View GitHub Repository Crawler-Detect

Schedule Inspection
Subscribe
Completed
Pull Request — master (#37)
by Romaric
03:21
created
Category
Toggle Patches
src/CrawlerDetect.php 2 patches
Indentation   +499 added lines, -499 removed lines patch added patch discarded remove patch 
@@ -4,518 +4,518 @@
 
 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 
-    protected static $crawlers = array(
14 
-        '007ac9 Crawler',
15 
-        '008\\/',
16 
-        '360Spider',
17 
-        'A6-Indexer',
18 
-        'ABACHOBot',
19 
-        'AbiLogicBot',
20 
-        'Aboundex',
21 
-        'Accoona-AI-Agent',
22 
-        'acoon',
23 
-        'AddSugarSpiderBot',
24 
-        'AddThis',
25 
-        'Adidxbot',
26 
-        'ADmantX',
27 
-        'AdvBot',
28 
-        'AHC',
29 
-        'ahrefsbot',
30 
-        'aihitbot',
31 
-        'Airmail',
32 
-        'AISearchBot',
33 
-        'Anemone',
34 
-        'antibot',
35 
-        'AnyApexBot',
36 
-        'Applebot',
37 
-        'arabot',
38 
-        'Arachmo',
39 
-        'archive-com',
40 
-        'archive.org_bot',
41 
-        'B-l-i-t-z-B-O-T',
42 
-        'backlinkcrawler',
43 
-        'baiduspider',
44 
-        'BecomeBot',
45 
-        'BeslistBot',
46 
-        'bibnum\.bnf',
47 
-        'biglotron',
48 
-        'BillyBobBot',
49 
-        'Bimbot',
50 
-        'bingbot',
51 
-        'binlar',
52 
-        'blekkobot',
53 
-        'blexbot',
54 
-        'BlitzBOT',
55 
-        'bl\.uk_lddc_bot',
56 
-        'bnf\.fr_bot',
57 
-        'boitho\.com-dc',
58 
-        'boitho\.com-robot',
59 
-        'brainobot',
60 
-        'btbot',
61 
-        'BUbiNG',
62 
-        'Butterfly\/',
63 
-        'buzzbot',
64 
-        'BuzzSumo',
65 
-        'careerbot',
66 
-        'CatchBot',
67 
-        'CC Metadata Scaper',
68 
-        'ccbot',
69 
-        'Cerberian Drtrs',
70 
-        'changedetection',
71 
-        'Charlotte',
72 
-        'clips\.ua\.ac\.be',
73 
-        'CloudFlare-AlwaysOnline',
74 
-        'citeseerxbot',
75 
-        'coccoc',
76 
-        'classbot',
77 
-        'Commons-HttpClient',
78 
-        'content crawler spider',
79 
-        'Content Crawler',
80 
-        'convera',
81 
-        'ConveraCrawler',
82 
-        'CoPubbot',
83 
-        'cosmos',
84 
-        'Covario-IDS',
85 
-        'CrawlBot',
86 
-        'crawler4j',
87 
-        'CrystalSemanticsBot',
88 
-        'curl',
89 
-        'cXensebot',
90 
-        'CyberPatrol',
91 
-        'DataparkSearch',
92 
-        'dataprovider',
93 
-        'DiamondBot',
94 
-        'Digg',
95 
-        'discobot',
96 
-        'DomainAppender',
97 
-        'domaincrawler',
98 
-        'Domain Re-Animator Bot',
99 
-        'dotbot',
100 
-        'drupact',
101 
-        'DuckDuckBot',
102 
-        'EARTHCOM',
103 
-        'EasouSpider',
104 
-        'ec2linkfinder',
105 
-        'edisterbot',
106 
-        'ElectricMonk',
107 
-        'elisabot',
108 
-        'emailmarketingrobot',
109 
-        'Embedly',
110 
-        'EmeraldShield\.com WebBot',
111 
-        'envolk\[ITS\]spider',
112 
-        'EsperanzaBot',
113 
-        'europarchive\.org',
114 
-        'EventMachine HttpClient',
115 
-        'exabot',
116 
-        'ezooms',
117 
-        'facebookexternalhit',
118 
-        'Facebot',
119 
-        'FAST Enteprise Crawler',
120 
-        'FAST Enterprise Crawler',
121 
-        'FAST-WebCrawler',
122 
-        'FDSE robot',
123 
-        'Feedfetcher-Google',
124 
-        'FindLinks',
125 
-        'findlink',
126 
-        'findthatfile',
127 
-        'findxbot',
128 
-        'Flamingo_SearchEngine',
