Completed
Pull Request — master (#42)
by Mark
10:06
created
src/CrawlerDetect.php 1 patch
Indentation   +339 added lines, -339 removed lines patch added patch discarded remove patch
@@ -4,361 +4,361 @@
 block discarded – undo
4 4
 
5 5
 class CrawlerDetect
6 6
 {
7
-    protected $userAgent = null;
7
+	protected $userAgent = null;
8 8
 
9
-    protected $httpHeaders = array();
9
+	protected $httpHeaders = array();
10 10
 
11
-    protected $matches = array();
11
+	protected $matches = array();
12 12
 
13
-    /**
14
-     * List of strings to remove from the user agent before running the crawler regex
15
-     * Over a large list of user agents, this gives us about a 55% speed increase!
16
-     * 
17
-     * @var array
18
-     */
19
-    protected static $ignore = array(
20
-        'Safari.[\d\.]*',
21
-        'Firefox.[\d\.]*',
22
-        'Chrome.[\d\.]*',
23
-        'Chromium.[\d\.]*',
24
-        'MSIE.[\d\.]',
25
-        'Opera\/[\d\.]*',
26
-        'Mozilla.[\d\.]*',
27
-        'AppleWebKit.[\d\.]*',
28
-        'Trident.[\d\.]*',
29
-        'Windows NT.[\d\.]*',
30
-        'Android.[\d\.]*',
31
-        'Macintosh.',
32
-        'Ubuntu',
33
-        'Linux',
34
-        'Intel',
35
-        'Mac OS X',
36
-        'Gecko.[\d\.]*',
37
-        'KHTML',
38
-        'CriOS.[\d\.]*',
39
-        'CPU iPhone OS ([0-9_])* like Mac OS X',
40
-        'CPU OS ([0-9_])* like Mac OS X',
41
-        'iPod',
42
-        'like Gecko',
43
-        'compatible',
44
-        'x86_..',
45
-        'i686',
46
-        'x64',
47
-        'X11',
48
-        'rv:[\d\.]*',
49
-        'Version.[\d\.]*',
50
-        'WOW64',
51
-        'Win64',
52
-        'Dalvik.[\d\.]*',
53
-        '\.NET CLR [\d\.]*',
54
-        'Presto.[\d\.]*',
55
-        'Media Center PC',
56
-    );
13
+	/**
14
+	 * List of strings to remove from the user agent before running the crawler regex
15
+	 * Over a large list of user agents, this gives us about a 55% speed increase!
16
+	 * 
17
+	 * @var array
18
+	 */
19
+	protected static $ignore = array(
20
+		'Safari.[\d\.]*',
21
+		'Firefox.[\d\.]*',
22
+		'Chrome.[\d\.]*',
23
+		'Chromium.[\d\.]*',
24
+		'MSIE.[\d\.]',
25
+		'Opera\/[\d\.]*',
26
+		'Mozilla.[\d\.]*',
27
+		'AppleWebKit.[\d\.]*',
28
+		'Trident.[\d\.]*',
29
+		'Windows NT.[\d\.]*',
30
+		'Android.[\d\.]*',
31
+		'Macintosh.',
32
+		'Ubuntu',
33
+		'Linux',
34
+		'Intel',
35
+		'Mac OS X',
36
+		'Gecko.[\d\.]*',
37
+		'KHTML',
38
+		'CriOS.[\d\.]*',
39
+		'CPU iPhone OS ([0-9_])* like Mac OS X',
40
+		'CPU OS ([0-9_])* like Mac OS X',
41
+		'iPod',
42
+		'like Gecko',
43
+		'compatible',
44
+		'x86_..',
45
+		'i686',
46
+		'x64',
47
+		'X11',
48
+		'rv:[\d\.]*',
49
+		'Version.[\d\.]*',
50
+		'WOW64',
51
+		'Win64',
52
+		'Dalvik.[\d\.]*',
53
+		'\.NET CLR [\d\.]*',
54
+		'Presto.[\d\.]*',
55
+		'Media Center PC',
56
+	);
57 57
 
