file) = File::open(filename) {
+            let reader = BufReader::new(file);
+            let state: serde_json::Value = serde_json::from_reader(reader).unwrap();
+
+            if let Some(state_stats) = state.get("statistics") {
+                if let Ok(d_stats) = serde_json::from_value::<Stats>(state_stats.clone()) {
+                    atomic_increment!(self.successes, atomic_load!(d_stats.successes));
+                    atomic_increment!(self.timeouts, atomic_load!(d_stats.timeouts));
+                    atomic_increment!(self.requests, atomic_load!(d_stats.requests));
+                    atomic_increment!(self.errors, atomic_load!(d_stats.errors));
+                    atomic_increment!(self.redirects, atomic_load!(d_stats.redirects));
+                    atomic_increment!(self.client_errors, atomic_load!(d_stats.client_errors));
+                    atomic_increment!(self.server_errors, atomic_load!(d_stats.server_errors));
+                    atomic_increment!(self.links_extracted, atomic_load!(d_stats.links_extracted));
+                    atomic_increment!(self.status_200s, atomic_load!(d_stats.status_200s));
+                    atomic_increment!(self.status_301s, atomic_load!(d_stats.status_301s));
+                    atomic_increment!(self.status_302s, atomic_load!(d_stats.status_302s));
+                    atomic_increment!(self.status_401s, atomic_load!(d_stats.status_401s));
+                    atomic_increment!(self.status_403s, atomic_load!(d_stats.status_403s));
+                    atomic_increment!(self.status_429s, atomic_load!(d_stats.status_429s));
+                    atomic_increment!(self.status_500s, atomic_load!(d_stats.status_500s));
+                    atomic_increment!(self.status_503s, atomic_load!(d_stats.status_503s));
+                    atomic_increment!(self.status_504s, atomic_load!(d_stats.status_504s));
+                    atomic_increment!(self.status_508s, atomic_load!(d_stats.status_508s));
+                    atomic_increment!(
+                        self.wildcards_filtered,
+                        atomic_load!(d_stats.wildcards_filtered)
+                    );
+                    atomic_increment!(
+                        self.responses_filtered,
+                        atomic_load!(d_stats.responses_filtered)
+                    );
+                    atomic_increment!(
+                        self.resources_discovered,
+                        atomic_load!(d_stats.resources_discovered)
+                    );
+                    atomic_increment!(
+                        self.url_format_errors,
+                        atomic_load!(d_stats.url_format_errors)
+                    );
+                    atomic_increment!(
+                        self.connection_errors,
+                        atomic_load!(d_stats.connection_errors)
+                    );
+                    atomic_increment!(
+                        self.redirection_errors,
+                        atomic_load!(d_stats.redirection_errors)
+                    );
+                    atomic_increment!(self.request_errors, atomic_load!(d_stats.request_errors));
+
+                    if let Ok(scan_times) = d_stats.directory_scan_times.lock() {
+                        for scan_time in scan_times.iter() {
+                            self.update_f64_field(StatField::DirScanTimes, *scan_time);
+                        }
+                    }
+                }
+            }
+        }
+    }
+}
+
+#[derive(Debug)]
+/// Enum variants used to inform the `StatCommand` protocol what `Stats` fields should be updated
+pub enum StatError {
+    /// Represents a 403 response code
+    Status403,
+
+    /// Represents a timeout error
+    Timeout,
+
+    /// Represents a URL formatting error
+    UrlFormat,
+
+    /// Represents an error encountered during redirection
+    Redirection,
+
+    /// Represents an error encountered during connection
+    Connection,
+
+    /// Represents an error resulting from the client's request
+    Request,
+
+    /// Represents any other error not explicitly defined above
+    Other,
+}
+
+/// Protocol definition for updating a Stats object via mpsc
+#[derive(Debug)]
+pub enum StatCommand {
+    /// Add one to the total number of requests
+    AddRequest,
+
+    /// Add one to the proper field(s) based on the given `StatError`
+    AddError(StatError),
+
+    /// Add one to the proper field(s) based on the given `StatusCode`
+    AddStatus(StatusCode),
+
+    /// Create the progress bar (`BarType::Total`) that is updated from the stats thread
+    CreateBar,
+
+    /// Update a `Stats` field that corresponds to the given `StatField` by the given `usize` value
+    UpdateUsizeField(StatField, usize),
+
+    /// Update a `Stats` field that corresponds to the given `StatField` by the given `f64` value
+    UpdateF64Field(StatField, f64),
+
+    /// Save a `Stats` object to disk using `reporter::get_cached_file_handle`
+    Save,
+
+    /// Load a `Stats` object from disk
+    LoadStats(String),
+
+    /// Break out of the (infinite) mpsc receive loop
+    Exit,
+}
+
+/// Enum representing fields whose updates need to be performed in batches instead of one at
+/// a time
+#[derive(Debug)]
+pub enum StatField {
+    /// Due to the necessary order of events, the number of requests expected to be sent isn't
+    /// known until after `statistics::initialize` is called. This command allows for updating
+    /// the `expected_per_scan` field after initialization
+    ExpectedPerScan,
+
+    /// Translates to `total_scans`
+    TotalScans,
+
+    /// Translates to `links_extracted`
+    LinksExtracted,
+
+    /// Translates to `total_expected`
+    TotalExpected,
+
+    /// Translates to `wildcards_filtered`
+    WildcardsFiltered,
+
+    /// Translates to `responses_filtered`
+    ResponsesFiltered,
+
+    /// Translates to `resources_discovered`
+    ResourcesDiscovered,
+
+    /// Translates to `initial_targets`
+    InitialTargets,
+
+    /// Translates to `directory_scan_times`; assumes a single append to the vector
+    DirScanTimes,
+}
+
+/// Spawn a single consumer task (sc side of mpsc)
+///
+/// The consumer simply receives `StatCommands` and updates the given `Stats` object as appropriate
+pub async fn spawn_statistics_handler(
+    mut rx_stats: UnboundedReceiver<StatCommand>,
+    stats: Arc<Stats>,
+    tx_stats: UnboundedSender<StatCommand>,
+) {
+    log::trace!(
+        "enter: spawn_statistics_handler({:?}, {:?}, {:?})",
+        rx_stats,
+        stats,
+        tx_stats
+    );
+
+    // will be updated later via StatCommand; delay is for banner to print first
+    let mut bar = ProgressBar::hidden();
+
+    let start = Instant::now();
+
+    while let Some(command) = rx_stats.recv().await {
+        match command as StatCommand {
+            StatCommand::AddError(err) => {
+                stats.add_error(err);
+            }
+            StatCommand::AddStatus(status) => {
+                stats.add_status_code(status);
+            }
+            StatCommand::AddRequest => stats.add_request(),
+            StatCommand::Save => stats.save(start.elapsed().as_secs_f64()),
+            StatCommand::UpdateUsizeField(field, value) => {
+                let update_len = matches!(field, StatField::TotalScans);
+                stats.update_usize_field(field, value);
+
+                if update_len {
+                    bar.set_length(atomic_load!(stats.total_expected) as u64)
+                }
+            }
+            StatCommand::UpdateF64Field(field, value) => stats.update_f64_field(field, value),
+            StatCommand::CreateBar => {
+                bar = add_bar(
+                    "",
+                    atomic_load!(stats.total_expected) as u64,
+                    BarType::Total,
+                );
+            }
+            StatCommand::LoadStats(filename) => {
+                stats.merge_from(&filename);
+            }
+            StatCommand::Exit => break,
+        }
+
+        let msg = format!(
+            "{}:{:<7} {}:{:<7}",
+            style("found").green(),
+            atomic_load!(stats.resources_discovered),
+            style("errors").red(),
+            atomic_load!(stats.errors),
+        );
+
+        bar.set_message(&msg);
+        bar.inc(1);
+    }
+
+    bar.finish();
+
+    log::debug!("{:#?}", *stats);
+    log::trace!("exit: spawn_statistics_handler")
+}
+
+/// Initialize new `Stats` object and the sc side of an mpsc channel that is responsible for
+/// updates to the aforementioned object.
+pub fn initialize() -> (Arc<Stats>, UnboundedSender<StatCommand>, JoinHandle<()>) {
+    log::trace!("enter: initialize");
+
+    let stats_tracker = Arc::new(Stats::new());
+    let stats_cloned = stats_tracker.clone();
+    let (tx_stats, rx_stats): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
+    let tx_stats_cloned = tx_stats.clone();
+    let stats_thread = tokio::spawn(async move {
+        spawn_statistics_handler(rx_stats, stats_cloned, tx_stats_cloned).await
+    });
+
+    log::trace!(
+        "exit: initialize -> ({:?}, {:?}, {:?})",
+        stats_tracker,
+        tx_stats,
+        stats_thread
+    );
+
+    (stats_tracker, tx_stats, stats_thread)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use std::fs::write;
+    use tempfile::NamedTempFile;
+
+    /// simple helper to reduce code reuse
+    fn setup_stats_test() -> (Arc<Stats>, UnboundedSender<StatCommand>, JoinHandle<()>) {
+        initialize()