129 
-        'fluffy',
130 
-        'fr-crawler',
131 
-        'FRCrawler',
132 
-        'FurlBot',
133 
-        'FyberSpider',
134 
-        'g00g1e\.net',
135 
-        'GigablastOpenSource',
136 
-        'grub-client',
137 
-        'g2crawler',
138 
-        'Gaisbot',
139 
-        'GalaxyBot',
140 
-        'genieBot',
141 
-        'Genieo',
142 
-        'GermCrawler',
143 
-        'getprismatic.com',
144 
-        'gigabot',
145 
-        'GingerCrawler',
146 
-        'Girafabot',
147 
-        'Gluten Free Crawler',
148 
-        'gnam gnam spider',
149 
-        'Go-http-client',
150 
-        'Googlebot-Image',
151 
-        'Googlebot-Mobile',
152 
-        'Googlebot',
153 
-        'Google-HTTP-Java-Client',
154 
-        'Google favicon',
155 
-        'GrapeshotCrawler',
156 
-        'gslfbot',
157 
-        'GurujiBot',
158 
-        'HappyFunBot',
159 
-        'Healthbot',
160 
-        'heritrix',
161 
-        'hl_ftien_spider',
162 
-        'Holmes',
163 
-        'htdig',
164 
-        'httpunit',
165 
-        'httrack',
166 
-        'ia_archiver',
167 
-        'iaskspider',
168 
-        'iCCrawler',
169 
-        'ichiro',
170 
-        'igdeSpyder',
171 
-        'iisbot',
172 
-        'InAGist',
173 
-        'InfoWizards Reciprocal Link System PRO',
174 
-        'Insitesbot',
175 
-        'integromedb',
176 
-        'intelium_bot',
177 
-        'InterfaxScanBot',
178 
-        'IODC',
179 
-        'IOI',
180 
-        'ip-web-crawler\.com',
181 
-        'ips-agent',
182 
-        'IRLbot',
183 
-        'IssueCrawler',
184 
-        'IstellaBot',
185 
-        'it2media-domain-crawler',
186 
-        'iZSearch',
187 
-        'Jaxified Bot',
188 
-        'JOC Web Spider',
189 
-        'jyxobot',
190 
-        'KoepaBot',
191 
-        'L\.webis',
192 
-        'LapozzBot',
193 
-        'Larbin',
194 
-        'lb-spider',
195 
-        'LDSpider',
196 
-        'LexxeBot',
197 
-        'libwww',
198 
-        'Linguee Bot',
199 
-        'Link Valet',
200 
-        'linkdex',
201 
-        'LinkExaminer',
202 
-        'LinksManager\.com_bot',
203 
-        'LinkpadBot',
204 
-        'LinksCrawler',
205 
-        'LinkWalker',
206 
-        'Lipperhey Link Explorer',
207 
-        'Lipperhey SEO Service',
208 
-        'Livelapbot',
209 
-        'LongURL API',
210 
-        'lmspider',
211 
-        'lssbot',
212 
-        'lssrocketcrawler',
213 
-        'ltx71',
214 
-        'lufsbot',
215 
-        'lwp-trivial',
216 
-        'Mail\.RU_Bot',
217 
-        'MegaIndex\.ru',
218 
-        'mabontland',
219 
-        'magpie-crawler',
220 
-        'MagpieRSS',
221 
-        'Mediapartners-Google',
222 
-        'memorybot',
223 
-        'MetaURI',
224 
-        'MJ12bot',
225 
-        'mlbot',
226 
-        'Mnogosearch',
227 
-        'mogimogi',
228 
-        'MojeekBot',
229 
-        'Moreoverbot',
230 
-        'Morning Paper',
231 
-        'Mrcgiguy',
232 
-        'MSIECrawler',
233 
-        'msnbot',
234 
-        'msrbot',
235 
-        'MVAClient',
236 
-        'mxbot',
237 
-        'NerdByNature\.Bot',
238 
-        'NerdyBot',
239 
-        'netEstate NE Crawler',
240 
-        'netresearchserver',
241 
-        'NetSeer Crawler',
242 
-        'NewsGator',
243 
-        'newsme',
244 
-        'NextGenSearchBot',
245 
-        'NG-Search',
246 
-        'ngbot',
247 
-        'nicebot',
248 
-        'niki-bot',
249 
-        'Notifixious',
250 
-        'noxtrumbot',
251 
-        'Nusearch Spider',
252 
-        'nutch',
253 
-        'NutchCVS',
254 
-        'Nymesis',
255 