58
-    protected static $crawlers = array(
59
-        '008\\/',
60
-        'A6-Indexer',
61
-        'Aboundex',
62
-        'Accoona-AI-Agent',
63
-        'acoon',
64
-        'AddThis',
65
-        'ADmantX',
66
-        'AHC',
67
-        'Airmail',
68
-        'Anemone',
69
-        'Arachmo',
70
-        'archive-com',
71
-        'B-l-i-t-z-B-O-T',
72
-        'bibnum\.bnf',
73
-        'biglotron',
74
-        'binlar',
75
-        'boitho\.com-dc',
76
-        'BUbiNG',
77
-        'Butterfly\\/',
78
-        'BuzzSumo',
79
-        'CC Metadata Scaper',
80
-        'Cerberian Drtrs',
81
-        'changedetection',
82
-        'Charlotte',
83
-        'clips\.ua\.ac\.be',
84
-        'CloudFlare-AlwaysOnline',
85
-        'coccoc',
86
-        'Commons-HttpClient',
87
-        'convera',
88
-        'cosmos',
89
-        'Covario-IDS',
90
-        'curl',
91
-        'CyberPatrol',
92
-        'DataparkSearch',
93
-        'dataprovider',
94
-        'Digg',
95
-        'DomainAppender',
96
-        'drupact',
97
-        'EARTHCOM',
98
-        'ec2linkfinder',
99
-        'ElectricMonk',
100
-        'Embedly',
101
-        'europarchive\.org',
102
-        'EventMachine HttpClient',
103
-        'ezooms',
104
-        'eZ Publish Link Validator',
105
-        'facebookexternalhit',
106
-        'Feedfetcher-Google',
107
-        'FeedValidator',
108
-        'FindLinks',
109
-        'findlink',
110
-        'findthatfile',
111
-        'Flamingo_SearchEngine',
112
-        'fluffy',
113
-        'getprismatic\.com',
114
-        'g00g1e\.net',
115
-        'GigablastOpenSource',
116
-        'grub-client',
117
-        'Genieo',
118
-        'Go-http-client',
119
-        'Google-HTTP-Java-Client',
120
-        'Google favicon',
121
-        'heritrix',
122
-        'Holmes',
123
-        'htdig',
124
-        'httpunit',
125
-        'httrack',
126
-        'ichiro',
127
-        'igdeSpyder',
128
-        'InAGist',
129
-        'InfoWizards Reciprocal Link System PRO',
130
-        'integromedb',
131
-        'IODC',
132
-        'IOI',
133
-        'ips-agent',
134
-        'iZSearch',
135
-        'L\.webis',
136
-        'Larbin',
137
-        'libwww',
138
-        'Link Valet',
139
-        'linkdex',
140
-        'LinkExaminer',
141
-        'LinkWalker',
142
-        'Lipperhey Link Explorer',
143
-        'Lipperhey SEO Service',
144
-        'LongURL API',
145
-        'ltx71',
146
-        'lwp-trivial',
147
-        'MegaIndex\.ru',
148
-        'mabontland',
149
-        'MagpieRSS',
150
-        'Mediapartners-Google',
151
-        'MetaURI',
152
-        'Mnogosearch',
153
-        'mogimogi',
154
-        'Morning Paper',
155
-        'Mrcgiguy',
156
-        'MVAClient',
157
-        'netresearchserver',
158
-        'NewsGator',
159
-        'newsme',
160
-        'NG-Search',
161
-        '^NING\\/',
162
-        'Notifixious',
163
-        'nutch',
164
-        'NutchCVS',
165
-        'Nymesis',
166
-        'oegp',
167
-        'online link validator',
168
-        'Online Website Link Checker',
169
-        'Orbiter',
170
-        'ow\.ly',
171
-        'Ploetz \+ Zeller',
172
-        'page2rss',
173
-        'panscient',
174
-        'Peew',
175
-        'phpcrawl',
176
-        'Pizilla',
177
-        'Plukkie',
178
-        'Pompos',
179
-        'postano',
180
-        'PostPost',
181
-        'postrank',
182
-        'proximic',
183
-        'PycURL',
184
-        'Python-httplib2',
185
-        'python-requests',
186
-        'Python-urllib',
187
-        'Qseero',
188
-        'Qwantify',
189
-        'Radian6',
190
-        'RebelMouse',
191
-        'REL Link Checker',
192
-        'RetrevoPageAnalyzer',
193
-        'Riddler',
194
-        'Robosourcer',
195
-        'Ruby',
196
-        'SBIder',
197
-        'ScoutJet',
198
-        'ScoutURLMonitor',
199
-        'Scrapy',
200
-        'Scrubby',
201
-        'SearchSight',
202
-        'semanticdiscovery',
203
-        'SEOstats',
204
-        'Seznam screenshot-generator',
205
-        'ShopWiki',
206
-        'SiteBar',
207
-        'siteexplorer\.info',
208
-        'slider\.com',
209
-        'slurp',
210
-        'Snappy',
211
-        'sogou',
212
-        'speedy',
213
-        'Sqworm',
214
-        'StackRambler',
215
-        'Stratagems Kumo',
216
-        'summify',
217
-        'teoma',
218
-        'theoldreader\.com',
219
-        'TinEye',
220
-        'Traackr.com',
221
-        'truwoGPS',
222
-        'tweetedtimes\.com',
223
-        'Twikle',
224
-        'UnwindFetchor',
225
-        'updated',
226
-        'urlresolver',
227
-        'Validator\.nu\\/LV',
228
-        'Vagabondo',
229
-        'Vivante Link Checker',
230
-        'Vortex',
231
-        'voyager\\/',
232
-        'VYU2',
233
-        'W3C-checklink',
234
-        'W3C_CSS_Validator_JFouffa',
235
-        'W3C_I18n-Checker',
236
-        'W3C-mobileOK',
237
-        'W3C_Unicorn',
238
-        'W3C_Validator',
239
-        'WebIndex',
240
-        'Websquash\.com',
241
-        'webcollage',
242
-        'webmon ',
243
-        'WeSEE:Search',
244
-        'wf84',
245
-        'wget',
246
