Rename botdetection to blockbot

Adding composer/vendor to blockbot

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
+    );
+}