-        'obot',
256 
-        'oegp',
257 
-        'ocrawler',
258 
-        'omgilibot',
259 
-        'OmniExplorer_Bot',
260 
-        'online link validator',
261 
-        'Online Website Link Checker',
262 
-        'OOZBOT',
263 
-        'openindexspider',
264 
-        'OpenWebSpider',
265 
-        'OrangeBot',
266 
-        'Orbiter',
267 
-        'ow\.ly',
268 
-        'PaperLiBot',
269 
-        'Pingdom\.com_bot',
270 
-        'Ploetz \+ Zeller',
271 
-        'page2rss',
272 
-        'PageBitesHyperBot',
273 
-        'panscient',
274 
-        'Peew',
275 
-        'PercolateCrawler',
276 
-        'phpcrawl',
277 
-        'Pizilla',
278 
-        'Plukkie',
279 
-        'polybot',
280 
-        'Pompos',
281 
-        'postano',
282 
-        'PostPost',
283 
-        'postrank',
284 
-        'proximic',
285 
-        'psbot',
286 
-        'purebot',
287 
-        'PycURL',
288 
-        'Python-httplib2',
289 
-        'python-requests',
290 
-        'Python-urllib',
291 
-        'Qseero',
292 
-        'QuerySeekerSpider',
293 
-        'Qwantify',
294 
-        'Radian6',
295 
-        'RAMPyBot',
296 
-        'RebelMouse',
297 
-        'REL Link Checker',
298 
-        'RetrevoPageAnalyzer',
299 
-        'Riddler',
300 
-        'Robosourcer',
301 
-        'rogerbot',
302 
-        'Ruby',
303 
-        'RufusBot',
304 
-        'SandCrawler',
305 
-        'SBIder',
306 
-        'ScoutJet',
307 
-        'ScoutURLMonitor',
308 
-        'Scrapy',
309 
-        'ScreenerBot',
310 
-        'scribdbot',
311 
-        'Scrubby',
312 
-        'SearchmetricsBot',
313 
-        'SearchSight',
314 
-        'seekbot',
315 
-        'semanticdiscovery',
316 
-        'SemrushBot',
317 
-        'Sensis Web Crawler',
318 
-        'SEOChat::Bot',
319 
-        'seokicks-robot',
320 
-        'SEOstats',
321 
-        'Seznam screenshot-generator',
322 
-        'seznambot',
323 
-        'Shim-Crawler',
324 
-        'ShopWiki',
325 
-        'Shoula robot',
326 
-        'ShowyouBot',
327 
-        'SimpleCrawler',
328 
-        'sistrix crawler',
329 
-        'SiteBar',
330 
-        'sitebot',
331 
-        'siteexplorer\.info',
332 
-        'SklikBot',
333 
-        'slider\.com',
334 
-        'slurp',
335 
-        'smtbot',
336 
-        'Snappy',
337 
-        'sogou spider',
338 
-        'sogou',
339 
-        'Sosospider',
340 
-        'spbot',
341 
-        'Speedy Spider',
342 
-        'speedy',
343 
-        'SpiderMan',
344 
-        'Sqworm',
345 
-        'SSL-Crawler',
346 
-        'StackRambler',
347 
-        'suggybot',
348 
-        'summify',
349 
-        'SurdotlyBot',
350 
-        'SurveyBot',
351 
-        'SynooBot',
352 
-        'tagoobot',
353 
-        'teoma',
354 
-        'TerrawizBot',
355 
-        'TheSuBot',
356 
-        'Thumbnail\.CZ robot',
357 
-        'TinEye',
358 
-        'toplistbot',
359 
-        'trendictionbot',
360 
-        'TrueBot',
361 
-        'truwoGPS',
362 
-        'turnitinbot',
363 
-        'TweetedTimes Bot',
364 
-        'tweetedtimes.com',
365 
-        'TweetmemeBot',
366 
-        'twengabot',
367 
-        'Twikle',
368 
-        'Twitterbot',
369 
-        'uMBot',
370 
-        'UnisterBot',
371 
-        'UnwindFetchor',
372 
-        'updated',
373 
-        'urlappendbot',
374 
-        'Urlfilebot',
375 
-        'urlresolver',
376 
-        'UsineNouvelleCrawler',
377 
-        'Vagabondo',
378 
-        'Vivante Link Checker',
379 
-        'voilabot',
380 
-        'Vortex',
381 
-        'voyager\\/',
382 
-        'VYU2',
383 
-        'web-archive-net\.com\.bot',