-        'WomlpeFactory',
247
-        'wotbox',
248
-        'Xenu Link Sleuth',
249
-        'XML Sitemaps Generator',
250
-        'Y!J-ASR',
251
-        'yacy',
252
-        'Yahoo Link Preview',
253
-        'Yahoo! Slurp China',
254
-        'Yahoo! Slurp',
255
-        'YahooSeeker',
256
-        'YahooSeeker-Testing',
257
-        'YandexImages',
258
-        'YandexMetrika',
259
-        'yandex',
260
-        'yanga',
261
-        'yeti',
262
-        'yoogliFetchAgent',
263
-        'Zao',
264
-        'ZyBorg',
265
-        '[a-z0-9\\-_]*((?<!cu)bot|crawler|archiver|transcoder|spider)',
266
-    );
58
+	protected static $crawlers = array(
59
+		'008\\/',
60
+		'A6-Indexer',
61
+		'Aboundex',
62
+		'Accoona-AI-Agent',
63
+		'acoon',
64
+		'AddThis',
65
+		'ADmantX',
66
+		'AHC',
67
+		'Airmail',
68
+		'Anemone',
69
+		'Arachmo',
70
+		'archive-com',
71
+		'B-l-i-t-z-B-O-T',
72
+		'bibnum\.bnf',
73
+		'biglotron',
74
+		'binlar',
75
+		'boitho\.com-dc',
76
+		'BUbiNG',
77
+		'Butterfly\\/',
78
+		'BuzzSumo',
79
+		'CC Metadata Scaper',
80
+		'Cerberian Drtrs',
81
+		'changedetection',
82
+		'Charlotte',
83
+		'clips\.ua\.ac\.be',
84
+		'CloudFlare-AlwaysOnline',
85
+		'coccoc',
86
+		'Commons-HttpClient',
87
+		'convera',
88
+		'cosmos',
89
+		'Covario-IDS',
90
+		'curl',
91
+		'CyberPatrol',
92
+		'DataparkSearch',
93
+		'dataprovider',
94
+		'Digg',
95
+		'DomainAppender',
96
+		'drupact',
97
+		'EARTHCOM',
98
+		'ec2linkfinder',
99
+		'ElectricMonk',
100
+		'Embedly',
101
+		'europarchive\.org',
102
+		'EventMachine HttpClient',
103
+		'ezooms',
104
+		'eZ Publish Link Validator',
105
+		'facebookexternalhit',
106
+		'Feedfetcher-Google',
107
+		'FeedValidator',
108
+		'FindLinks',
109
+		'findlink',
110
+		'findthatfile',
111
+		'Flamingo_SearchEngine',
112
+		'fluffy',
113
+		'getprismatic\.com',
114
+		'g00g1e\.net',
115
+		'GigablastOpenSource',
116
+		'grub-client',
117
+		'Genieo',
118
+		'Go-http-client',
119
+		'Google-HTTP-Java-Client',
120
+		'Google favicon',
121
+		'heritrix',
122
+		'Holmes',
123
+		'htdig',
124
+		'httpunit',
125
+		'httrack',
126
+		'ichiro',
127
+		'igdeSpyder',
128
+		'InAGist',
129
+		'InfoWizards Reciprocal Link System PRO',
130
+		'integromedb',
131
+		'IODC',
132
+		'IOI',
133
+		'ips-agent',
134
+		'iZSearch',
135
+		'L\.webis',
136
+		'Larbin',
137
+		'libwww',
138
+		'Link Valet',
139
+		'linkdex',
140
+		'LinkExaminer',
141
+		'LinkWalker',
142
+		'Lipperhey Link Explorer',
143
+		'Lipperhey SEO Service',
144
+		'LongURL API',
145
+		'ltx71',
146
+		'lwp-trivial',
147
+		'MegaIndex\.ru',
148
+		'mabontland',
149
+		'MagpieRSS',
150
+		'Mediapartners-Google',
151
+		'MetaURI',
152
+		'Mnogosearch',
153
+		'mogimogi',
154
+		'Morning Paper',
155
+		'Mrcgiguy',
156
+		'MVAClient',
157
+		'netresearchserver',
158
+		'NewsGator',
159
+		'newsme',
160
+		'NG-Search',
161
+		'^NING\\/',
162
+		'Notifixious',
163
+		'nutch',
164
+		'NutchCVS',
165
+		'Nymesis',
166
+		'oegp',
167
+		'online link validator',
168
+		'Online Website Link Checker',
169
+		'Orbiter',
170
+		'ow\.ly',
171
+		'Ploetz \+ Zeller',
172
+		'page2rss',
173
+		'panscient',
174
+		'Peew',
175
+		'phpcrawl',
176
+		'Pizilla',
177
+		'Plukkie',
178
+		'Pompos',
179
+		'postano',
180
+		'PostPost',
181
+		'postrank',
182
+		'proximic',
183
+		'PycURL',
184
+		'Python-httplib2',
185
+		'python-requests',
186
+		'Python-urllib',
187
+		'Qseero',
188
+		'Qwantify',
189
+		'Radian6',
190
+		'RebelMouse',
191
+		'REL Link Checker',
192
+		'RetrevoPageAnalyzer',
193
+		'Riddler',
194
+		'Robosourcer',
195
+		'Ruby',
196
+		'SBIder',
197
+		'ScoutJet',
198
+		'ScoutURLMonitor',
199
+		'Scrapy',
200
+		'Scrubby',
201
+		'SearchSight',
202
+		'semanticdiscovery',
203
+		'SEOstats',
204
+		'Seznam screenshot-generator',
205
+		'ShopWiki',
206
+		'SiteBar',
207
+		'siteexplorer\.info',
208
+		'slider\.com',
209
+		'slurp',
210
+		'Snappy',
211
+		'sogou',
212
+		'speedy',
213
+		'Sqworm',
214
+		'StackRambler',
215
+		'Stratagems Kumo',
216
+		'summify',
217
+		'teoma',
218
+		'theoldreader\.com',
219
+		'TinEye',
220
+		'Traackr.com',
221
+		'truwoGPS',
222
+		'tweetedtimes\.com',
223
+		'Twikle',
224
+		'UnwindFetchor',
225
+		'updated',
226
+		'urlresolver',
227
+		'Validator\.nu\\/LV',
228
+		'Vagabondo',
229
+		'Vivante Link Checker',
230
+		'Vortex',
231
+		'voyager\\/',
232
+		'VYU2',
233
+		'W3C-checklink',
234
+		'W3C_CSS_Validator_JFouffa',
235
+		'W3C_I18n-Checker',
236
+		'W3C-mobileOK',
237
+		'W3C_Unicorn',
238
+		'W3C_Validator',
239
+		'WebIndex',
240
+		'Websquash\.com',
241
+		'webcollage',
242
+		'webmon ',
243
+		'WeSEE:Search',
244
+		'wf84',
245
+		'wget',
246
+		'WomlpeFactory',
247
+		'wotbox',
248
+		'Xenu Link Sleuth',
249
+		'XML Sitemaps Generator',
250
+		'Y!J-ASR',
251
+		'yacy',
252
+		'Yahoo Link Preview',
253
+		'Yahoo! Slurp China',
254
+		'Yahoo! Slurp',
255
+		'YahooSeeker',
256
+		'YahooSeeker-Testing',
257
+		'YandexImages',
258
+		'YandexMetrika',
259
+		'yandex',
260
+		'yanga',
261
+		'yeti',
262
+		'yoogliFetchAgent',
263
+		'Zao',
264
+		'ZyBorg',
265
+		'[a-z0-9\\-_]*((?<!cu)bot|crawler|archiver|transcoder|spider)',
266
+	);
267 267
 
