Rename botdetection to blockbot

Adding composer/vendor to blockbot

blockbot/vendor/jaybizzle/crawler-detect/LICENSE

@@ -0,0 +1,22 @@
+The MIT License (MIT)
+
+Copyright (c) 2015-2018 Mark Beech
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+

blockbot/vendor/jaybizzle/crawler-detect/README.md

@@ -0,0 +1,72 @@
+<p align="center"><a href="http://crawlerdetect.io/" target="_blank"><img src="https://cloud.githubusercontent.com/assets/340752/23082173/1bd1a396-f550-11e6-8aba-4d3c75edea2f.png" width="321" height="219" /></a><br><br>
+<a href="http://crawlerdetect.io/" target="_blank">crawlerdetect.io</a>
+<br><br>
+</p>
+
+<p align="center">
+<a href="https://travis-ci.org/JayBizzle/Crawler-Detect"><img src="https://img.shields.io/travis/JayBizzle/Crawler-Detect/master.svg?style=flat-square" /></a>
+<a href="https://packagist.org/packages/jaybizzle/crawler-detect"><img src="https://img.shields.io/packagist/dm/JayBizzle/Crawler-Detect.svg?style=flat-square" /></a>
+<a href="https://scrutinizer-ci.com/g/JayBizzle/Crawler-Detect/?branch=master"><img src="https://img.shields.io/scrutinizer/g/JayBizzle/Crawler-Detect.svg?style=flat-square" /></a>
+<a href="https://github.com/JayBizzle/Crawler-Detect"><img src="https://img.shields.io/badge/license-MIT-ff69b4.svg?style=flat-square" /></a>
+<a href="https://packagist.org/packages/jaybizzle/crawler-detect"><img src="https://img.shields.io/packagist/v/jaybizzle/Crawler-Detect.svg?style=flat-square" /></a>
+<a href="https://styleci.io/repos/32755917"><img src="https://styleci.io/repos/32755917/shield" /></a>
+<a href="https://coveralls.io/github/JayBizzle/Crawler-Detect"><img src="https://img.shields.io/coveralls/JayBizzle/Crawler-Detect/master.svg?style=flat-square" /></a>
+</p>
+
+## About CrawlerDetect
+
+CrawlerDetect is a PHP class for detecting bots/crawlers/spiders via the user agent and http_from header. Currently able to detect 1,000's of bots/spiders/crawlers.
+
+### Installation
+Run `composer require jaybizzle/crawler-detect 1.*` or add `"jaybizzle/crawler-detect" :"1.*"` to your `composer.json`.
+
+### Usage
+```PHP
+use Jaybizzle\CrawlerDetect\CrawlerDetect;
+
+$CrawlerDetect = new CrawlerDetect;
+
+// Check the user agent of the current 'visitor'
+if($CrawlerDetect->isCrawler()) {
+    // true if crawler user agent detected
+}
+
+// Pass a user agent as a string
+if($CrawlerDetect->isCrawler('Mozilla/5.0 (compatible; Sosospider/2.0; +http://help.soso.com/webspider.htm)')) {
+    // true if crawler user agent detected
+}
+
+// Output the name of the bot that matched (if any)
+echo $CrawlerDetect->getMatches();
+```
+
+### Contributing
+If you find a bot/spider/crawler user agent that CrawlerDetect fails to detect, please submit a pull request with the regex pattern added to the `$data` array in `Fixtures/Crawlers.php` and add the failing user agent to `tests/crawlers.txt`.
+
+Failing that, just create an issue with the user agent you have found, and we'll take it from there :)
+
+### Laravel Package
+If you would like to use this with Laravel 4/5, please see [Laravel-Crawler-Detect](https://github.com/JayBizzle/Laravel-Crawler-Detect)
+
+### Symfony Bundle
+To use this library with Symfony 2/3/4, check out the [CrawlerDetectBundle](https://github.com/nicolasmure/CrawlerDetectBundle).
+
+### YII2 Extension
+To use this library with the YII2 framework, check out [yii2-crawler-detect](https://github.com/AlikDex/yii2-crawler-detect).
+
+### ES6 Library
+To use this library with NodeJS or any ES6 application based, check out [es6-crawler-detect](https://github.com/JefferyHus/es6-crawler-detect).
+
+### .NET Library
+To use this library in a .net standard (including .net core) based project, check out [NetCrawlerDetect](https://github.com/gplumb/NetCrawlerDetect).
+
+### Nette Extension
+To use this library with the Nette framework, checkout [NetteCrawlerDetect](https://github.com/JanGalek/Crawler-Detect).
+
+### Ruby Gem
+
+To use this library with Ruby on Rails or any Ruby-based application, check out [crawler_detect](https://github.com/loadkpi/crawler_detect) gem.
+
+_Parts of this class are based on the brilliant [MobileDetect](https://github.com/serbanghita/Mobile-Detect)_
+
+[![Analytics](https://ga-beacon.appspot.com/UA-72430465-1/Crawler-Detect/readme?pixel)](https://github.com/JayBizzle/Crawler-Detect)