384 
-        'Websquash\.com',
385 
-        'WeSEE:Ads\/PageBot',
386 
-        'wbsearchbot',
387 
-        'webcollage',
388 
-        'webcompanycrawler',
389 
-        'webcrawler',
390 
-        'webmon ',
391 
-        'WeSEE:Search',
392 
-        'wf84',
393 
-        'wget',
394 
-        'wocbot',
395 
-        'WoFindeIch Robot',
396 
-        'WomlpeFactory',
397 
-        'woriobot',
398 
-        'wotbox',
399 
-        'Xaldon_WebSpider',
400 
-        'Xenu Link Sleuth',
401 
-        'xintellibot',
402 
-        'XML Sitemaps Generator',
403 
-        'XoviBot',
404 
-        'Y!J-ASR',
405 
-        'yacy',
406 
-        'yacybot',
407 
-        'Yahoo Link Preview',
408 
-        'Yahoo! Slurp China',
409 
-        'Yahoo! Slurp',
410 
-        'YahooSeeker',
411 
-        'YahooSeeker-Testing',
412 
-        'YandexBot',
413 
-        'YandexImages',
414 
-        'YandexMetrika',
415 
-        'yandex',
416 
-        'yanga',
417 
-        'Yasaklibot',
418 
-        'yeti',
419 
-        'YioopBot',
420 
-        'YisouSpider',
421 
-        'YodaoBot',
422 
-        'yoogliFetchAgent',
423 
-        'yoozBot',
424 
-        'YoudaoBot',
425 
-        'Zao',
426 
-        'Zealbot',
427 
-        'zspider',
428 
-        'ZyBorg',
429 
-        '[a-z0-9\\-_]*((?<!cu)bot|crawler|archiver|transcoder|spider)',
430 
-    );
13 
+	protected static $crawlers = array(
14 
+		'007ac9 Crawler',
15 
+		'008\\/',
16 
+		'360Spider',
17 
+		'A6-Indexer',
18 
+		'ABACHOBot',
19 
+		'AbiLogicBot',
20 
+		'Aboundex',
21 
+		'Accoona-AI-Agent',
22 
+		'acoon',
23 
+		'AddSugarSpiderBot',
24 
+		'AddThis',
25 
+		'Adidxbot',
26 
+		'ADmantX',
27 
+		'AdvBot',
28 
+		'AHC',
29 
+		'ahrefsbot',
30 
+		'aihitbot',
31 
+		'Airmail',
32 
+		'AISearchBot',
33 
+		'Anemone',
34 
+		'antibot',
35 
+		'AnyApexBot',
36 
+		'Applebot',
37 
+		'arabot',
38 
+		'Arachmo',
39 
+		'archive-com',
40 
+		'archive.org_bot',
41 
+		'B-l-i-t-z-B-O-T',
42 
+		'backlinkcrawler',
43 
+		'baiduspider',
44 
+		'BecomeBot',
45 
+		'BeslistBot',
46 
+		'bibnum\.bnf',
47 
+		'biglotron',
48 
+		'BillyBobBot',
49 
+		'Bimbot',
50 
+		'bingbot',
51 
+		'binlar',
52 
+		'blekkobot',
53 
+		'blexbot',
54 
+		'BlitzBOT',
55 
+		'bl\.uk_lddc_bot',
56 
+		'bnf\.fr_bot',
57 
+		'boitho\.com-dc',
58 
+		'boitho\.com-robot',
59 
+		'brainobot',
60 
+		'btbot',
61 
+		'BUbiNG',
62 
+		'Butterfly\/',
63 
+		'buzzbot',
64 
+		'BuzzSumo',
65 
+		'careerbot',
66 
+		'CatchBot',
67 
+		'CC Metadata Scaper',
68 
+		'ccbot',
69 
+		'Cerberian Drtrs',
70 
+		'changedetection',
71 
+		'Charlotte',
72 
+		'clips\.ua\.ac\.be',
73 
+		'CloudFlare-AlwaysOnline',
74 
+		'citeseerxbot',
75 
+		'coccoc',
76 
+		'classbot',
77 
+		'Commons-HttpClient',
78 
+		'content crawler spider',
79 
+		'Content Crawler',
80 
+		'convera',
81 
+		'ConveraCrawler',
82 
+		'CoPubbot',
83 
+		'cosmos',
84 
+		'Covario-IDS',
85 
+		'CrawlBot',
86 
+		'crawler4j',
87 
+		'CrystalSemanticsBot',
88 
+		'curl',
89 
+		'cXensebot',
90 
+		'CyberPatrol',
91 
+		'DataparkSearch',
92 
+		'dataprovider',
93 
+		'DiamondBot',
94 
+		'Digg',
95 
+		'discobot',
96 
+		'DomainAppender',
97 
+		'domaincrawler',
98 
+		'Domain Re-Animator Bot',
99 
+		'dotbot',
100 
+		'drupact',
101 
+		'DuckDuckBot',
102 
+		'EARTHCOM',
103 
+		'EasouSpider',
104 
+		'ec2linkfinder',
105 
+		'edisterbot',
106 
+		'ElectricMonk',
107 
+		'elisabot',
108 
+		'emailmarketingrobot',
109 
+		'Embedly',
110 
+		'EmeraldShield\.com WebBot',
111 
+		'envolk\[ITS\]spider',
112 
+		'EsperanzaBot',
113 
+		'europarchive\.org',
114 
+		'EventMachine HttpClient',
115 