268
-    /**
269
-     * All possible HTTP headers that represent the
270
-     * User-Agent string.
271
-     *
272
-     * @var array
273
-     */
274
-    protected static $uaHttpHeaders = array(
275
-        // The default User-Agent string.
276
-        'HTTP_USER_AGENT',
277
-        // Header can occur on devices using Opera Mini.
278
-        'HTTP_X_OPERAMINI_PHONE_UA',
279
-        // Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/
280
-        'HTTP_X_DEVICE_USER_AGENT',
281
-        'HTTP_X_ORIGINAL_USER_AGENT',
282
-        'HTTP_X_SKYFIRE_PHONE',
283
-        'HTTP_X_BOLT_PHONE_UA',
284
-        'HTTP_DEVICE_STOCK_UA',
285
-        'HTTP_X_UCBROWSER_DEVICE_UA',
286
-    );
268
+	/**
269
+	 * All possible HTTP headers that represent the
270
+	 * User-Agent string.
271
+	 *
272
+	 * @var array
273
+	 */
274
+	protected static $uaHttpHeaders = array(
275
+		// The default User-Agent string.
276
+		'HTTP_USER_AGENT',
277
+		// Header can occur on devices using Opera Mini.
278
+		'HTTP_X_OPERAMINI_PHONE_UA',
279
+		// Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/
280
+		'HTTP_X_DEVICE_USER_AGENT',
281
+		'HTTP_X_ORIGINAL_USER_AGENT',
282
+		'HTTP_X_SKYFIRE_PHONE',
283
+		'HTTP_X_BOLT_PHONE_UA',
284
+		'HTTP_DEVICE_STOCK_UA',
285
+		'HTTP_X_UCBROWSER_DEVICE_UA',
286
+	);
287 287
 
