1 | <?php |
||
5 | class CrawlerDetect |
||
6 | { |
||
7 | /** |
||
8 | * The user agent. |
||
9 | * |
||
10 | * @var null |
||
11 | */ |
||
12 | protected $userAgent = null; |
||
13 | |||
14 | /** |
||
15 | * Headers that contain a user agent. |
||
16 | * |
||
17 | * @var array |
||
18 | */ |
||
19 | protected $httpHeaders = array(); |
||
20 | |||
21 | /** |
||
22 | * Store regex matches. |
||
23 | * |
||
24 | * @var array |
||
25 | */ |
||
26 | protected $matches = array(); |
||
27 | |||
28 | /** |
||
29 | * List of strings to remove from the user agent before running the crawler regex |
||
30 | * Over a large list of user agents, this gives us about a 55% speed increase! |
||
31 | * |
||
32 | * @var array |
||
33 | */ |
||
34 | protected static $ignore = array( |
||
35 | 'Safari.[\d\.]*', |
||
36 | 'Firefox.[\d\.]*', |
||
37 | 'Chrome.[\d\.]*', |
||
38 | 'Chromium.[\d\.]*', |
||
39 | 'MSIE.[\d\.]', |
||
40 | 'Opera\/[\d\.]*', |
||
41 | 'Mozilla.[\d\.]*', |
||
42 | 'AppleWebKit.[\d\.]*', |
||
43 | 'Trident.[\d\.]*', |
||
44 | 'Windows NT.[\d\.]*', |
||
45 | 'Android.[\d\.]*', |
||
46 | 'Macintosh.', |
||
47 | 'Ubuntu', |
||
48 | 'Linux', |
||
49 | '[ ]Intel', |
||
50 | 'Mac OS X [\d_]*', |
||
51 | '(like )?Gecko(.[\d\.]*)?', |
||
52 | 'KHTML', |
||
53 | 'CriOS.[\d\.]*', |
||
54 | 'CPU iPhone OS ([0-9_])* like Mac OS X', |
||
55 | 'CPU OS ([0-9_])* like Mac OS X', |
||
56 | 'iPod', |
||
57 | 'compatible', |
||
58 | 'x86_..', |
||
59 | 'i686', |
||
60 | 'x64', |
||
61 | 'X11', |
||
62 | 'rv:[\d\.]*', |
||
63 | 'Version.[\d\.]*', |
||
64 | 'WOW64', |
||
65 | 'Win64', |
||
66 | 'Dalvik.[\d\.]*', |
||
67 | ' \.NET CLR [\d\.]*', |
||
68 | 'Presto.[\d\.]*', |
||
69 | 'Media Center PC', |
||
70 | 'BlackBerry', |
||
71 | 'Build', |
||
72 | 'Opera Mini\/\d{1,2}\.\d{1,2}\.[\d\.]*\/\d{1,2}\.', |
||
73 | 'Opera', |
||
74 | ' \.NET[\d\.]*', |
||
75 | '\(|\)|;|,', // Remove the following characters ( ) : , |
||
76 | ); |
||
77 | |||
78 | /** |
||
79 | * Array of regular expressions to match against the user agent. |
||
80 | * |
||
81 | * @var array |
||
82 | */ |
||
83 | protected static $crawlers = array( |
||
84 | '.*Java.*outbrain', |
||
85 | '008\\/', |
||
86 | '^NING\\/', |
||
87 | 'A6-Indexer', |
||
88 | 'Aboundex', |
||
89 | 'Accoona-AI-Agent', |
||
90 | 'acoon', |
||
91 | 'AddThis', |
||
92 | 'ADmantX', |
||
93 | 'AHC', |
||
94 | 'Airmail', |
||
95 | 'Anemone', |
||
96 | 'Arachmo', |
||
97 | 'archive-com', |
||
98 | 'B-l-i-t-z-B-O-T', |
||
99 | 'Backlink-Ceck\.de', |
||
100 | 'BazQux', |
||
101 | 'bibnum\.bnf', |
||
102 | 'biglotron', |
||
103 | 'BingPreview', |
||
104 | 'binlar', |
||
105 | 'Bloglovin', |
||
106 | 'Blogtrottr', |
||
107 | 'boitho\.com-dc', |
||
108 | 'Browsershots', |
||
109 | 'BUbiNG', |
||
110 | 'Butterfly\\/', |
||
111 | 'BuzzSumo', |
||
112 | 'CapsuleChecker', |
||
113 | 'CC Metadata Scaper', |
||
114 | 'Cerberian Drtrs', |
||
115 | 'changedetection', |
||
116 | 'Charlotte', |
||
117 | 'clips\.ua\.ac\.be', |
||