+		'exabot',
116 
+		'ezooms',
117 
+		'facebookexternalhit',
118 
+		'Facebot',
119 
+		'FAST Enteprise Crawler',
120 
+		'FAST Enterprise Crawler',
121 
+		'FAST-WebCrawler',
122 
+		'FDSE robot',
123 
+		'Feedfetcher-Google',
124 
+		'FindLinks',
125 
+		'findlink',
126 
+		'findthatfile',
127 
+		'findxbot',
128 
+		'Flamingo_SearchEngine',
129 
+		'fluffy',
130 
+		'fr-crawler',
131 
+		'FRCrawler',
132 
+		'FurlBot',
133 
+		'FyberSpider',
134 
+		'g00g1e\.net',
135 
+		'GigablastOpenSource',
136 
+		'grub-client',
137 
+		'g2crawler',
138 
+		'Gaisbot',
139 
+		'GalaxyBot',
140 
+		'genieBot',
141 
+		'Genieo',
142 
+		'GermCrawler',
143 
+		'getprismatic.com',
144 
+		'gigabot',
145 
+		'GingerCrawler',
146 
+		'Girafabot',
147 
+		'Gluten Free Crawler',
148 
+		'gnam gnam spider',
149 
+		'Go-http-client',
150 
+		'Googlebot-Image',
151 
+		'Googlebot-Mobile',
152 
+		'Googlebot',
153 
+		'Google-HTTP-Java-Client',
154 
+		'Google favicon',
155 
+		'GrapeshotCrawler',
156 
+		'gslfbot',
157 
+		'GurujiBot',
158 
+		'HappyFunBot',
159 
+		'Healthbot',
160 
+		'heritrix',
161 
+		'hl_ftien_spider',
162 
+		'Holmes',
163 
+		'htdig',
164 
+		'httpunit',
165 
+		'httrack',
166 
+		'ia_archiver',
167 
+		'iaskspider',
168 
+		'iCCrawler',
169 
+		'ichiro',
170 
+		'igdeSpyder',
171 
+		'iisbot',
172 
+		'InAGist',
173 
+		'InfoWizards Reciprocal Link System PRO',
174 
+		'Insitesbot',
175 
+		'integromedb',
176 
+		'intelium_bot',
177 
+		'InterfaxScanBot',
178 
+		'IODC',
179 
+		'IOI',
180 
+		'ip-web-crawler\.com',
181 
+		'ips-agent',
182 
+		'IRLbot',
183 
+		'IssueCrawler',
184 
+		'IstellaBot',
185 
+		'it2media-domain-crawler',
186 
+		'iZSearch',
187 
+		'Jaxified Bot',
188 
+		'JOC Web Spider',
189 
+		'jyxobot',
190 
+		'KoepaBot',
191 
+		'L\.webis',
192 
+		'LapozzBot',
193 
+		'Larbin',
194 
+		'lb-spider',
195 
+		'LDSpider',
196 
+		'LexxeBot',
197 
+		'libwww',
198 
+		'Linguee Bot',
199 
+		'Link Valet',
200 
+		'linkdex',
201 
+		'LinkExaminer',
202 
+		'LinksManager\.com_bot',
203 
+		'LinkpadBot',
204 
+		'LinksCrawler',
205 
+		'LinkWalker',
206 
+		'Lipperhey Link Explorer',
207 
+		'Lipperhey SEO Service',
208 
+		'Livelapbot',
209 
+		'LongURL API',
210 
+		'lmspider',
211 
+		'lssbot',
212 
+		'lssrocketcrawler',
213 
+		'ltx71',
214 
+		'lufsbot',
215 
+		'lwp-trivial',
216 
+		'Mail\.RU_Bot',
217 
+		'MegaIndex\.ru',
218 
+		'mabontland',
219 
+		'magpie-crawler',
220 
+		'MagpieRSS',
221 
+		'Mediapartners-Google',
222 
+		'memorybot',
223 
+		'MetaURI',
224 
+		'MJ12bot',
225 
+		'mlbot',
226 
+		'Mnogosearch',
227 
+		'mogimogi',
228 
+		'MojeekBot',
229 
+		'Moreoverbot',
230 
+		'Morning Paper',
231 
+		'Mrcgiguy',
232 
+		'MSIECrawler',
233 
+		'msnbot',
234 
+		'msrbot',
235 
+		'MVAClient',
236 
+		'mxbot',
237 
+		'NerdByNature\.Bot',
238 
+		'NerdyBot',
239 
+		'netEstate NE Crawler',
240 
+		'netresearchserver',
241 
+		'NetSeer Crawler',
242 
+		'NewsGator',
243 
+		'newsme',
244 
+		'NextGenSearchBot',
245 
+		'NG-Search',
246 
+		'ngbot',
247 
+		'nicebot',
248 
+		'niki-bot',
249 
+		'Notifixious',
250 
+		'noxtrumbot',
251 
+		'Nusearch Spider',
252 
+		'nutch',
253 
+		'NutchCVS',
254 
+		'Nymesis',
255 
+		'obot',
256 
+		'oegp',
257 
+		'ocrawler',
258 
+		'omgilibot',
259 
+		'OmniExplorer_Bot',
260 
+		'online link validator',
261 
+		'Online Website Link Checker',
262 
+		'OOZBOT',
263 
+		'openindexspider',
264 
+		'OpenWebSpider',
265 
+		'OrangeBot',
266 
+		'Orbiter',
267 
+		'ow\.ly',
268 
+		'PaperLiBot',
269 
+		'Pingdom\.com_bot',
270 
+		'Ploetz \+ Zeller',
271 
+		'page2rss',
272 
+		'PageBitesHyperBot',
273 