+    }
+
+    /// another helper to stay DRY; must be called after any sent commands and before any checks
+    /// performed against the Stats object
+    async fn teardown_stats_test(sender: UnboundedSender<StatCommand>, handle: JoinHandle<()>) {
+        // send exit and await, once the await completes, stats should be updated
+        sender.send(StatCommand::Exit).unwrap_or_default();
+        handle.await.unwrap();
+    }
+
+    #[tokio::test(core_threads = 1)]
+    /// when sent StatCommand::Exit, function should exit its while loop (runs forever otherwise)
+    async fn statistics_handler_exits() {
+        let (_, sender, handle) = setup_stats_test();
+
+        sender.send(StatCommand::Exit).unwrap_or_default();
+
+        handle.await.unwrap(); // blocks on the handler's while loop
+
+        // if we've made it here, the test has succeeded
+    }
+
+    #[tokio::test(core_threads = 1)]
+    /// when sent StatCommand::AddRequest, stats object should reflect the change
+    async fn statistics_handler_increments_requests() {
+        let (stats, tx, handle) = setup_stats_test();
+
+        tx.send(StatCommand::AddRequest).unwrap_or_default();
+        tx.send(StatCommand::AddRequest).unwrap_or_default();
+        tx.send(StatCommand::AddRequest).unwrap_or_default();
+
+        teardown_stats_test(tx, handle).await;
+
+        assert_eq!(stats.requests.load(Ordering::Relaxed), 3);
+    }
+
+    #[tokio::test(core_threads = 1)]
+    /// when sent StatCommand::AddRequest, stats object should reflect the change
+    ///
+    /// incrementing a 403 (tracked in status_403s) should also increment:
+    ///     - errors
+    ///     - requests
+    ///     - client_errors
+    async fn statistics_handler_increments_403() {
+        let (stats, tx, handle) = setup_stats_test();
+
+        let err = StatCommand::AddError(StatError::Status403);
+        let err2 = StatCommand::AddError(StatError::Status403);
+
+        tx.send(err).unwrap_or_default();
+        tx.send(err2).unwrap_or_default();
+
+        teardown_stats_test(tx, handle).await;
+
+        assert_eq!(stats.errors.load(Ordering::Relaxed), 2);
+        assert_eq!(stats.requests.load(Ordering::Relaxed), 2);
+        assert_eq!(stats.status_403s.load(Ordering::Relaxed), 2);
+        assert_eq!(stats.client_errors.load(Ordering::Relaxed), 2);
+    }
+
+    #[tokio::test(core_threads = 1)]
+    /// when sent StatCommand::AddRequest, stats object should reflect the change
+    ///
+    /// incrementing a 403 (tracked in status_403s) should also increment:
+    ///     - requests
+    ///     - client_errors
+    async fn statistics_handler_increments_403_via_status_code() {
+        let (stats, tx, handle) = setup_stats_test();
+
+        let err = StatCommand::AddStatus(reqwest::StatusCode::FORBIDDEN);
+        let err2 = StatCommand::AddStatus(reqwest::StatusCode::FORBIDDEN);
+
+        tx.send(err).unwrap_or_default();
+        tx.send(err2).unwrap_or_default();
+
+        teardown_stats_test(tx, handle).await;
+
+        assert_eq!(stats.requests.load(Ordering::Relaxed), 2);
+        assert_eq!(stats.status_403s.load(Ordering::Relaxed), 2);
+        assert_eq!(stats.client_errors.load(Ordering::Relaxed), 2);
+    }
+
+    #[tokio::test(core_threads = 1)]
+    /// when sent StatCommand::AddStatus, stats object should reflect the change
+    ///
+    /// incrementing a 500 (tracked in server_errors) should also increment:
+    ///     - requests
+    async fn statistics_handler_increments_500_via_status_code() {
+        let (stats, tx, handle) = setup_stats_test();
+
+        let err = StatCommand::AddStatus(reqwest::StatusCode::INTERNAL_SERVER_ERROR);
+        let err2 = StatCommand::AddStatus(reqwest::StatusCode::INTERNAL_SERVER_ERROR);
+
+        tx.send(err).unwrap_or_default();
+        tx.send(err2).unwrap_or_default();
+
+        teardown_stats_test(tx, handle).await;
+
+        assert_eq!(stats.requests.load(Ordering::Relaxed), 2);
+        assert_eq!(stats.server_errors.load(Ordering::Relaxed), 2);
+    }
+
+    #[test]
+    /// when Stats::add_error receives StatError::Timeout, it should increment the following:
+    ///     - timeouts
+    ///     - requests
+    ///     - errors
+    fn stats_increments_timeouts() {
+        let stats = Stats::new();
+        stats.add_error(StatError::Timeout);
+        stats.add_error(StatError::Timeout);
+        stats.add_error(StatError::Timeout);
+        stats.add_error(StatError::Timeout);
+
+        assert_eq!(stats.errors.load(Ordering::Relaxed), 4);
+        assert_eq!(stats.requests.load(Ordering::Relaxed), 4);
+        assert_eq!(stats.timeouts.load(Ordering::Relaxed), 4);
+    }
+
+    #[test]
+    /// when Stats::update_usize_field receives StatField::WildcardsFiltered, it should increment
+    /// the following:
+    ///     - responses_filtered
+    fn stats_increments_wildcards() {
+        let stats = Stats::new();
+        assert_eq!(stats.responses_filtered.load(Ordering::Relaxed), 0);
+        assert_eq!(stats.wildcards_filtered.load(Ordering::Relaxed), 0);
+
+        stats.update_usize_field(StatField::WildcardsFiltered, 1);
+        stats.update_usize_field(StatField::WildcardsFiltered, 1);
+
+        assert_eq!(stats.responses_filtered.load(Ordering::Relaxed), 2);
+        assert_eq!(stats.wildcards_filtered.load(Ordering::Relaxed), 2);
+    }
+
+    #[test]
+    /// when Stats::update_usize_field receives StatField::ResponsesFiltered, it should increment
+    fn stats_increments_responses_filtered() {
+        let stats = Stats::new();
+        assert_eq!(stats.responses_filtered.load(Ordering::Relaxed), 0);
+
+        stats.update_usize_field(StatField::ResponsesFiltered, 1);
+        stats.update_usize_field(StatField::ResponsesFiltered, 1);
+        stats.update_usize_field(StatField::ResponsesFiltered, 1);
+
+        assert_eq!(stats.responses_filtered.load(Ordering::Relaxed), 3);
+    }
+
+    #[test]
+    /// Stats::merge_from should properly incrememnt expected fields and ignore others
+    fn stats_merge_from_alters_correct_fields() {
+        let contents = r#"{"statistics":{"type":"statistics","timeouts":1,"requests":9207,"expected_per_scan":707,"total_expected":9191,"errors":3,"successes":720,"redirects":13,"client_errors":8474,"server_errors":2,"total_scans":13,"initial_targets":1,"links_extracted":51,"status_403s":3,"status_200s":720,"status_301s":12,"status_302s":1,"status_401s":4,"status_429s":2,"status_500s":5,"status_503s":9,"status_504s":6,"status_508s":7,"wildcards_filtered":707,"responses_filtered":707,"resources_discovered":27,"directory_scan_times":[2.211973078,1.989015505,1.898675839,3.9714468910000003,4.938152838,5.256073528,6.021986595,6.065740734,6.42633762,7.095142125,7.336982137,5.319785619,4.843649778],"total_runtime":[11.556575456000001],"url_format_errors":17,"redirection_errors":12,"connection_errors":21,"request_errors":4}}"#;
+        let stats = Stats::new();
+        let tfile = NamedTempFile::new().unwrap();
+        write(&tfile, contents).unwrap();
+
+        stats.merge_from(tfile.path().to_str().unwrap());
+
+        // as of 1.11.1; all Stats fields are accounted for whether they're updated in merge_from
+        // or not
+        assert_eq!(atomic_load!(stats.timeouts), 1);
+        assert_eq!(atomic_load!(stats.requests), 9207);
+        assert_eq!(atomic_load!(stats.expected_per_scan), 0); // not updated in merge_from
+        assert_eq!(atomic_load!(stats.total_expected), 0); // not updated in merge_from
+        assert_eq!(atomic_load!(stats.errors), 3);
+        assert_eq!(atomic_load!(stats.successes), 720);
+        assert_eq!(atomic_load!(stats.redirects), 13);
+        assert_eq!(atomic_load!(stats.client_errors), 8474);
+        assert_eq!(atomic_load!(stats.server_errors), 2);
+        assert_eq!(atomic_load!(stats.total_scans), 0); // not updated in merge_from
+        assert_eq!(atomic_load!(stats.initial_targets), 0); // not updated in merge_from
+        assert_eq!(atomic_load!(stats.links_extracted), 51);
+        assert_eq!(atomic_load!(stats.status_200s), 720);
+        assert_eq!(atomic_load!(stats.status_301s), 12);
+        assert_eq!(atomic_load!(stats.status_302s), 1);
+        assert_eq!(atomic_load!(stats.status_401s), 4);
+        assert_eq!(atomic_load!(stats.status_403s), 3);
+        assert_eq!(atomic_load!(stats.status_429s), 2);
+        assert_eq!(atomic_load!(stats.status_500s), 5);
+        assert_eq!(atomic_load!(stats.status_503s), 9);
+        assert_eq!(atomic_load!(stats.status_504s), 6);
+        assert_eq!(atomic_load!(stats.status_508s), 7);
+        assert_eq!(atomic_load!(stats.wildcards_filtered), 707);
+        assert_eq!(atomic_load!(stats.responses_filtered), 707);
+        assert_eq!(atomic_load!(stats.resources_discovered), 27);
+        assert_eq!(atomic_load!(stats.url_format_errors), 17);
+        assert_eq!(atomic_load!(stats.redirection_errors), 12);
+        assert_eq!(atomic_load!(stats.connection_errors), 21);
+        assert_eq!(atomic_load!(stats.request_errors), 4);
+        assert_eq!(stats.directory_scan_times.lock().unwrap().len(), 13);
+        for scan in stats.directory_scan_times.lock().unwrap().iter() {
+            assert!(scan.max(0.0) > 0.0); // all scans are non-zero
+        }
+        // total_runtime not updated in merge_from
+        assert_eq!(stats.total_runtime.lock().unwrap().len(), 1);
+        assert!((stats.total_runtime.lock().unwrap()[0] - 0.0).abs() < f64::EPSILON);
+    }
+}