blockbot/vendor/jaybizzle/crawler-detect/composer.json

@@ -0,0 +1,30 @@
+{
+    "name": "jaybizzle/crawler-detect",
+    "type": "library",
+    "description": "CrawlerDetect is a PHP class for detecting bots/crawlers/spiders via the user agent",
+    "keywords": ["crawler", "crawler detect", "crawler detector", "crawlerdetect", "php crawler detect"],
+    "homepage": "https://github.com/JayBizzle/Crawler-Detect/",
+    "license": "MIT",
+    "authors": [
+        {
+            "name": "Mark Beech",
+            "email": "m@rkbee.ch",
+            "role": "Developer"
+        }
+    ],
+    "require": {
+        "php": ">=5.3.0"
+    },
+    "require-dev": {
+        "phpunit/phpunit": "^4.8|^5.5|^6.5",
+        "satooshi/php-coveralls": "1.*"
+    },
+    "autoload": {
+        "psr-4": {
+            "Jaybizzle\\CrawlerDetect\\": "src/"
+        }
+    },
+    "scripts": {
+        "test": "vendor/bin/phpunit"
+    }
+}

blockbot/vendor/jaybizzle/crawler-detect/export.php

@@ -0,0 +1,41 @@
+<?php
+
+/*
+ * This file is part of Crawler Detect - the web crawler detection library.
+ *
+ * (c) Mark Beech <m@rkbee.ch>
+ *
+ * This source file is subject to the MIT license that is bundled
+ * with this source code in the file LICENSE.
+ */
+
+require 'src/Fixtures/AbstractProvider.php';
+require 'src/Fixtures/Crawlers.php';
+require 'src/Fixtures/Exclusions.php';
+require 'src/Fixtures/Headers.php';
+
+$src = array(
+    'Crawlers',
+    'Exclusions',
+    'Headers',
+);
+
+foreach ($src as $class) {
+    $class = "Jaybizzle\\CrawlerDetect\\Fixtures\\$class";
+    $object = new $class;
+
+    outputJson($object);
+    outputTxt($object);
+}
+
+function outputJson($object)
+{
+    $className = (new ReflectionClass($object))->getShortName();
+    file_put_contents("raw/$className.json", json_encode($object->getAll()));
+}
+
+function outputTxt($object)
+{
+    $className = (new ReflectionClass($object))->getShortName();
+    file_put_contents("raw/$className.txt", implode($object->getAll(), PHP_EOL));
+}

blockbot/vendor/jaybizzle/crawler-detect/raw/Exclusions.json

@@ -0,0 +1 @@
+["Safari.[\\d\\.]*","Firefox.[\\d\\.]*"," Chrome.[\\d\\.]*","Chromium.[\\d\\.]*","MSIE.[\\d\\.]","Opera\\\/[\\d\\.]*","Mozilla.[\\d\\.]*","AppleWebKit.[\\d\\.]*","Trident.[\\d\\.]*","Windows NT.[\\d\\.]*","Android [\\d\\.]*","Macintosh.","Ubuntu","Linux","[ ]Intel","Mac OS X [\\d_]*","(like )?Gecko(.[\\d\\.]*)?","KHTML,","CriOS.[\\d\\.]*","CPU iPhone OS ([0-9_])* like Mac OS X","CPU OS ([0-9_])* like Mac OS X","iPod","compatible","x86_..","i686","x64","X11","rv:[\\d\\.]*","Version.[\\d\\.]*","WOW64","Win64","Dalvik.[\\d\\.]*"," \\.NET CLR [\\d\\.]*","Presto.[\\d\\.]*","Media Center PC","BlackBerry","Build","Opera Mini\\\/\\d{1,2}\\.\\d{1,2}\\.[\\d\\.]*\\\/\\d{1,2}\\.","Opera"," \\.NET[\\d\\.]*","cubot","; M bot","; CRONO","; B bot","; IDbot","; ID bot","; POWER BOT",";"]