+		'panscient',
274 
+		'Peew',
275 
+		'PercolateCrawler',
276 
+		'phpcrawl',
277 
+		'Pizilla',
278 
+		'Plukkie',
279 
+		'polybot',
280 
+		'Pompos',
281 
+		'postano',
282 
+		'PostPost',
283 
+		'postrank',
284 
+		'proximic',
285 
+		'psbot',
286 
+		'purebot',
287 
+		'PycURL',
288 
+		'Python-httplib2',
289 
+		'python-requests',
290 
+		'Python-urllib',
291 
+		'Qseero',
292 
+		'QuerySeekerSpider',
293 
+		'Qwantify',
294 
+		'Radian6',
295 
+		'RAMPyBot',
296 
+		'RebelMouse',
297 
+		'REL Link Checker',
298 
+		'RetrevoPageAnalyzer',
299 
+		'Riddler',
300 
+		'Robosourcer',
301 
+		'rogerbot',
302 
+		'Ruby',
303 
+		'RufusBot',
304 
+		'SandCrawler',
305 
+		'SBIder',
306 
+		'ScoutJet',
307 
+		'ScoutURLMonitor',
308 
+		'Scrapy',
309 
+		'ScreenerBot',
310 
+		'scribdbot',
311 
+		'Scrubby',
312 
+		'SearchmetricsBot',
313 
+		'SearchSight',
314 
+		'seekbot',
315 
+		'semanticdiscovery',
316 
+		'SemrushBot',
317 
+		'Sensis Web Crawler',
318 
+		'SEOChat::Bot',
319 
+		'seokicks-robot',
320 
+		'SEOstats',
321 
+		'Seznam screenshot-generator',
322 
+		'seznambot',
323 
+		'Shim-Crawler',
324 
+		'ShopWiki',
325 
+		'Shoula robot',
326 
+		'ShowyouBot',
327 
+		'SimpleCrawler',
328 
+		'sistrix crawler',
329 
+		'SiteBar',
330 
+		'sitebot',
331 
+		'siteexplorer\.info',
332 
+		'SklikBot',
333 
+		'slider\.com',
334 
+		'slurp',
335 
+		'smtbot',
336 
+		'Snappy',
337 
+		'sogou spider',
338 
+		'sogou',
339 
+		'Sosospider',
340 
+		'spbot',
341 
+		'Speedy Spider',
342 
+		'speedy',
343 
+		'SpiderMan',
344 
+		'Sqworm',
345 
+		'SSL-Crawler',
346 
+		'StackRambler',
347 
+		'suggybot',
348 
+		'summify',
349 
+		'SurdotlyBot',
350 
+		'SurveyBot',
351 
+		'SynooBot',
352 
+		'tagoobot',
353 
+		'teoma',
354 
+		'TerrawizBot',
355 
+		'TheSuBot',
356 
+		'Thumbnail\.CZ robot',
357 
+		'TinEye',
358 
+		'toplistbot',
359 
+		'trendictionbot',
360 
+		'TrueBot',
361 
+		'truwoGPS',
362 
+		'turnitinbot',
363 
+		'TweetedTimes Bot',
364 
+		'tweetedtimes.com',
365 
+		'TweetmemeBot',
366 
+		'twengabot',
367 
+		'Twikle',
368 
+		'Twitterbot',
369 
+		'uMBot',
370 
+		'UnisterBot',
371 
+		'UnwindFetchor',
372 
+		'updated',
373 
+		'urlappendbot',
374 
+		'Urlfilebot',
375 
+		'urlresolver',
376 
+		'UsineNouvelleCrawler',
377 
+		'Vagabondo',
378 
+		'Vivante Link Checker',
379 
+		'voilabot',
380 
+		'Vortex',
381 
+		'voyager\\/',
382 
+		'VYU2',
383 
+		'web-archive-net\.com\.bot',
384 
+		'Websquash\.com',
385 
+		'WeSEE:Ads\/PageBot',
386 
+		'wbsearchbot',
387 
+		'webcollage',
388 
+		'webcompanycrawler',
389 
+		'webcrawler',
390 
+		'webmon ',
391 
+		'WeSEE:Search',
392 
+		'wf84',
393 
+		'wget',
394 
+		'wocbot',
395 
+		'WoFindeIch Robot',
396 
+		'WomlpeFactory',
397 
+		'woriobot',
398 
+		'wotbox',
399 
+		'Xaldon_WebSpider',
400 
+		'Xenu Link Sleuth',
401 
+		'xintellibot',
402 
+		'XML Sitemaps Generator',
403 
+		'XoviBot',
404 
+		'Y!J-ASR',
405 
+		'yacy',
406 
+		'yacybot',
407 
+		'Yahoo Link Preview',
408 
+		'Yahoo! Slurp China',
409 
+		'Yahoo! Slurp',
410 
+		'YahooSeeker',
411 
+		'YahooSeeker-Testing',
412 
+		'YandexBot',
413 
+		'YandexImages',
414 
+		'YandexMetrika',
415 
+		'yandex',
416 
+		'yanga',
417 
+		'Yasaklibot',
418 
+		'yeti',
419 
+		'YioopBot',
420 
+		'YisouSpider',
421 
+		'YodaoBot',
422 
+		'yoogliFetchAgent',
423 
+		'yoozBot',
424 
+		'YoudaoBot',
425 
+		'Zao',
426 
+		'Zealbot',
427 
+		'zspider',
428 
+		'ZyBorg',
429 
+		'[a-z0-9\\-_]*((?<!cu)bot|crawler|archiver|transcoder|spider)',
430 
+	);
431 431
432 
-    /**
433 
-     * All possible HTTP headers that represent the
434 
-     * User-Agent string.
435 
-     *
436 
-     * @var array
437 
-     */
438 
-    protected static $uaHttpHeaders = array(
439 
-        // The default User-Agent string.
440 
-        'HTTP_USER_AGENT',
441 
-        // Header can occur on devices using Opera Mini.
442 
-        'HTTP_X_OPERAMINI_PHONE_UA',
443 
-        // Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/
444 
-        'HTTP_X_DEVICE_USER_AGENT',
445 
-        'HTTP_X_ORIGINAL_USER_AGENT',
446 
-        'HTTP_X_SKYFIRE_PHONE',
447 
-        'HTTP_X_BOLT_PHONE_UA',
448 
-        'HTTP_DEVICE_STOCK_UA',
449 
-        'HTTP_X_UCBROWSER_DEVICE_UA',
450 
-    );
432 
+	/**
433 
+	 * All possible HTTP headers that represent the
434 
+	 * User-Agent string.
435 
+	 *
436 
+	 * @var array
437 
+	 */
438 
+	protected static $uaHttpHeaders = array(
439 
+		// The default User-Agent string.
440 
+		'HTTP_USER_AGENT',
441 
+		// Header can occur on devices using Opera Mini.
442 
+		'HTTP_X_OPERAMINI_PHONE_UA',
443 
+		// Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/
444 
+		'HTTP_X_DEVICE_USER_AGENT',
445 
+		'HTTP_X_ORIGINAL_USER_AGENT',
446 
+		'HTTP_X_SKYFIRE_PHONE',
447 
+		'HTTP_X_BOLT_PHONE_UA',
448 
+		'HTTP_DEVICE_STOCK_UA',
449 
+		'HTTP_X_UCBROWSER_DEVICE_UA',
450 
+	);
451 451
452 
-    /**
453 
-     * Class constructor.
454 
-     */
455 
-    public function __construct(array $headers = null, $userAgent = null)
456 
-    {
457 
-        $this->setHttpHeaders($headers);
458 
-        $this->setUserAgent($userAgent);
459 
-    }
452 
+	/**
453 
+	 * Class constructor.
454 
+	 */
455 
+	public function __construct(array $headers = null, $userAgent = null)
456 
+	{
457 
+		$this->setHttpHeaders($headers);
458 
+		$this->setUserAgent($userAgent);
459 
+	}
460 460
461 
-    public function setHttpHeaders($httpHeaders = null)
462 
-    {
463 
-        // use global _SERVER if $httpHeaders aren't defined
464 
-        if (!is_array($httpHeaders) || !count($httpHeaders)) {
465 
-            $httpHeaders = $_SERVER;
466 
-        }
467 
-        // clear existing headers
468 
-        $this->httpHeaders = array();
469 
-        // Only save HTTP headers. In PHP land, that means only _SERVER vars that
470 
-        // start with HTTP_.
471 
-        foreach ($httpHeaders as $key => $value) {
472 
-            if (substr($key, 0, 5) === 'HTTP_') {
473 
-                $this->httpHeaders[$key] = $value;
474 
-            }
475 
-        }
476 
-    }
461 
+	public function setHttpHeaders($httpHeaders = null)
462 
+	{
463 
+		// use global _SERVER if $httpHeaders aren't defined
464 
+		if (!is_array($httpHeaders) || !count($httpHeaders)) {
465 
+			$httpHeaders = $_SERVER;
466 
+		}
467 
+		// clear existing headers
468 
+		$this->httpHeaders = array();
469 
+		// Only save HTTP headers. In PHP land, that means only _SERVER vars that
470 
+		// start with HTTP_.