118 | 'CloudFlare-AlwaysOnline', |
||
119 | 'coccoc', |
||
120 | 'CommaFeed', |
||
121 | 'Commons-HttpClient', |
||
122 | 'convera', |
||
123 | 'cosmos', |
||
124 | 'Covario-IDS', |
||
125 | 'Curious George', |
||
126 | 'curl', |
||
127 | 'CyberPatrol', |
||
128 | 'DataparkSearch', |
||
129 | 'dataprovider', |
||
130 | 'Daum(oa)?[ \\/][0-9]', |
||
131 | 'Digg', |
||
132 | 'DomainAppender', |
||
133 | 'Dragonfly File Reader', |
||
134 | 'drupact', |
||
135 | 'EARTHCOM', |
||
136 | 'ec2linkfinder', |
||
137 | 'ECCP', |
||
138 | 'ElectricMonk', |
||
139 | 'EMail Exractor', |
||
140 | 'EmailWolf', |
||
141 | 'Embed PHP Library', |
||
142 | 'Embedly', |
||
143 | 'europarchive\.org', |
||
144 | 'EventMachine HttpClient', |
||
145 | 'ExactSearch', |
||
146 | 'ExaleadCloudview', |
||
147 | 'eZ Publish Link Validator', |
||
148 | 'ezooms', |
||
149 | 'facebookexternalhit', |
||
150 | 'facebookplatform', |
||
151 | 'Feed Wrangler', |
||
152 | 'Feedbin', |
||
153 | 'FeedBurner', |
||
154 | 'Feedfetcher-Google', |
||
155 | 'Feedly', |
||
156 | 'Feedspot', |
||
157 | 'FeedValidator', |
||
158 | 'Fever', |
||
159 | 'findlink', |
||
160 | 'findthatfile', |
||
161 | 'Flamingo_SearchEngine', |
||
162 | 'fluffy', |
||
163 | 'g00g1e\.net', |
||
164 | 'Genieo', |
||
165 | 'getprismatic\.com', |
||
166 | 'GigablastOpenSource', |
||
167 | 'Go-http-client', |
||
168 | 'Google favicon', |
||
169 | 'Google Keyword Suggestion', |
||
170 | 'Google Page Speed Insights', |
||
171 | 'Google-HTTP-Java-Client', |
||
172 | 'google_partner_monitoring', |
||
173 | 'GoogleProducer', |
||
174 | 'grub-client', |
||
175 | 'heritrix', |
||
176 | 'Holmes', |
||
177 | 'htdig', |
||
178 | 'HTTPMon', |
||
179 | 'httpunit', |
||
180 | 'httrack', |
||
181 | 'HubPages.*crawlingpolicy', |
||
182 | 'HubSpot Marketing Grader', |
||
183 | 'ichiro', |
||
184 | 'IDG Twitter Links Resolver', |
||
185 | 'igdeSpyder', |
||
186 | 'InAGist', |
||
187 | 'infegy', |
||
188 | 'InfoWizards Reciprocal Link System PRO', |
||
189 | 'integromedb', |
||
190 | 'IODC', |
||
191 | 'IOI', |
||
192 | 'ips-agent', |
||
193 | 'iZSearch', |
||
194 | 'Jigsaw', |
||
195 | 'Jobrapido', |
||
196 | 'kouio', |
||
197 | 'L\.webis', |
||
198 | 'Larbin', |
||
199 | 'libwww', |
||
200 | 'Link Valet', |
||
201 | 'linkCheck', |
||
202 | 'linkdex', |
||
203 | 'LinkExaminer', |
||
204 | 'LinkWalker', |
||
205 | 'Lipperhey', |
||
206 | 'LongURL API', |
||
207 | 'ltx71', |
||
208 | 'lwp-trivial', |
||
209 | 'lycos', |
||
210 | 'mabontland', |
||
211 | 'MagpieRSS', |
||
212 | 'Mediapartners-Google', |
||
213 | 'Mediapartners-Google', |
||
214 | 'MegaIndex\.ru', |
||
215 | 'MetaURI', |
||
216 | 'Mnogosearch', |
||
217 | 'mogimogi', |
||
218 | 'Morning Paper', |
||
219 | 'Mrcgiguy', |
||
220 | 'MVAClient', |
||
221 | 'Netcraft Web Server Survey', |
||
222 | 'NetLyzer FastProbe', |
||
223 | 'netresearch', |
||
224 | 'Netvibes', |
||
225 | 'NewsBlur .*(Fetcher|Finder)', |
||
226 | 'NewsGator', |
||
227 | 'newsme', |
||