blockbot/vendor/jaybizzle/crawler-detect/raw/Exclusions.txt

@@ -0,0 +1,48 @@
+Safari.[\d\.]*
+Firefox.[\d\.]*
+ Chrome.[\d\.]*
+Chromium.[\d\.]*
+MSIE.[\d\.]
+Opera\/[\d\.]*
+Mozilla.[\d\.]*
+AppleWebKit.[\d\.]*
+Trident.[\d\.]*
+Windows NT.[\d\.]*
+Android [\d\.]*
+Macintosh.
+Ubuntu
+Linux
+[ ]Intel
+Mac OS X [\d_]*
+(like )?Gecko(.[\d\.]*)?
+KHTML,
+CriOS.[\d\.]*
+CPU iPhone OS ([0-9_])* like Mac OS X
+CPU OS ([0-9_])* like Mac OS X
+iPod
+compatible
+x86_..
+i686
+x64
+X11
+rv:[\d\.]*
+Version.[\d\.]*
+WOW64
+Win64
+Dalvik.[\d\.]*
+ \.NET CLR [\d\.]*
+Presto.[\d\.]*
+Media Center PC
+BlackBerry
+Build
+Opera Mini\/\d{1,2}\.\d{1,2}\.[\d\.]*\/\d{1,2}\.
+Opera
+ \.NET[\d\.]*
+cubot
+; M bot
+; CRONO
+; B bot
+; IDbot
+; ID bot
+; POWER BOT
+;

blockbot/vendor/jaybizzle/crawler-detect/raw/Headers.json

@@ -0,0 +1 @@
+["HTTP_USER_AGENT","HTTP_X_OPERAMINI_PHONE_UA","HTTP_X_DEVICE_USER_AGENT","HTTP_X_ORIGINAL_USER_AGENT","HTTP_X_SKYFIRE_PHONE","HTTP_X_BOLT_PHONE_UA","HTTP_DEVICE_STOCK_UA","HTTP_X_UCBROWSER_DEVICE_UA","HTTP_FROM","HTTP_X_SCANNER"]

blockbot/vendor/jaybizzle/crawler-detect/raw/Headers.txt

@@ -0,0 +1,10 @@
+HTTP_USER_AGENT
+HTTP_X_OPERAMINI_PHONE_UA
+HTTP_X_DEVICE_USER_AGENT
+HTTP_X_ORIGINAL_USER_AGENT
+HTTP_X_SKYFIRE_PHONE
+HTTP_X_BOLT_PHONE_UA
+HTTP_DEVICE_STOCK_UA
+HTTP_X_UCBROWSER_DEVICE_UA
+HTTP_FROM
+HTTP_X_SCANNER

blockbot/vendor/jaybizzle/crawler-detect/src/CrawlerDetect.php

@@ -0,0 +1,193 @@
+<?php
+
+/*
+ * This file is part of Crawler Detect - the web crawler detection library.
+ *
+ * (c) Mark Beech <m@rkbee.ch>
+ *
+ * This source file is subject to the MIT license that is bundled
+ * with this source code in the file LICENSE.
+ */
+
+namespace Jaybizzle\CrawlerDetect;
+
+use Jaybizzle\CrawlerDetect\Fixtures\Crawlers;
+use Jaybizzle\CrawlerDetect\Fixtures\Exclusions;
+use Jaybizzle\CrawlerDetect\Fixtures\Headers;
+
+class CrawlerDetect
+{
+    /**
+     * The user agent.
+     *
+     * @var null
+     */
+    protected $userAgent = null;
+
+    /**
+     * Headers that contain a user agent.
+     *
+     * @var array
+     */
+    protected $httpHeaders = array();
+
+    /**
+     * Store regex matches.
+     *
+     * @var array
+     */
+    protected $matches = array();
+
+    /**
+     * Crawlers object.
+     *
+     * @var \Jaybizzle\CrawlerDetect\Fixtures\Crawlers
+     */
+    protected $crawlers;
+
+    /**
+     * Exclusions object.
+     *
+     * @var \Jaybizzle\CrawlerDetect\Fixtures\Exclusions
+     */
+    protected $exclusions;
+
+    /**
+     * Headers object.
+     *
+     * @var \Jaybizzle\CrawlerDetect\Fixtures\Headers
+     */
+    protected $uaHttpHeaders;
+
+    /**
+     * The compiled regex string.
+     *
+     * @var string
+     */
+    protected $compiledRegex;
+
+    /**
+     * The compiled exclusions regex string.
+     *
+     * @var string
+     */
+    protected $compiledExclusions;
+
+    /**
+     * Class constructor.
+     */
+    public function __construct(array $headers = null, $userAgent = null)
+    {
+        $this->crawlers = new Crawlers();
+        $this->exclusions = new Exclusions();
+        $this->uaHttpHeaders = new Headers();
+
+        $this->compiledRegex = $this->compileRegex($this->crawlers->getAll());
+        $this->compiledExclusions = $this->compileRegex($this->exclusions->getAll());
+
+        $this->setHttpHeaders($headers);
+        $this->setUserAgent($userAgent);
+    }
+
+    /**
+     * Compile the regex patterns into one regex string.
+     *
+     * @param array
+     * 
+     * @return string
+     */
+    public function compileRegex($patterns)
+    {
+        return '('.implode('|', $patterns).')';
+    }
+
+    /**
+     * Set HTTP headers.
+     *
+     * @param array|null $httpHeaders
+     */
+    public function setHttpHeaders($httpHeaders)
+    {
+        // Use global _SERVER if $httpHeaders aren't defined.
+        if (! is_array($httpHeaders) || ! count($httpHeaders)) {
+            $httpHeaders = $_SERVER;
+        }
+
+        // Clear existing headers.
+        $this->httpHeaders = array();
+
+        // Only save HTTP headers. In PHP land, that means
+        // only _SERVER vars that start with HTTP_.
+        foreach ($httpHeaders as $key => $value) {
+            if (strpos($key, 'HTTP_') === 0) {
+                $this->httpHeaders[$key] = $value;
+            }
+        }
+    }
+
+    /**
+     * Return user agent headers.
+     *
+     * @return array
+     */
+    public function getUaHttpHeaders()
+    {
+        return $this->uaHttpHeaders->getAll();
+    }
+
+    /**
+     * Set the user agent.
+     *
+     * @param string $userAgent
+     */
+    public function setUserAgent($userAgent)
+    {
+        if (is_null($userAgent)) {
+            foreach ($this->getUaHttpHeaders() as $altHeader) {
+                if (isset($this->httpHeaders[$altHeader])) {
+                    $userAgent .= $this->httpHeaders[$altHeader].' ';
+                }
+            }
+        }
+
+        return $this->userAgent = $userAgent;
+    }
+
+    /**
+     * Check user agent string against the regex.
+     *
+     * @param string|null $userAgent
+     *
+     * @return bool
+     */
+    public function isCrawler($userAgent = null)
+    {
+        $agent = trim(preg_replace(
+            "/{$this->compiledExclusions}/i",
+            '',
+            $userAgent ?: $this->userAgent
+        ));
+
+        if ($agent == '') {
+            return false;
+        }
+
+        $result = preg_match("/{$this->compiledRegex}/i", $agent, $matches);
+
+        if ($matches) {
+            $this->matches = $matches;
+        }
+
+        return (bool) $result;
+    }
+
+    /**
+     * Return the matches.
+     *
+     * @return string|null
+     */
+    public function getMatches()
+    {
+        return isset($this->matches[0]) ? $this->matches[0] : null;
+    }
+}

blockbot/vendor/jaybizzle/crawler-detect/src/Fixtures/AbstractProvider.php

@@ -0,0 +1,32 @@
+<?php
+
+/*
+ * This file is part of Crawler Detect - the web crawler detection library.
+ *
+ * (c) Mark Beech <m@rkbee.ch>
+ *
+ * This source file is subject to the MIT license that is bundled
+ * with this source code in the file LICENSE.
+ */
+
+namespace Jaybizzle\CrawlerDetect\Fixtures;
+
+abstract class AbstractProvider
+{
+    /**
+     * The data set.
+     * 
+     * @var array
+     */
+    protected $data;
+
+    /**
+     * Return the data set.
+     * 
+     * @return array
+     */
+    public function getAll()
+    {
+        return $this->data;
+    }
+}

blockbot/vendor/jaybizzle/crawler-detect/src/Fixtures/Exclusions.php

@@ -0,0 +1,72 @@
+<?php
+
+/*
+ * This file is part of Crawler Detect - the web crawler detection library.
+ *
+ * (c) Mark Beech <m@rkbee.ch>
+ *
+ * This source file is subject to the MIT license that is bundled
+ * with this source code in the file LICENSE.
+ */
+
+namespace Jaybizzle\CrawlerDetect\Fixtures;
+
+class Exclusions extends AbstractProvider
+{
+    /**
+     * List of strings to remove from the user agent before running the crawler regex
+     * Over a large list of user agents, this gives us about a 55% speed increase!
+     *
+     * @var array
+     */
+    protected $data = array(
+        'Safari.[\d\.]*',
+        'Firefox.[\d\.]*',
+        ' Chrome.[\d\.]*',
+        'Chromium.[\d\.]*',
+        'MSIE.[\d\.]',
+        'Opera\/[\d\.]*',
+        'Mozilla.[\d\.]*',
+        'AppleWebKit.[\d\.]*',
+        'Trident.[\d\.]*',
+        'Windows NT.[\d\.]*',
+        'Android [\d\.]*',
+        'Macintosh.',
+        'Ubuntu',
+        'Linux',
+        '[ ]Intel',
+        'Mac OS X [\d_]*',
+        '(like )?Gecko(.[\d\.]*)?',
+        'KHTML,',
+        'CriOS.[\d\.]*',
+        'CPU iPhone OS ([0-9_])* like Mac OS X',
+        'CPU OS ([0-9_])* like Mac OS X',
+        'iPod',
+        'compatible',
+        'x86_..',
+        'i686',
+        'x64',
+        'X11',
+        'rv:[\d\.]*',
+        'Version.[\d\.]*',
+        'WOW64',
+        'Win64',
+        'Dalvik.[\d\.]*',
+        ' \.NET CLR [\d\.]*',
+        'Presto.[\d\.]*',
+        'Media Center PC',
+        'BlackBerry',
+        'Build',
+        'Opera Mini\/\d{1,2}\.\d{1,2}\.[\d\.]*\/\d{1,2}\.',
+        'Opera',
+        ' \.NET[\d\.]*',
+        'cubot',
+        '; M bot',
+        '; CRONO',
+        '; B bot',
+        '; IDbot',
+        '; ID bot',
+        '; POWER BOT',
+        ';', // Remove the following characters ;
+    );
+}

blockbot/vendor/jaybizzle/crawler-detect/src/Fixtures/Headers.php

@@ -0,0 +1,37 @@
+<?php
+
+/*
+ * This file is part of Crawler Detect - the web crawler detection library.
+ *
+ * (c) Mark Beech <m@rkbee.ch>
+ *
+ * This source file is subject to the MIT license that is bundled
+ * with this source code in the file LICENSE.
+ */
+
+namespace Jaybizzle\CrawlerDetect\Fixtures;
+
+class Headers extends AbstractProvider
+{
+    /**
+     * All possible HTTP headers that represent the user agent string.
+     *
+     * @var array
+     */
+    protected $data = array(
+        // The default User-Agent string.
+        'HTTP_USER_AGENT',
+        // Header can occur on devices using Opera Mini.
+        'HTTP_X_OPERAMINI_PHONE_UA',
+        // Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/
+        'HTTP_X_DEVICE_USER_AGENT',
+        'HTTP_X_ORIGINAL_USER_AGENT',
+        'HTTP_X_SKYFIRE_PHONE',
+        'HTTP_X_BOLT_PHONE_UA',
+        'HTTP_DEVICE_STOCK_UA',
+        'HTTP_X_UCBROWSER_DEVICE_UA',
+        // Sometimes, bots (especially Google) use a genuine user agent, but fill this header in with their email address
+        'HTTP_FROM',
+        'HTTP_X_SCANNER', // Seen in use by Netsparker
+    );
+}