471 
+		foreach ($httpHeaders as $key => $value) {
472 
+			if (substr($key, 0, 5) === 'HTTP_') {
473 
+				$this->httpHeaders[$key] = $value;
474 
+			}
475 
+		}
476 
+	}
477 477
478 
-    public function getUaHttpHeaders()
479 
-    {
480 
-        return self::$uaHttpHeaders;
481 
-    }
478 
+	public function getUaHttpHeaders()
479 
+	{
480 
+		return self::$uaHttpHeaders;
481 
+	}
482 482
483 
-    public function setUserAgent($userAgent = null)
484 
-    {
485 
-        if (false === empty($userAgent)) {
486 
-            return $this->userAgent = $userAgent;
487 
-        } else {
488 
-            $this->userAgent = null;
489 
-            foreach ($this->getUaHttpHeaders() as $altHeader) {
490 
-                if (false === empty($this->httpHeaders[$altHeader])) { // @todo: should use getHttpHeader(), but it would be slow. (Serban)
491 
-                    $this->userAgent .= $this->httpHeaders[$altHeader].' ';
492 
-                }
493 
-            }
483 
+	public function setUserAgent($userAgent = null)
484 
+	{
485 
+		if (false === empty($userAgent)) {
486 
+			return $this->userAgent = $userAgent;
487 
+		} else {
488 
+			$this->userAgent = null;
489 
+			foreach ($this->getUaHttpHeaders() as $altHeader) {
490 
+				if (false === empty($this->httpHeaders[$altHeader])) { // @todo: should use getHttpHeader(), but it would be slow. (Serban)
491 
+					$this->userAgent .= $this->httpHeaders[$altHeader].' ';
492 
+				}
493 
+			}
494 494
495 
-            return $this->userAgent = (!empty($this->userAgent) ? trim($this->userAgent) : null);
496 
-        }
497 
-    }
495 
+			return $this->userAgent = (!empty($this->userAgent) ? trim($this->userAgent) : null);
496 
+		}
497 
+	}
498 498
499 
-    public function getRegex()
500 
-    {
501 
-        return '('.implode('|', self::$crawlers).')';
502 
-    }
499 
+	public function getRegex()
500 
+	{
501 
+		return '('.implode('|', self::$crawlers).')';
502 
+	}
503 503
504 
-    public function isCrawler($userAgent = null)
505 
-    {
506 
-        $agent = is_null($userAgent) ? $this->userAgent : $userAgent;
504 
+	public function isCrawler($userAgent = null)
505 
+	{
506 
+		$agent = is_null($userAgent) ? $this->userAgent : $userAgent;
507 507
508 
-        $result = preg_match('/'.$this->getRegex().'/i', $agent, $matches);
508 
+		$result = preg_match('/'.$this->getRegex().'/i', $agent, $matches);
509 509
510 
-        if ($matches) {
511 
-            $this->matches = $matches;
512 
-        }
510 
+		if ($matches) {
511 
+			$this->matches = $matches;
512 
+		}
513 513
514 
-        return (bool) $result;
515 
-    }
514 
+		return (bool) $result;
515 
+	}
516 516
517 
-    public function getMatches()
518 
-    {
519 
-        return $this->matches[0];
520 
-    }
517 
+	public function getMatches()
518 
+	{
519 
+		return $this->matches[0];
520 
+	}
521 521 
 }
Please login to merge, or discard this patch.
Spacing   +2 added lines, -2 removed lines patch added patch discarded remove patch 
@@ -461,7 +461,7 @@  discard block
 
 block discarded – undo
461 461 
     public function setHttpHeaders($httpHeaders = null)
462 462 
     {
463 463 
         // use global _SERVER if $httpHeaders aren't defined
464 
-        if (!is_array($httpHeaders) || !count($httpHeaders)) {
464 
+        if ( ! is_array($httpHeaders) || ! count($httpHeaders)) {
465 465 
             $httpHeaders = $_SERVER;
466 466 
         }
467 467 
         // clear existing headers
 
@@ -492,7 +492,7 @@  discard block
 
 block discarded – undo
492 492 
                 }
493 493 
             }
494 494
495 
-            return $this->userAgent = (!empty($this->userAgent) ? trim($this->userAgent) : null);
495 
+            return $this->userAgent = ( ! empty($this->userAgent) ? trim($this->userAgent) : null);
496 496 
         }
497 497 
     }
498 498
Please login to merge, or discard this patch.
tests/UATests.php 1 patch
Indentation   +21 added lines, -21 removed lines patch added patch discarded remove patch 
@@ -2,30 +2,30 @@
 
 block discarded – undo
2 2
3 3 
 class UserAgentTest extends PHPUnit_Framework_TestCase
4 4 
 {
5 
-    protected $CrawlerDetect;
5 
+	protected $CrawlerDetect;
6 6
7 
-    public function setUp()
8 
-    {
9 
-        $this->CrawlerDetect = new Jaybizzle\CrawlerDetect\CrawlerDetect();
10 
-    }
7 
+	public function setUp()
8 
+	{
9 
+		$this->CrawlerDetect = new Jaybizzle\CrawlerDetect\CrawlerDetect();
10 
+	}
11 11
12 
-    public function testBots()
13 
-    {
14 
-        $lines = file(__DIR__.'/crawlers.txt');
12 
+	public function testBots()
13 
+	{
14 
+		$lines = file(__DIR__.'/crawlers.txt');
15 15
16 
-        foreach ($lines as $line) {
17 
-            $test = $this->CrawlerDetect->isCrawler($line);
18 
-            $this->assertEquals($test, true, $line);
19 
-        }
20 
-    }
16 
+		foreach ($lines as $line) {
17 
+			$test = $this->CrawlerDetect->isCrawler($line);
18 
+			$this->assertEquals($test, true, $line);
19 
+		}
20 
+	}
21 21
22 
-    public function testDevices()
23 
-    {
24 
-        $lines = file(__DIR__.'/devices.txt');
22 
+	public function testDevices()
23 
+	{
24 
+		$lines = file(__DIR__.'/devices.txt');
25 25
26 
-        foreach ($lines as $line) {
27 
-            $test = $this->CrawlerDetect->isCrawler($line);
28 
-            $this->assertEquals($test, false, $line);
29 
-        }
30 
-    }
26 
+		foreach ($lines as $line) {
27 
+			$test = $this->CrawlerDetect->isCrawler($line);
28 
+			$this->assertEquals($test, false, $line);
29 
+		}
30 
+	}
31 31 
 }
Please login to merge, or discard this patch.