288
-    /**
289
-     * Class constructor.
290
-     */
291
-    public function __construct(array $headers = null, $userAgent = null)
292
-    {
293
-        $this->setHttpHeaders($headers);
294
-        $this->setUserAgent($userAgent);
295
-    }
288
+	/**
289
+	 * Class constructor.
290
+	 */
291
+	public function __construct(array $headers = null, $userAgent = null)
292
+	{
293
+		$this->setHttpHeaders($headers);
294
+		$this->setUserAgent($userAgent);
295
+	}
296 296
 
297
-    public function setHttpHeaders($httpHeaders = null)
298
-    {
299
-        // use global _SERVER if $httpHeaders aren't defined
300
-        if (!is_array($httpHeaders) || !count($httpHeaders)) {
301
-            $httpHeaders = $_SERVER;
302
-        }
303
-        // clear existing headers
304
-        $this->httpHeaders = array();
305
-        // Only save HTTP headers. In PHP land, that means only _SERVER vars that
306
-        // start with HTTP_.
307
-        foreach ($httpHeaders as $key => $value) {
308
-            if (substr($key, 0, 5) === 'HTTP_') {
309
-                $this->httpHeaders[$key] = $value;
310
-            }
311
-        }
312
-    }
297
+	public function setHttpHeaders($httpHeaders = null)
298
+	{
299
+		// use global _SERVER if $httpHeaders aren't defined
300
+		if (!is_array($httpHeaders) || !count($httpHeaders)) {
301
+			$httpHeaders = $_SERVER;
302
+		}
303
+		// clear existing headers
304
+		$this->httpHeaders = array();
305
+		// Only save HTTP headers. In PHP land, that means only _SERVER vars that
306
+		// start with HTTP_.
307
+		foreach ($httpHeaders as $key => $value) {
308
+			if (substr($key, 0, 5) === 'HTTP_') {
309
+				$this->httpHeaders[$key] = $value;
310
+			}
311
+		}
312
+	}
313 313
 
314
-    public function getUaHttpHeaders()
315
-    {
316
-        return self::$uaHttpHeaders;
317
-    }
314
+	public function getUaHttpHeaders()
315
+	{
316
+		return self::$uaHttpHeaders;
317
+	}
318 318
 
319
-    public function setUserAgent($userAgent = null)
320
-    {
321
-        if (false === empty($userAgent)) {
322
-            return $this->userAgent = $userAgent;
323
-        } else {
324
-            $this->userAgent = null;
325
-            foreach ($this->getUaHttpHeaders() as $altHeader) {
326
-                if (false === empty($this->httpHeaders[$altHeader])) { // @todo: should use getHttpHeader(), but it would be slow. (Serban)
327
-                    $this->userAgent .= $this->httpHeaders[$altHeader].' ';
328
-                }
329
-            }
319
+	public function setUserAgent($userAgent = null)
320
+	{
321
+		if (false === empty($userAgent)) {
322
+			return $this->userAgent = $userAgent;
323
+		} else {
324
+			$this->userAgent = null;
325
+			foreach ($this->getUaHttpHeaders() as $altHeader) {
326
+				if (false === empty($this->httpHeaders[$altHeader])) { // @todo: should use getHttpHeader(), but it would be slow. (Serban)
327
+					$this->userAgent .= $this->httpHeaders[$altHeader].' ';
328
+				}
329
+			}
330 330
 
331
-            return $this->userAgent = (!empty($this->userAgent) ? trim($this->userAgent) : null);
332
-        }
333
-    }
331
+			return $this->userAgent = (!empty($this->userAgent) ? trim($this->userAgent) : null);
332
+		}
333
+	}
334 334
 
335
-    public function getRegex()
336
-    {
337
-        return '('.implode('|', self::$crawlers).')';
338
-    }
335
+	public function getRegex()
336
+	{
337
+		return '('.implode('|', self::$crawlers).')';
338
+	}
339 339
 
340
-    public function getIgnored()
341
-    {
342
-        return '('.implode('|', self::$ignore).')';
343
-    }
340
+	public function getIgnored()
341
+	{
342
+		return '('.implode('|', self::$ignore).')';
343
+	}
344 344
 
345
-    public function isCrawler($userAgent = null)
346
-    {
347
-        $agent = is_null($userAgent) ? $this->userAgent : $userAgent;
345
+	public function isCrawler($userAgent = null)
346
+	{
347
+		$agent = is_null($userAgent) ? $this->userAgent : $userAgent;
348 348
 
349
-        $agent = preg_replace('/'.$this->getIgnored().'/i', '', $agent);
349
+		$agent = preg_replace('/'.$this->getIgnored().'/i', '', $agent);
350 350
 
351
-        $result = preg_match('/'.$this->getRegex().'/i', $agent, $matches);
351
+		$result = preg_match('/'.$this->getRegex().'/i', $agent, $matches);
352 352
 
353
-        if ($matches) {
354
-            $this->matches = $matches;
355
-        }
353
+		if ($matches) {
354
+			$this->matches = $matches;
355
+		}
356 356
 
357
-        return (bool) $result;
358
-    }
357
+		return (bool) $result;
358
+	}
359 359
 
360
-    public function getMatches()
361
-    {
362
-        return $this->matches[0];
363
-    }
360
+	public function getMatches()
361
+	{
362
+		return $this->matches[0];
363
+	}
364 364
 }
Please login to merge, or discard this patch.