228 | 'NG-Search', |
||
229 | 'nineconnections\.com', |
||
230 | 'nominet\.org\.uk', |
||
231 | 'Notifixious', |
||
232 | 'nuhk', |
||
233 | 'nutch', |
||
234 | 'Nymesis', |
||
235 | 'oegp', |
||
236 | 'Omea Reader', |
||
237 | 'online link validator', |
||
238 | 'Online Website Link Checker', |
||
239 | 'Orbiter', |
||
240 | 'ow\.ly', |
||
241 | 'page2rss', |
||
242 | 'PagePeeker', |
||
243 | 'panscient', |
||
244 | 'Peew', |
||
245 | 'phpcrawl', |
||
246 | 'phpservermon', |
||
247 | 'Pingdom\.com', |
||
248 | 'Pinterest', |
||
249 | 'Pizilla', |
||
250 | 'Ploetz \+ Zeller', |
||
251 | 'Plukkie', |
||
252 | 'PocketParser', |
||
253 | 'Pompos', |
||
254 | 'postano', |
||
255 | 'PostPost', |
||
256 | 'postrank', |
||
257 | 'proximic', |
||
258 | 'Pulsepoint XT3 web scraper', |
||
259 | 'Python-httplib2', |
||
260 | 'python-requests', |
||
261 | 'Python-urllib', |
||
262 | 'Qseero', |
||
263 | 'Qwantify', |
||
264 | 'Radian6', |
||
265 | 'RebelMouse', |
||
266 | 'REL Link Checker', |
||
267 | 'RetrevoPageAnalyzer', |
||
268 | 'Riddler', |
||
269 | 'Robosourcer', |
||
270 | 'ROI Hunter', |
||
271 | 'Ruby', |
||
272 | 'SBIder', |
||
273 | 'scooter', |
||
274 | 'ScoutJet', |
||
275 | 'ScoutURLMonitor', |
||
276 | 'Scrapy', |
||
277 | 'Scrubby', |
||
278 | 'SearchSight', |
||
279 | 'semanticdiscovery', |
||
280 | 'SEOstats', |
||
281 | 'Server Density Service Monitoring.*', |
||
282 | 'servernfo\.com', |
||
283 | 'Seznam screenshot-generator', |
||
284 | 'ShopWiki', |
||
285 | 'SilverReader', |
||
286 | 'SimplePie', |
||
287 | 'Site24x7', |
||
288 | 'SiteBar', |
||
289 | 'siteexplorer\.info', |
||
290 | 'Siteimprove\.com', |
||
291 | 'SkypeUriPreview', |
||
292 | 'slider\.com', |
||
293 | 'slurp', |
||
294 | 'Snappy', |
||
295 | 'sogou', |
||
296 | 'SortSite', |
||
297 | 'speedy', |
||
298 | 'Spinn3r', |
||
299 | 'Springshare Link Checker', |
||
300 | 'Sqworm', |
||
301 | 'StackRambler', |
||
302 | 'Stratagems Kumo', |
||
303 | 'summify', |
||
304 | 'teoma', |
||
305 | 'theoldreader\.com', |
||
306 | 'TinEye', |
||
307 | 'Tiny Tiny RSS', |
||
308 | 'Traackr.com', |
||
309 | 'truwoGPS', |
||
310 | 'tweetedtimes\.com', |
||
311 | 'Twikle', |
||
312 | 'Typhoeus', |
||
313 | 'UdmSearch', |
||
314 | 'UnwindFetchor', |
||
315 | 'updated', |
||
316 | 'URLChecker', |
||
317 | 'urlresolver', |
||
318 | 'Vagabondo', |
||
319 | 'Validator\.nu\\/LV', |
||
320 | 'via ggpht\.com GoogleImageProxy', |
||
321 | 'Vivante Link Checker', |
||
322 | 'Vortex', |
||
323 | 'voyager\\/', |
||
324 | 'VYU2', |
||
325 | 'W3C-checklink', |
||
326 | 'W3C-mobileOK', |
||
327 | 'W3C_CSS_Validator_JFouffa', |
||
328 | 'W3C_I18n-Checker', |
||
329 | 'W3C_Unicorn', |
||
330 | 'W3C_Validator', |
||
331 | 'web-capture\.net', |
||
332 | 'webcollage', |
||
333 | 'WebIndex', |
||
334 | 'webmon ', |
||
335 | 'websitepulse[+ ]checker', |
||
336 | 'Websquash\.com', |
||
337 | 'WebThumbnail', |
||
338 | 'WeSEE:Search', |
||
339 | 'wf84', |
||
340 | 'wget', |
||
341 | 'WomlpeFactory', |