src/utils.rs

@@ -1,5 +1,10 @@
+#![macro_use]
 use crate::{
     config::{CONFIGURATION, PROGRESS_PRINTER},
+    statistics::{
+        StatCommand::{self, AddError, AddStatus},
+        StatError::{Connection, Other, Redirection, Request, Timeout, UrlFormat},
+    },
     FeroxError, FeroxResult,
 };
 use console::{strip_ansi_codes, style, user_attended};
@@ -10,6 +15,7 @@ use rlimit::{getrlimit, setrlimit, Resource, Rlim};
 use std::convert::TryInto;
 use std::sync::{Arc, RwLock};
 use std::{fs, io};
+use tokio::sync::mpsc::UnboundedSender;
 
 /// 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
@@ -160,6 +166,14 @@ pub fn ferox_print(msg: &str, bar: &ProgressBar) {
     }
 }
 
+#[macro_export]
+/// wrapper to improve code readability
+macro_rules! update_stat {
+    ($tx:expr, $value:expr) => {
+        $tx.send($value).unwrap_or_default();
+    };
+}
+
 /// Simple helper to generate a `Url`
 ///
 /// Errors during parsing `url` or joining `word` are propagated up the call stack
@@ -169,14 +183,16 @@ pub fn format_url(
     add_slash: bool,
     queries: &[(String, String)],
     extension: Option<&str>,
+    tx_stats: UnboundedSender<StatCommand>,
 ) -> FeroxResult<Url> {
     log::trace!(
-        "enter: format_url({}, {}, {}, {:?} {:?})",
+        "enter: format_url({}, {}, {}, {:?} {:?}, {:?})",
         url,
         word,
         add_slash,
         queries,
-        extension
+        extension,
+        tx_stats
     );
 
     if Url::parse(&word).is_ok() {
@@ -193,8 +209,9 @@ pub fn format_url(
         );
         log::warn!("{}", message);
 
-        let mut err = FeroxError::default();
-        err.message = message;
+        let err = FeroxError { message };
+
+        update_stat!(tx_stats, AddError(UrlFormat));
 
         log::trace!("exit: format_url -> {}", err);
         return Err(Box::new(err));
@@ -208,7 +225,7 @@ 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 word.is_empty() {
-        // v1.0.6: added during --extract-links feature inplementation to support creating urls
+        // v1.0.6: added during --extract-links feature implementation 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('/') {
@@ -255,6 +272,7 @@ pub fn format_url(
             }
         }
         Err(e) => {
+            update_stat!(tx_stats, AddError(UrlFormat));
             log::trace!("exit: format_url -> {}", e);
             log::error!("Could not join {} with {}", word, base_url);
             Err(Box::new(e))
@@ -263,37 +281,63 @@ pub fn format_url(
 }
 
 /// Initiate request to the given `Url` using `Client`
-pub async fn make_request(client: &Client, url: &Url) -> FeroxResult<Response> {
-    log::trace!("enter: make_request(CONFIGURATION.Client, {})", url);
+pub async fn make_request(
+    client: &Client,
+    url: &Url,
+    tx_stats: UnboundedSender<StatCommand>,
+) -> FeroxResult<Response> {
+    log::trace!(
+        "enter: make_request(CONFIGURATION.Client, {}, {:?})",
+        url,
+        tx_stats
+    );
 
     match client.get(url.to_owned()).send().await {
-        Ok(resp) => {
-            log::trace!("exit: make_request -> {:?}", resp);
-            Ok(resp)
-        }
         Err(e) => {
+            let mut log_level = log::Level::Error;
+
             log::trace!("exit: make_request -> {}", e);
-            if e.to_string().contains("operation timed out") {
+            if e.is_timeout() {
                 // only warn for timeouts, while actual errors are still left as errors
-                log::warn!("Error while making request: {}", e);
+                log_level = log::Level::Warn;
+                update_stat!(tx_stats, AddError(Timeout));
             } 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() {
+                        update_stat!(tx_stats, AddStatus(msg_status));
                         create_report_string(msg_status.as_str(), "-1", "-1", "-1", &fancy_message)
                     } else {
                         create_report_string("UNK", "-1", "-1", "-1", &fancy_message)
                     };
 
+                    update_stat!(tx_stats, AddError(Redirection));
+
                     ferox_print(&report, &PROGRESS_PRINTER)
                 };
+            } else if e.is_connect() {
+                update_stat!(tx_stats, AddError(Connection));
+            } else if e.is_request() {
+                update_stat!(tx_stats, AddError(Request));
             } else {
-                log::error!("Error while making request: {}", e);
+                update_stat!(tx_stats, AddError(Other));
             }
+
+            if matches!(log_level, log::Level::Error) {
+                log::error!("Error while making request: {}", e);
+            } else {
+                log::warn!("Error while making request: {}", e);
+            }
+
             Err(Box::new(e))
         }
+        Ok(resp) => {
+            log::trace!("exit: make_request -> {:?}", resp);
+            update_stat!(tx_stats, AddStatus(resp.status()));
+            Ok(resp)
+        }
     }
 }
 
@@ -391,6 +435,8 @@ pub fn normalize_url(url: &str) -> String {
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::FeroxChannel;
+    use tokio::sync::mpsc;
 
     #[test]
     /// set_open_file_limit with a low requested limit succeeds
@@ -458,8 +504,9 @@ mod tests {
     #[test]
     /// base url + 1 word + no slash + no extension
     fn format_url_normal() {
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
         assert_eq!(
-            format_url("http://localhost", "stuff", false, &Vec::new(), None).unwrap(),
+            format_url("http://localhost", "stuff", false, &Vec::new(), None, tx).unwrap(),
             reqwest::Url::parse("http://localhost/stuff").unwrap()
         );
     }
@@ -467,8 +514,9 @@ mod tests {
     #[test]
     /// base url + no word + no slash + no extension
     fn format_url_no_word() {
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
         assert_eq!(
-            format_url("http://localhost", "", false, &Vec::new(), None).unwrap(),
+            format_url("http://localhost", "", false, &Vec::new(), None, tx).unwrap(),
             reqwest::Url::parse("http://localhost").unwrap()
         );
     }
@@ -476,13 +524,15 @@ mod tests {
     #[test]
     /// base url + word + no slash + no extension + queries
     fn format_url_joins_queries() {
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
         assert_eq!(
             format_url(
                 "http://localhost",
                 "lazer",
                 false,
                 &[(String::from("stuff"), String::from("things"))],
-                None
+                None,
+                tx
             )
             .unwrap(),
             reqwest::Url::parse("http://localhost/lazer?stuff=things").unwrap()
@@ -492,13 +542,15 @@ mod tests {
     #[test]
     /// base url + no word + no slash + no extension + queries
     fn format_url_without_word_joins_queries() {
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
         assert_eq!(
             format_url(
                 "http://localhost",
                 "",
                 false,
                 &[(String::from("stuff"), String::from("things"))],
-                None
+                None,
+                tx
             )
             .unwrap(),
             reqwest::Url::parse("http://localhost/?stuff=things").unwrap()
@@ -509,14 +561,16 @@ mod tests {
     #[should_panic]
     /// no base url is an error
     fn format_url_no_url() {
-        format_url("", "stuff", false, &Vec::new(), None).unwrap();
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
+        format_url("", "stuff", false, &Vec::new(), None, tx).unwrap();
     }
 
     #[test]
     /// word prepended with slash is adjusted for correctness
     fn format_url_word_with_preslash() {
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
         assert_eq!(
-            format_url("http://localhost", "/stuff", false, &Vec::new(), None).unwrap(),
+            format_url("http://localhost", "/stuff", false, &Vec::new(), None, tx).unwrap(),
             reqwest::Url::parse("http://localhost/stuff").unwrap()
         );
     }
@@ -524,8 +578,9 @@ mod tests {
     #[test]
     /// word with appended slash allows the slash to persist
     fn format_url_word_with_postslash() {
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
         assert_eq!(
-            format_url("http://localhost", "stuff/", false, &Vec::new(), None).unwrap(),
+            format_url("http://localhost", "stuff/", false, &Vec::new(), None, tx).unwrap(),
             reqwest::Url::parse("http://localhost/stuff/").unwrap()
         );
     }
@@ -533,12 +588,14 @@ mod tests {
     #[test]
     /// word that is a fully formed url, should return an error
     fn format_url_word_that_is_a_url() {
+        let (tx, _): FeroxChannel<StatCommand> = mpsc::unbounded_channel();
         let url = format_url(
             "http://localhost",
             "http://schmocalhost",
             false,
             &Vec::new(),
             None,
+            tx,
         );
         assert!(url.is_err());
     }

tests/test_banner.rs

@@ -810,3 +810,30 @@ fn banner_prints_time_limit() {
                 .and(predicate::str::contains("─┴─")),
         );
 }
+
+#[test]
+/// test allows non-existent wordlist to trigger the banner printing to stderr
+/// expect to see all mandatory prints + similarity filter
+fn banner_prints_similarity_filter() {
+    Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg("http://localhost")
+        .arg("--filter-similar-to")
+        .arg("https://somesite.com")
+        .assert()
+        .success()
+        .stderr(
+            predicate::str::contains("─┬─")
+                .and(predicate::str::contains("Target Url"))
+                .and(predicate::str::contains("http://localhost"))
+                .and(predicate::str::contains("Threads"))
+                .and(predicate::str::contains("Wordlist"))
+                .and(predicate::str::contains("Status Codes"))
+                .and(predicate::str::contains("Timeout (secs)"))
+                .and(predicate::str::contains("User-Agent"))
+                .and(predicate::str::contains("Similarity Filter"))
+                .and(predicate::str::contains("│ https://somesite.com"))
+                .and(predicate::str::contains("─┴─")),
+        );
+}

tests/test_extractor.rs

@@ -163,15 +163,14 @@ fn extractor_finds_same_relative_url_twice() {
     cmd.assert().success().stdout(
         predicate::str::contains("/LICENSE")
             .and(predicate::str::contains("200"))
-            .and(predicate::str::contains(
-                "/homepage/assets/img/icons/handshake.svg",
-            )),
+            // .count(1) asserts that we only see the endpoint reported once, even though there
+            // is the potential to request the same url twice
+            .and(predicate::str::contains("/homepage/assets/img/icons/handshake.svg").count(1)),
     );
 
     assert_eq!(mock.hits(), 1);
     assert_eq!(mock_two.hits(), 1);
-    assert!(mock_three.hits() <= 2); // todo: sometimes this is 2 instead of 1
-                                     // the expectation is one, suggesting a race condition... investigate and fix
+    assert!(mock_three.hits() <= 2);
     teardown_tmp_directory(tmp_dir);
 }
 
@@ -220,3 +219,68 @@ fn extractor_finds_filtered_content() -> Result<(), Box<dyn std::error::Error>>
     teardown_tmp_directory(tmp_dir);
     Ok(())
 }
+
+#[test]
+/// serve a robots.txt with a file and and a folder link contained within it. ferox should
+/// find both links and request each one. Additionally, a scan should start with the directory
+/// link found, meaning the wordlist will be thrown at the sub directory
+fn extractor_finds_robots_txt_links_and_displays_files_or_scans_directories() {
+    let srv = MockServer::start();
+    let (tmp_dir, file) = setup_tmp_directory(&["LICENSE".to_string()], "wordlist").unwrap();
+
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200).body("im a little teapot"); // 18
+    });
+
+    let mock_two = srv.mock(|when, then| {
+        when.method(GET).path("/robots.txt");
+        then.status(200).body(
+            r#"
+            User-agent: *
+            Crawl-delay: 10
+            # CSS, JS, Images
+            Allow: /misc/*.css$
+            Disallow: /misc/stupidfile.php
+               Disallow: /disallowed-subdir/
+            "#,
+        );
+    });
+
+    let mock_file = srv.mock(|when, then| {
+        when.method(GET).path("/misc/stupidfile.php");
+        then.status(200).body("im a little teapot too"); // 22
+    });
+
+    let mock_dir = srv.mock(|when, then| {
+        when.method(GET).path("/disallowed-subdir/LICENSE");
+        then.status(200).body("i too, am a container for tea"); // 29
+    });
+
+    let cmd = Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg(srv.url("/"))
+        .arg("--wordlist")
+        .arg(file.as_os_str())
+        .arg("--extract-links")
+        .arg("-vvvv")
+        .unwrap();
+
+    cmd.assert().success().stdout(
+        predicate::str::contains("/LICENSE") // 2 directories contain LICENSE
+            .count(2)
+            .and(predicate::str::contains("18c"))
+            .and(predicate::str::contains("/misc/stupidfile.php"))
+            .and(predicate::str::contains("22c"))
+            .and(predicate::str::contains("/disallowed-subdir/LICENSE"))
+            .and(predicate::str::contains("29c"))
+            .and(predicate::str::contains("200").count(3)),
+    );
+
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(mock_dir.hits(), 1);
+    assert_eq!(mock_two.hits(), 1);
+    assert_eq!(mock_file.hits(), 1);
+    teardown_tmp_directory(tmp_dir);
+}

tests/test_filters.rs

@@ -189,3 +189,61 @@ fn filters_size_should_filter_response() {
     assert_eq!(mock_two.hits(), 1);
     teardown_tmp_directory(tmp_dir);
 }
+
+#[test]
+/// create a FeroxResponse that should elicit a true from
+/// SimilarityFilter::should_filter_response
+fn filter_similar_should_filter_response() {
+    let srv = MockServer::start();
+    let (tmp_dir, file) = setup_tmp_directory(
+        &["not-similar".to_string(), "similar".to_string()],
+        "wordlist",
+    )
+    .unwrap();
+
+    // ''.join(random.choices(string.ascii_letters + string.digits + string.whitespace, k=4096))
+    let content = "VCiYFr0HKsEIK6r\r1hJLYnOr90Aji\rDWAjQA3LVAzrluN48FuSPrRpm\n \tV\x0cx\nSCc5sX\nTB\x0c6Of7ns\t2HDwQCduKTqG8gG\x0beszazwljW01H60HMOLziOKwQwEYV7CbrLWQiLeCWKVxX\rvag\nAAEOhjER7gURuGXw\nMyY\t8mSw\x0b\x0bK0Z9G0Pt\x0bJZItAIqAq FxeaoOeLqWVFvxtDFfko0YVYt1I\rNmSXZ4lnOoiBCLbu6TLb80lClhY\tPN7Lp36F786I\nglwRK2oD45EtN SWW IF6uqKdf\x0czAcVycf\x0cBzHYnn1HAkU2Jluos0qwMGJ2m74z\nLd3\x0cIUVZmnRmHHWQGd1u2xmsZR\x0bfnml10ur6J\x0ba8xOZatiY 15Aq3KOGWdD3xQwqo\r5SKnnxH5tqU\rO\rZpJ\n7t7UUgfE\niWFgqWDpMeOG 1248M I\ro5B9Yed\r2aq2\tXxLn31s3hCV WEfQd60DKp6eFhUeUSeXDq6qjgTnWigoCZQERf\rXp7s2L37 iOEMl3\r41\nBShOjLfD8Kj0\rbu0ENreRjP\nY77jsrsaYgOsUrEzw\x0bw3OLi\n8fkddcaOvJeutTy B\rsDMkK\x0cnx2S0N\x0cDaY\x0c9iyo6p4IL\tOC1qgNlWP4VLg\tWmPG46ZMCirth5h4FwkS\nD2WsiEA2Z\n0xbLd7Uww hUQC6 3V\r1SsWem4UcQxG\rfuVvWl\nD9\nDpZQFFgiqhQiq1I0LMAR\r\rKBmj4iurrxaoMHTl9oj\x0b0N3AfD17gyqZiJ67bgizvecsRGeB1f\x0c\nYRvieJqIVHDKOOR\ruhqnVZz4BQ5FFBusz\x0cZl5\x0bt\tbdOUhAAAKyA6Jwl 7OjzojiRHGD6dl ncsgndsKURhFv4\tV5d\n73iPzbT\t8v6IrJtnq\nJuFl7A\x0b\rVnnsjTW0Y4QB1BgCy3B\x0cma7\tpPt5jmcJH7v5J\tYKEXh UqRChBFY5nbFbmXjJYxevPYJmSHC\rDQ4j9de\rTMZ\rtWaPAzkJjH\x0c\nyrEuf9WaMM\trFlKo9r9w\r\nQkQqIEu8Gfr\t aRzvN\r2oZhCyB4fa\np37\tXQi4Wa\no7gHUDQLoRvkK1dy2K3ydrI0O6\rFTGS7oHA\x0bajFOd\rcS5W25tFGhocwxM0\nuugNGDLjBQ\tWGdJV0\x0c\r7bNLs\x0cr deAWt35A4co\x0bPCuYmQ ExxtK\rvpckCyJxLrK5xULK\x0cvqtiGyovHQW8aDjV3rhXhR\nmQvmK\x0czLx\x0cECSYSF5jP35zN VkaRzQ lZ4 l06X4HHpsVn 8y8fGbIP\tRWFUAeFI24\rqN\x0cBW7u7WPMv36BmkgzQ\x0c2\x0cyLf\tYo8iRjE7zMsceym4ZnWg7EsOedh2cES\rz2n\x0cJi52uIPfSkAPzW\rEekjgWdb8y 285F4xae8\n8AiIkT4l3AOy\rT4yeXgaRMCI4t3PkHeFZ\rEb6R4FNCE \nbVil\x0c6qxSVPnU\nh\ttFMNE4\x0c\rwF\t\x0cW5vebbRWG\x0biVZLP\x0ct\x0c5gQ4CJ9KJl\x0cwyIfSIYaCvi4m1r\tJbYqmI0NVO36A\t8BSPNlaKbR73l9mxZxoqD4yca\n5h\r7a0z\tVm34aTy\tnLj5nSrh8er5lN0J7hcjmUk2DL\nyWEVNXTF8RWfC\x0bpcgBQXOQzidyYO\x0bh76UyUPAjELmNoECgGq06hiFGDI LiPZcofhcm\r62fEixIoyG\tmI\x0cYLQvBCbCluGgbm\x0c7GI6\n19il8PdPqss2uQqA5KgkHMIb hh211YuqV9kdmVnwyD63pz3p t58q6kHX\r\teYBrg6eDh\x0bx8\x0cI1SOV3Gt5qubmixHR\rApbgkTQJQ\tX0t11IP55hys2d\x0bF dh7j7G0Ac\x0bQMNvkSU9AV\x0b8mcIPHy9d\x0cyINf5qu\x0cdiBFrhiNRmCZ4r\tSx4N5VOm6KCp2T8bOVEjOR6otPAN5e\n\x0csyJ3giBjkgg 9dYQKq5P75AG5\x0bfD6zZO4DxQ44uX7Kz50dv4ncXQA\rqgHT\rLRcsRl\rW\t7We\tpAEJHMChxwVK\x0cprVvINvolf7hj\tUrob\rW3pXlqKIEQT8t7\x0bGODJanb328OiQCxE\rPfW4j\rl3p\x0cRXDB55u0MN7isBL\ty3UvE1 7I\nfuoZVPzk7az1\rMzA2FROXu0k\rFq pby6pHMqfTQT7iTw izlk0CUpyoUaq5w3UPFK7\rMOPw2cZ6FsVITbCoPhT\rIvuImCFGqmYpE hNevWkPCtwwnx2sX\x0c7oKzBExp32ZpdY\tstuDjSzfalsO1M\x0bNMUegnBDr3Liv3Lv\x0b\n37VZT2LEJ9fNYDi9r\t\x0bYC\rHSt0oJbk\x0b\x0bUdS8eB\nMXBPDEppZjHR7vGZYqX7yFm t1i682AXWf VPTzYTvm6mhOre8\x0bk0spJNYuI\tk\tC1B1N0 AYYDWH\t\tX1TjinXdkXcbFTlIiBLzx\rmUoyx9b7paJSVMX\tfLo8hU1Dmuluyk8R8\x0c4\x0cBe\nCrIMlyek4i\x0bFwuE9\nXUqpVxikH0PZspopUwPM9Kcue\rBh2Mf\rme3h4qelC\x0bEH\x0bkkxi6U\x0cE\x0ctqBgN93 V4ovmocLrK6\ngCQlf\x0cshRVvrPq\x0cOjgbjhSEK8PIx8OYqjjDDkJ0AgLhfbdGw2\nLMv2M0E08PGXnqUyVsjN\t C 4\n80 Fia g\x0b5dEFvyl5Y80U6sMAdHgk2nzC5ElDBhgcBprXC\x0bIMKXyt\x0ce5SkYcRartfblLqD1 A5\nre\x0bj67lJYCs\t8b50xA69eMHqGDLLP8sJceN19kkonjLj\t\rS\tk9sMOeewQHbT \x0cp53aMX9\x0bDYCZWAtdA6h\rAFHDEYFBE1MzdOxMO\x0cvDE7QfLb3jq4s\tI3aVTmDDOQAnuvWb2AGUUP\rf2HinUAiF13LKEfpqcD06S8aQC0Kyl729L7a6CbuoB0GRlJx tD yuTVqD62HuXpfKrDsbejEdp3\rxjc\x0bn4lLNaViizec\rWR\x0cTT5aZ\ny9\rO1qB1XGQPnES\nUhJtU Ll7t3Zglj1IAEx 8Rh3V\x0bfmUSC4\x0bVR9l33LS3bPAJpLbH3Q2\nv2fqMeIt3nGR\x0cgCixM4qzVSx7Yb192a1HWx8nnuWQIEK7QHL6p\x0cD3d0Y1FoZqsmY2U\rspvt3gwKOHR6RaZlmhX\n3bmIEF6\x0b\x0bMXJKOnXPgjkdhun4aGDBw\x0cOEW\repDYTcc48oZ4lg7PukNq7TU\tWP0ZJbzVKK\rxAMaZujwTqQXsXODiE2DdwnstAa6CMYfzj7J\x0c2Q\tY2764IYCy 3Fqm0\x0ckbe7VvfqWUh0\tUlubxZ\rX59MfNSfCfcH8GFZIGIRPt\rZVXfra1 H7VI2yJ\x0cspGDCi\rcgHfZa8528CP9tilUx0ifWPGqskLVDPLJP\nciNxodMQSrJXp\ro\r9aBFHCV\x0cR\rrp\x0bmMfxg5rG\tSuWonbJQlmHQ\ri34w8S\x0cN9Ezj2k2OmLH\x0cEcVUDjXNZIFCtlA843I44p GZyhlOctwpd7 OZnUxk4uacN\r8NihNGO\n9eXy5l6gQe5srySxxvuX5jtCzuJ35xvCfEXYa\x0b2lTDBOAaSYpnl v9L\x0cY8RLg2oE7xeCUbD\tSHKZgeXHZIzYAmA7bsmiZUfzmo5ZZUhtBh4F\x0bTx1\x0bz zQov5mYwfpWJTR2Q\x0bLRXMuBzj\x0bZC\x0b pFNPj8ixWJQggQlr9eNW6SHLJk731nc\x0cBn\x0ckQxg2BdRT\x0bp6lf7G\x0bnIMDeY8w6fUf\x0cjGE1Pfsekv7EYEIHsOAsZb3lBfBPO9\tXpHPBMRmRtzMc5WoX6C5cc\x0cBuTPtPOgXnap1Y3xq7pcMcgu55xblsXEAJKsojjR7aDB\tU84kUKRNEj\n8mcqEyOmvq1WA\na6bhzYf9VQv2aj9KLfByVqUKNFVIc4Mkha\x0c0aCPQSKe0GGwPlSfbtNXhdhxAb3RLf1J\x0cshJzjQe4DCmlRmjt\tlB0BwzBpkg2hTYM\r S\x0cux\x0bj6IcEZ\n\ngQ\rKKgg \rrv4sUMy5sfY1aatjK1MmUyXR\rRHk\x0cqq\x0cD1fy4C0\n\x0byd4SFKOyKJqx2mzI74vPxLLo\x0c0OamjXuUu\nWGkiA70nuf0PGRfwLEBPCMeyneJI1HcIXH\nCTFEIMiAq6fT\rmJgC hXEU\rriAhCm3OzgbcDgvQgDSyUw5jl\x0cTaLOPuFseq\x0cj2npTd57itktTdWBY7sqlOGKNSc\x0ctx2mUoHi31EF3l5lvYPDeG6bIPFwIn7\tG6G \x0bgNkSn89flvqcvI73RA";
+    let mutated = "VCiYFr0HKsEIK6r\r1hJLYnOr90Aji\rDWAjQA3LVAzrluN484327FuSPrRpm\n \tV\x0cx\nSCc5sX\nTB\x0c6Of7ns\t2HDwQCduKTqG8gG\x0beszazwljW01H60HMOLziOKwQwEYV7CbrLWQiLeCWKVxX\rvag\nAAEOhjER7gURuGXw\nMyY\t8mSw\x0b\x0bK0Z9G0Pt\x0bJZItAIqAq FxeaoOeLqWVFvxtDFfko0YVYt1I\rNmSXZ4lnOoiBCLbu6TLb80lClhY\tPN7Lp36F786I\nglwRK2oD45EtN SWW IF6uqKdf\x0czAcVycf\x0cBzHYnn1HAkU2Jluos0qwMGJ2m74z\nLd3\x0cIUVZmnRmHHWQGd1u2xmsZR\x0bfnml10ur6J\x0ba8xOZatiY 15Aq3KOGWdD3xQwqo\r5SKnnxH5tqU\rO\rZpJ\n7t7UUgfE\niWFgqWDpMeOG 1248M I\ro5B9Yed\r2aq2\tXxLn31s3hCV WEfQd60DKp6eFhUeUSeXDq6qjgTnWigoCZQERf\rXp7s2L37 iOEMl3\r41\nBShOjLfD8Kj0\rbu0ENreRjP\nY77jsrsaYgOsUrEzw\x0bw3OLi\n8fkddcaOvJeutTy B\rsDMkK\x0cnx2S0N\x0cDaY\x0c9iyo6p4IL\tOC1qgNlWP4VLg\tWmPG46ZMCirth5h4FwkS\nD2WsiEA2Z\n0xbLd7Uww hUQC6 3V\r1SsWem4UcQxG\rfuVvWl\nD9\nDpZQFFgiqhQiq1I0LMAR\r\rKBmj4iurrxaoMHTl9oj\x0b0N3AfD17gyqZiJ67bgizvecsRGeB1f\x0c\nYRvieJqIVHDKOOR\ruhqnVZz4BQ5FFBusz\x0cZl5\x0bt\tbdOUhAAAKyA6Jwl 7OjzojiRHGD6dl ncsgndsKURhFv4\tV5d\n73iPzbT\t8v6IrJtnq\nJuFl7A\x0b\rVnnsjTW0Y4QB1BgCy3B\x0cma7\tpPt5jmcJH7v5J\tYKEXh UqRChBFY5nbFbmXjJYxevPYJmSHC\rDQ4j9de\rTMZ\rtWaPAzkJjH\x0c\nyrEuf9WaMM\trFlKo9r9w\r\nQkQqIEu8Gfr\t aRzvN\r2oZhCyB4fa\np37\tXQi4Wa\no7gHUDQLoRvkK1dy2K3ydrI0O6\rFTGS7oHA\x0bajFOd\rcS5W25tFGhocwxM0\nuugNGDLjBQ\tWGdJV0\x0c\r7bNLs\x0cr deAWt35A4co\x0bPCuYmQ ExxtK\rvpckCyJxLrK5xULK\x0cvqtiGyovHQW8aDjV3rhXhR\nmQvmK\x0czLx\x0cECSYSF5jP35zN VkaRzQ lZ4 l06X4HHpsVn 8y8fGbIP\tRWFUAeFI24\rqN\x0cBW7u7WPMv36BmkgzQ\x0c2\x0cyLf\tYo8iRjE7zMsceym4ZnWg7EsOedh2cES\rz2n\x0cJi52uIPfSkAPzW\rEekjgWdb8y 285F4xae8\n8AiIkT4l3AOy\rT4yeXgaRMCI4t3PkHeFZ\rEb6R4FNCE \nbVil\x0c6qxSVPnU\nh\ttFMNE4\x0c\rwF\t\x0cW5vebbRWG\x0biVZLP\x0ct\x0c5gQ4CJ9KJl\x0cwyIfSIYaCvi4m1r\tJbYqmI0NVO36A\t8BSPNlaKbR73l9mxZxoqD4yca\n5h\r7a0z\tVm34aTy\tnLj5nSrh8er5lN0J7hcjmUk2DL\nyWEVNXTF8RWfC\x0bpcgBQXOQzidyYO\x0bh76UyUPAjELmNoECgGq06hiFGDI LiPZcofhcm\r62fEixIoyG\tmI\x0cYLQvBCbCluGgbm\x0c7GI6\n19il8PdPqss2uQqA5KgkHMIb hh211YuqV9kdmVnwyD63pz3p t58q6kHX\r\teYBrg6eDh\x0bx8\x0cI1SOV3Gt5qubmixHR\rApbgkTQJQ\tX0t11IP55hys2d\x0bF dh7j7G0Ac\x0bQMNvkSU9AV\x0b8mcIPHy9d\x0cyINf5qu\x0cdiBFrhiNRmCZ4r\tSx4N5VOm6KCp2T8bOVEjOR6otPAN5e\n\x0csyJ3giBjkgg 9dYQKq5P75AG5\x0bfD6zZO4DxQ44uX7Kz50dv4ncXQA\rqgHT\rLRcsRl\rW\t7We\tpAEJHMChxwVK\x0cprVvINvolf7hj\tUrob\rW3pXlqKIEQT8t7\x0bGODJanb328OiQCxE\rPfW4j\rl3p\x0cRXDB55u0MN7isBL\ty3UvE1 7I\nfuoZVPzk7az1\rMzA2FROXu0k\rFq pby6pHMqfTQT7iTw izlk0CUpyoUaq5w3UPFK7\rMOPw2cZ6FsVITbCoPhT\rIvuImCFGqmYpE hNevWkPCtwwnx2sX\x0c7oKzBExp32ZpdY\tstuDjSzfalsO1M\x0bNMUegnBDr3Liv3Lv\x0b\n37VZT2LEJ9fNYDi9r\t\x0bYC\rHSt0oJbk\x0b\x0bUdS8eB\nMXBPDEppZjHR7vGZYqX7yFm t1i682AXWf VPTzYTvm6mhOre8\x0bk0spJNYuI\tk\tC1B1N0 AYYDWH\t\tX1TjinXdkXcbFTlIiBLzx\rmUoyx9b7paJSVMX\tfLo8hU1Dmuluyk8R8\x0c4\x0cBe\nCrIMlyek4i\x0bFwuE9\nXUqpVxikH0PZspopUwPM9Kcue\rBh2Mf\rme3h4qelC\x0bEH\x0bkkxi6U\x0cE\x0ctqBgN93 V4ovmocLrK6\ngCQlf\x0cshRVvrPq\x0cOjgbjhSEK8PIx8OYqjjDDkJ0AgLhfbdGw2\nLMv2M0E08PGXnqUyVsjN\t C 4\n80 Fia g\x0b5dEFvyl5Y80U6sMAdHgk2nzC5ElDBhgcBprXC\x0bIMKXyt\x0ce5SkYcRartfblLqD1 A5\nre\x0bj67lJYCs\t8b50xA69eMHqGDLLP8sJceN19kkonjLj\t\rS\tk9sMOeewQHbT \x0cp53aMX9\x0bDYCZWAtdA6h\rAFHDEYFBE1MzdOxMO\x0cvDE7QfLb3jq4s\tI3aVTmDDOQAnuvWb2AGUUP\rf2HinUAiF13LKEfpqcD06S8aQC0Kyl729L7a6CbuoB0GRlJx tD yuTVqD62HuXpfKrDsbejEdp3\rxjc\x0bn4lLNaViizec\rWR\x0cTT5aZ\ny9\rO1qB1XGQPnES\nUhJtU Ll7t3Zglj1IAEx 8Rh3V\x0bfmUSC4\x0bVR9l33LS3bPAJpLbH3Q2\nv2fqMeIt3nGR\x0cgCixM4qzVSx7Yb192a1HWx8nnuWQIEK7QHL6p\x0cD3d0Y1FoZqsmY2U\rspvt3gwKOHR6RaZlmhX\n3bmIEF6\x0b\x0bMXJKOnXPgjkdhun4aGDBw\x0cOEW\repDYTcc48oZ4lg7PukNq7TU\tWP0ZJbzVKK\rxAMaZujwTqQXsXODiE2DdwnstAa6CMYfzj7J\x0c2Q\tY2764IYCy 3Fqm0\x0ckbe7VvfqWUh0\tUlubxZ\rX59MfNSfCfcH8GFZIGIRPt\rZVXfra1 H7VI2yJ\x0cspGDCi\rcgHfZa8528CP9tilUx0ifWPGqskLVDPLJP\nciNxodMQSrJXp\ro\r9aBFHCV\x0cR\rrp\x0bmMfxg5rG\tSuWonbJQlmHQ\ri34w8S\x0cN9Ezj2k2OmLH\x0cEcVUDjXNZIFCtlA843I44p GZyhlOctwpd7 OZnUxk4uacN\r8NihNGO\n9eXy5l6gQe5srySxxvuX5jtCzuJ35xvCfEXYa\x0b2lTDBOAaSYpnl v9L\x0cY8RLg2oE7xeCUbD\tSHKZgeXHZIzYAmA7bsmiZUfzmo5ZZUhtBh4F\x0bTx1\x0bz zQov5mYwfpWJTR2Q\x0bLRXMuBzj\x0bZC\x0b pFNPj8ixWJQggQlr9eNW6SHLJk731nc\x0cBn\x0ckQxg2BdRT\x0bp6lf7G\x0bnIMDeY8w6fUf\x0cjGE1Pfsekv7EYEIHsOAsZb3lBfBPO9\tXpHPBMRmRtzMc5WoX6C5cc\x0cBuTPtPOgXnap1Y3xq7pcMcgu55xblsXEAJKsojjR7aDB\tU84kUKRNEj\n8mcqEyOmvq1WA\na6bhzYf9VQv2aj9KLfByVqUKNFVIc4Mkha\x0c0aCPQSKe0GGwPlSfbtNXhdhxAb3RLf1J\x0cshJzjQe4DCmlRmjt\tlB0BwzBpkg2hTYM\r S\x0cux\x0bj6IcEZ\n\ngQ\rKKgg \rrv4sUMy5sfY1aatjK1MmUyXR\rRHk\x0cqq\x0cD1fy4C0\n\x0byd4SFKOyKJqx2mzI74vPxLLo\x0c0OamjXuUu\nWGkiA70nuf0PGRfwLEBPCMeyneJI1HcIXH\nCTFEIMiAq6fT\rmJgC hXEU\rriAhCm3OzgbcDgvQgDSyUw5jl\x0cTaimauFseq\x0cj2npTd57itktTdWBY7sqlOGKNSc\x0ctx2mUoHi31EF3l5lvYPDeG6bIPFwIn7\tG6G \x0bgNkSn89flvqcvI73RA";
+
+    let canary = srv.mock(|when, then| {
+        when.method(GET).path("/canary");
+        then.status(200).body(content);
+    });
+
+    // not similar, should see results in output
+    let not_similar = srv.mock(|when, then| {
+        when.method(GET).path("/not-similar");
+        then.status(302).body("this is a test");
+    });
+
+    // similar, should not see results
+    let similar = srv.mock(|when, then| {
+        when.method(GET).path("/similar");
+        then.status(200).body(mutated);
+    });
+
+    let cmd = Command::cargo_bin("feroxbuster")
+        .unwrap()
+        .arg("--url")
+        .arg(srv.url("/"))
+        .arg("--wordlist")
+        .arg(file.as_os_str())
+        .arg("--filter-similar-to")
+        .arg(srv.url("/canary"))
+        .unwrap();
+
+    cmd.assert().success().stdout(
+        predicate::str::contains("/LICfdafdsafdsafadsENSE")
+            .and(predicate::str::contains("302"))
+            .and(predicate::str::contains("14c"))
+            .and(predicate::str::contains("/similar"))
+            .not()
+            .and(predicate::str::contains("4100c"))
+            .not(),
+    );
+
+    assert_eq!(canary.hits(), 1);
+    assert_eq!(similar.hits(), 1);
+    assert_eq!(not_similar.hits(), 1);
+    teardown_tmp_directory(tmp_dir);
+}

tests/test_heuristics.rs

@@ -90,6 +90,50 @@ fn test_one_good_and_one_bad_target_scan_succeeds() -> Result<(), Box<dyn std::e
     Ok(())
 }
 
+#[test]
+/// test pipes two good targets to the scanner, expected result is that both targets
+/// are scanned successfully and no error is reported (result of issue #169)
+fn test_two_good_targets_scan_succeeds() -> Result<(), Box<dyn std::error::Error>> {
+    let srv = MockServer::start();
+    let srv2 = MockServer::start();
+
+    let urls = vec![srv.url("/"), srv2.url("/"), String::from("LICENSE")];
+    let (tmp_dir, file) = setup_tmp_directory(&urls, "wordlist")?;
+
+    let mock = srv.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(200).body("this is a test");
+    });
+
+    let mock2 = srv2.mock(|when, then| {
+        when.method(GET).path("/LICENSE");
+        then.status(403).body("this also is a test");
+    });
+
+    let mut cmd = Command::cargo_bin("feroxbuster").unwrap();
+
+    cmd.arg("--stdin")
+        .arg("--wordlist")
+        .arg(file.as_os_str())
+        .pipe_stdin(file)
+        .unwrap()
+        .assert()
+        .success()
+        .stdout(
+            predicate::str::contains("/LICENSE")
+                .and(predicate::str::contains("200"))
+                .and(predicate::str::contains("403"))
+                .and(predicate::str::contains("14c"))
+                .and(predicate::str::contains("19c")),
+        );
+
+    assert_eq!(mock.hits(), 1);
+    assert_eq!(mock2.hits(), 1);
+
+    teardown_tmp_directory(tmp_dir);
+    Ok(())
+}
+
 #[test]
 /// test finds a static wildcard and reports as much to stdout
 fn test_static_wildcard_request_found() -> Result<(), Box<dyn std::error::Error>> {