||
342 | 'wotbox', |
||
343 | 'www\.monitor\.us', |
||
344 | 'Xenu Link Sleuth', |
||
345 | 'XML Sitemaps Generator', |
||
346 | 'Y!J-ASR', |
||
347 | 'yacy', |
||
348 | 'Yahoo Ad monitoring', |
||
349 | 'Yahoo Link Preview', |
||
350 | 'YahooSeeker', |
||
351 | 'yandex', |
||
352 | 'yanga', |
||
353 | 'yeti', |
||
354 | 'yoogliFetchAgent', |
||
355 | 'YottaaMonitor', |
||
356 | 'Zao', |
||
357 | 'ZyBorg', |
||
358 | '[a-z0-9\\-_]*((?<!cu)bot|crawler|archiver|transcoder|spider)', |
||
359 | ); |
||
360 | |||
361 | /** |
||
362 | * All possible HTTP headers that represent the |
||
363 | * User-Agent string. |
||
364 | * |
||
365 | * @var array |
||
366 | */ |
||
367 | protected static $uaHttpHeaders = array( |
||
368 | // The default User-Agent string. |
||
369 | 'HTTP_USER_AGENT', |
||
370 | // Header can occur on devices using Opera Mini. |
||
371 | 'HTTP_X_OPERAMINI_PHONE_UA', |
||
372 | // Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/ |
||
373 | 'HTTP_X_DEVICE_USER_AGENT', |
||
374 | 'HTTP_X_ORIGINAL_USER_AGENT', |
||
375 | 'HTTP_X_SKYFIRE_PHONE', |
||
376 | 'HTTP_X_BOLT_PHONE_UA', |
||
377 | 'HTTP_DEVICE_STOCK_UA', |
||
378 | 'HTTP_X_UCBROWSER_DEVICE_UA', |
||
379 | ); |
||
380 | |||
381 | /** |
||
382 | * Class constructor. |
||
383 | */ |
||
384 | public function __construct(array $headers = null, $userAgent = null) |
||
389 | |||
390 | /** |
||
391 | * Set HTTP headers. |
||
392 | * |
||
393 | * @param array $httpHeaders |
||
394 | */ |
||
395 | public function setHttpHeaders($httpHeaders = null) |
||
411 | |||
412 | /** |
||
413 | * Return user agent headers. |
||
414 | * |
||
415 | * @return array |
||
416 | */ |
||
417 | public function getUaHttpHeaders() |
||
421 | |||
422 | /** |
||
423 | * Set the user agent. |
||
424 | * |
||
425 | * @param string $userAgent |
||
426 | */ |
||
427 | public function setUserAgent($userAgent = null) |
||
442 | |||
443 | /** |
||
444 | * Return the array of crawler regexs. |
||
445 | * |
||
446 | * @return array |
||
447 | */ |
||
448 | public function getCrawlers() |
||
452 | |||
453 | /** |
||
454 | * Build the user agent regex. |
||
455 | * |
||
456 | * @return string |
||
457 | */ |
||
458 | public function getRegex() |
||
462 | |||
463 | /** |
||
464 | * Build the replacement regex. |
||
465 | * |
||
466 | * @return string |
||
467 | */ |
||
468 | public function getIgnored() |
||
472 | |||
473 | /** |
||
474 | * Check user agent string against the regex. |
||
475 | * |
||
476 | * @param string $userAgent |
||
477 | * |
||
478 | * @return bool |
||
479 | */ |
||
480 | public function isCrawler($userAgent = null) |
||
498 | |||
499 | /** |
||
500 | * Return the matches. |
||
501 | * |
||
502 | * @return string |
||
503 | */ |
||
504 | public function getMatches() |
||
508 | } |
||
509 |
Instead of super-globals, we recommend to explicitly inject the dependencies of your class. This makes your code less dependent on global state and it becomes generally more testable: