View GitHub Repository Crawler-Detect

Schedule Inspection
Subscribe
Completed
Push — master ( 082cfe...e31477 )
by Mark
04:01 queued 01:43
created
Status
Category
Toggle Patches
src/CrawlerDetect.php 2 patches
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.
Indentation   +491 added lines, -491 removed lines patch added patch discarded remove patch 
@@ -4,514 +4,514 @@
 
 block discarded – undo
4 4
5 5 
 class CrawlerDetect
6 6 
 {
7 
-    /**
8 
-     * The user agent.
9 
-     *
10 
-     * @var null
11 
-     */
12 
-    protected $userAgent = null;
7 
+	/**
8 
+	 * The user agent.
9 
+	 *
10 
+	 * @var null
11 
+	 */
12 
+	protected $userAgent = null;
13 13
14 
-    /**
15 
-     * Headers that contain a user agent.
16 
-     *
17 
-     * @var array
18 
-     */
19 
-    protected $httpHeaders = array();
14 
+	/**
15 
+	 * Headers that contain a user agent.
16 
+	 *
17 
+	 * @var array
18 
+	 */
19 
+	protected $httpHeaders = array();
20 20
21 
-    /**
22 
-     * Store regex matches.
23 
-     *
24 
-     * @var array
25 
-     */
26 
-    protected $matches = array();
21 
+	/**
22 
+	 * Store regex matches.
23 
+	 *
24 
+	 * @var array
25 
+	 */
26 
+	protected $matches = array();
27 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 
-    );
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 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 
-        'Apache-HttpClient\/',
97 
-        'Arachmo',
98 
-        'archive-com',
99 
-        'B-l-i-t-z-B-O-T',
100 
-        'Backlink-Ceck\.de',
101 
-        'BazQux',
102 
-        'bibnum\.bnf',
103 
-        'biglotron',
104 
-        'BingPreview',
105 
-        'binlar',
106 
-        'Bloglovin',
107 
-        'Blogtrottr',
108 
-        'boitho\.com-dc',
109 
-        'Browsershots',
110 
-        'BUbiNG',
111 
-        'Butterfly\\/',
112 
-        'BuzzSumo',
113 
-        'CapsuleChecker',
114 
-        'CC Metadata Scaper',
115 
-        'Cerberian Drtrs',
116 
-        'changedetection',
117 
-        'Charlotte',
118 
-        'clips\.ua\.ac\.be',
119 
-        'CloudFlare-AlwaysOnline',
120 
-        'coccoc',
121 
-        'CommaFeed',
122 
-        'Commons-HttpClient',
123 
-        'convera',
124 
-        'cosmos',
125 
-        'Covario-IDS',
126 
-        'Curious George',
127 
-        'curl',
128 
-        'CyberPatrol',
129 
-        'DataparkSearch',
130 
-        'dataprovider',
131 
-        'Daum(oa)?[ \\/][0-9]',
132 
-        'Digg',
133 
-        'DomainAppender',
134 
-        'Dragonfly File Reader',
135 
-        'drupact',
136 
-        'EARTHCOM',
137 
-        'ec2linkfinder',
138 
-        'ECCP',
139 
-        'ElectricMonk',
140 
-        'EMail Exractor',
141 
-        'EmailWolf',
142 
-        'Embed PHP Library',
143 
-        'Embedly',
144 
-        'europarchive\.org',
145 
-        'EventMachine HttpClient',
146 
-        'ExactSearch',
147 
-        'ExaleadCloudview',
148 
-        'eZ Publish Link Validator',
149 
-        'ezooms',
150 
-        'facebookexternalhit',
151 
-        'facebookplatform',
152 
-        'Feed Wrangler',
153 
-        'Feedbin',
154 
-        'FeedBurner',
155 
-        'Feedfetcher-Google',
156 
-        'Feedly',
157 
-        'Feedspot',
158 
-        'FeedValidator',
159 
-        'Fever',
160 
-        'findlink',
161 
-        'findthatfile',
162 
-        'Flamingo_SearchEngine',
163 
-        'fluffy',
164 
-        'g00g1e\.net',
165 
-        'Genieo',
166 
-        'getprismatic\.com',
167 
-        'GigablastOpenSource',
168 
-        'Go-http-client',
169 
-        'Google favicon',
170 
-        'Google Keyword Suggestion',
171 
-        'Google Page Speed Insights',
172 
-        'Google-HTTP-Java-Client',
173 
-        'google_partner_monitoring',
174 
-        'GoogleProducer',
175 
-        'grub-client',
176 
-        'heritrix',
177 
-        'Holmes',
178 
-        'htdig',
179 
-        'HTTPMon',
180 
-        'httpunit',
181 
-        'http_request2',
182 
-        'httrack',
183 
-        'HubPages.*crawlingpolicy',
184 
-        'HubSpot Marketing Grader',
185 
-        'ichiro',
186 
-        'IDG Twitter Links Resolver',
187 
-        'igdeSpyder',
188 
-        'InAGist',
189 
-        'infegy',
190 
-        'InfoWizards Reciprocal Link System PRO',
191 
-        'inpwrd\.com',
192 
-        'integromedb',
193 
-        'IODC',
194 
-        'IOI',
195 
-        'ips-agent',
196 
-        'iZSearch',
197 
-        '^Java\/',
198 
-        'Jigsaw',
199 
-        'Jobrapido',
200 
-        'kouio',
201 
-        'L\.webis',
202 
-        'Larbin',
203 
-        'libwww',
204 
-        'Link Valet',
205 
-        'linkCheck',
206 
-        'linkdex',
207 
-        'LinkExaminer',
208 
-        'LinkWalker',
209 
-        'Lipperhey',
210 
-        'LongURL API',
211 
-        'ltx71',
212 
-        'lwp-trivial',
213 
-        'lycos',
214 
-        'mabontland',
215 
-        'MagpieRSS',
216 
-        'Mediapartners-Google',
217 
-        'Mediapartners-Google',
218 
-        'MegaIndex\.ru',
219 
-        'MetaURI',
220 
-        'Mnogosearch',
221 
-        'mogimogi',
222 
-        'Morning Paper',
223 
-        'Mrcgiguy',
224 
-        'MVAClient',
225 
-        'Netcraft Web Server Survey',
226 
-        'NetcraftSurveyAgent',
227 
-        'NetLyzer FastProbe',
228 
-        'netresearch',
229 
-        'Netvibes',
230 
-        'NewsBlur .*(Fetcher|Finder)',
231 
-        'NewsGator',
232 
-        'newsme',
233 
-        'NG-Search',
234 
-        'nineconnections\.com',
235 
-        'nominet\.org\.uk',
236 
-        'Notifixious',
237 
-        'nuhk',
238 
-        'nutch',
239 
-        'Nymesis',
240 
-        'oegp',
241 
-        'Omea Reader',
242 
-        'online link validator',
243 
-        'Online Website Link Checker',
244 
-        'Orbiter',
245 
-        'ow\.ly',
246 
-        'page2rss',
247 
-        'PagePeeker',
248 
-        'panscient',
249 
-        'Peew',
250 
-        'phpcrawl',
251 
-        'phpservermon',
252 
-        'Pingdom\.com',
253 
-        'Pinterest',
254 
-        'Pizilla',
255 
-        'Ploetz \+ Zeller',
256 
-        'Plukkie',
257 
-        'PocketParser',
258 
-        'Pompos',
259 
-        'postano',
260 
-        'PostPost',
261 
-        'postrank',
262 
-        'proximic',
263 
-        'Pulsepoint XT3 web scraper',
264 
-        'Python-httplib2',
265 
-        'python-requests',
266 
-        'Python-urllib',
267 
-        'Qseero',
268 
-        'Qwantify',
269 
-        'Radian6',
270 
-        'RebelMouse',
271 
-        'REL Link Checker',
272 
-        'RetrevoPageAnalyzer',
273 
-        'Riddler',
274 
-        'Robosourcer',
275 
-        'ROI Hunter',
276 
-        'Ruby',
277 
-        'SalesIntelligent',
278 
-        'SBIder',
279 
-        'scooter',
280 
-        'ScoutJet',
281 
-        'ScoutURLMonitor',
282 
-        'Scrapy',
283 
-        'Scrubby',
284 
-        'SearchSight',
285 
-        'semanticdiscovery',
286 
-        'SEOstats',
287 
-        'Server Density Service Monitoring.*',
288 
-        'servernfo\.com',
289 
-        'Seznam screenshot-generator',
290 
-        'ShopWiki',
291 
-        'SilverReader',
292 
-        'SimplePie',
293 
-        'Site24x7',
294 
-        'SiteBar',
295 
-        'siteexplorer\.info',
296 
-        'Siteimprove\.com',
297 
-        'SkypeUriPreview',
298 
-        'slider\.com',
299 
-        'slurp',
300 
-        'Snappy',
301 
-        'SNK Siteshooter B0t',
302 
-        'sogou',
303 
-        'SortSite',
304 
-        'speedy',
305 
-        'Spinn3r',
306 
-        'Springshare Link Checker',
307 
-        'Sqworm',
308 
-        'StackRambler',
309 
-        'Stratagems Kumo',
310 
-        'summify',
311 
-        'teoma',
312 
-        'theoldreader\.com',
313 
-        'TinEye',
314 
-        'Tiny Tiny RSS',
315 
-        'Traackr.com',
316 
-        'truwoGPS',
317 
-        'tweetedtimes\.com',
318 
-        'Twikle',
319 
-        'Typhoeus',
320 
-        'ubermetrics-technologies',
321 
-        'UdmSearch',
322 
-        'UnwindFetchor',
323 
-        'updated',
324 
-        'URLChecker',
325 
-        'urlresolver',
326 
-        'Vagabondo',
327 
-        'Validator\.nu\\/LV',
328 
-        'via ggpht\.com GoogleImageProxy',
329 
-        'Vivante Link Checker',
330 
-        'Vortex',
331 
-        'voyager\\/',
332 
-        'VYU2',
333 
-        'W3C-checklink',
334 
-        'W3C-mobileOK',
335 
-        'W3C_CSS_Validator_JFouffa',
336 
-        'W3C_I18n-Checker',
337 
-        'W3C_Unicorn',
338 
-        'W3C_Validator',
339 
-        'web-capture\.net',
340 
-        'webcollage',
341 
-        'WebIndex',
342 
-        'webmon ',
343 
-        'websitepulse[+ ]checker',
344 
-        'Websquash\.com',
345 
-        'WebThumbnail',
346 
-        'WeSEE:Search',
347 
-        'wf84',
348 
-        'wget',
349 
-        'WomlpeFactory',
350 
-        'wotbox',
351 
-        'www\.monitor\.us',
352 
-        'XaxisSemanticsClassifier',
353 
-        'Xenu Link Sleuth',
354 
-        'XML Sitemaps Generator',
355 
-        'Y!J-ASR',
356 
-        'yacy',
357 
-        'Yahoo Ad monitoring',
358 
-        'Yahoo Link Preview',
359 
-        'YahooSeeker',
360 
-        'yandex',
361 
-        'yanga',
362 
-        'yeti',
363 
-        'yoogliFetchAgent',
364 
-        'YottaaMonitor',
365 
-        'Zao',
366 
-        'ZyBorg',
367 
-        '[a-z0-9\\-_]*((?<!cu)bot|crawler|archiver|transcoder|spider)',
368 
-    );
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 
+		'Apache-HttpClient\/',
97 
+		'Arachmo',
98 
+		'archive-com',
99 
+		'B-l-i-t-z-B-O-T',
100 
+		'Backlink-Ceck\.de',
101 
+		'BazQux',
102 
+		'bibnum\.bnf',
103 
+		'biglotron',
104 
+		'BingPreview',
105 
+		'binlar',
106 
+		'Bloglovin',
107 
+		'Blogtrottr',
108 
+		'boitho\.com-dc',
109 
+		'Browsershots',
110 
+		'BUbiNG',
111 
+		'Butterfly\\/',
112 
+		'BuzzSumo',
113 
+		'CapsuleChecker',
114 
+		'CC Metadata Scaper',
115 
+		'Cerberian Drtrs',
116 
+		'changedetection',
117 
+		'Charlotte',
118 
+		'clips\.ua\.ac\.be',
119 
+		'CloudFlare-AlwaysOnline',
120 
+		'coccoc',
121 
+		'CommaFeed',
122 
+		'Commons-HttpClient',
123 
+		'convera',
124 
+		'cosmos',
125 
+		'Covario-IDS',
126 
+		'Curious George',
127 
+		'curl',
128 
+		'CyberPatrol',
129 
+		'DataparkSearch',
130 
+		'dataprovider',
131 
+		'Daum(oa)?[ \\/][0-9]',
132 
+		'Digg',
133 
+		'DomainAppender',
134 
+		'Dragonfly File Reader',
135 
+		'drupact',
136 
+		'EARTHCOM',
137 
+		'ec2linkfinder',
138 
+		'ECCP',
139 
+		'ElectricMonk',
140 
+		'EMail Exractor',
141 
+		'EmailWolf',
142 
+		'Embed PHP Library',
143 
+		'Embedly',
144 
+		'europarchive\.org',
145 
+		'EventMachine HttpClient',
146 
+		'ExactSearch',
147 
+		'ExaleadCloudview',
148 
+		'eZ Publish Link Validator',
149 
+		'ezooms',
150 
+		'facebookexternalhit',
151 
+		'facebookplatform',
152 
+		'Feed Wrangler',
153 
+		'Feedbin',
154 
+		'FeedBurner',
155 
+		'Feedfetcher-Google',
156 
+		'Feedly',
157 
+		'Feedspot',
158 
+		'FeedValidator',
159 
+		'Fever',
160 
+		'findlink',
161 
+		'findthatfile',
162 
+		'Flamingo_SearchEngine',
163 
+		'fluffy',
164 
+		'g00g1e\.net',
165 
+		'Genieo',
166 
+		'getprismatic\.com',
167 
+		'GigablastOpenSource',
168 
+		'Go-http-client',
169 
+		'Google favicon',
170 
+		'Google Keyword Suggestion',
171 
+		'Google Page Speed Insights',
172 
+		'Google-HTTP-Java-Client',
173 
+		'google_partner_monitoring',
174 
+		'GoogleProducer',
175 
+		'grub-client',
176 
+		'heritrix',
177 
+		'Holmes',
178 
+		'htdig',
179 
+		'HTTPMon',
180 
+		'httpunit',
181 
+		'http_request2',
182 
+		'httrack',
183 
+		'HubPages.*crawlingpolicy',
184 
+		'HubSpot Marketing Grader',
185 
+		'ichiro',
186 
+		'IDG Twitter Links Resolver',
187 
+		'igdeSpyder',
188 
+		'InAGist',
189 
+		'infegy',
190 
+		'InfoWizards Reciprocal Link System PRO',
191 
+		'inpwrd\.com',
192 
+		'integromedb',
193 
+		'IODC',
194 
+		'IOI',
195 
+		'ips-agent',
196 
+		'iZSearch',
197 
+		'^Java\/',
198 
+		'Jigsaw',
199 
+		'Jobrapido',
200 
+		'kouio',
201 
+		'L\.webis',
202 
+		'Larbin',
203 
+		'libwww',
204 
+		'Link Valet',
205 
+		'linkCheck',
206 
+		'linkdex',
207 
+		'LinkExaminer',
208 
+		'LinkWalker',
209 
+		'Lipperhey',
210 
+		'LongURL API',
211 
+		'ltx71',
212 
+		'lwp-trivial',
213 
+		'lycos',
214 
+		'mabontland',
215 
+		'MagpieRSS',
216 
+		'Mediapartners-Google',
217 
+		'Mediapartners-Google',
218 
+		'MegaIndex\.ru',
219 
+		'MetaURI',
220 
+		'Mnogosearch',
221 
+		'mogimogi',
222 
+		'Morning Paper',
223 
+		'Mrcgiguy',
224 
+		'MVAClient',
225 
+		'Netcraft Web Server Survey',
226 
+		'NetcraftSurveyAgent',
227 
+		'NetLyzer FastProbe',
228 
+		'netresearch',
229 
+		'Netvibes',
230 
+		'NewsBlur .*(Fetcher|Finder)',
231 
+		'NewsGator',
232 
+		'newsme',
233 
+		'NG-Search',
234 
+		'nineconnections\.com',
235 
+		'nominet\.org\.uk',
236 
+		'Notifixious',
237 
+		'nuhk',
238 
+		'nutch',
239 
+		'Nymesis',
240 
+		'oegp',
241 
+		'Omea Reader',
242 
+		'online link validator',
243 
+		'Online Website Link Checker',
244 
+		'Orbiter',
245 
+		'ow\.ly',
246 
+		'page2rss',
247 
+		'PagePeeker',
248 
+		'panscient',
249 
+		'Peew',
250 
+		'phpcrawl',
251 
+		'phpservermon',
252 
+		'Pingdom\.com',
253 
+		'Pinterest',
254 
+		'Pizilla',
255 
+		'Ploetz \+ Zeller',
256 
+		'Plukkie',
257 
+		'PocketParser',
258 
+		'Pompos',
259 
+		'postano',
260 
+		'PostPost',
261 
+		'postrank',
262 
+		'proximic',
263 
+		'Pulsepoint XT3 web scraper',
264 
+		'Python-httplib2',
265 
+		'python-requests',
266 
+		'Python-urllib',
267 
+		'Qseero',
268 
+		'Qwantify',
269 
+		'Radian6',
270 
+		'RebelMouse',
271 
+		'REL Link Checker',
272 
+		'RetrevoPageAnalyzer',
273 
+		'Riddler',
274 
+		'Robosourcer',
275 
+		'ROI Hunter',
276 
+		'Ruby',
277 
+		'SalesIntelligent',
278 
+		'SBIder',
279 
+		'scooter',
280 
+		'ScoutJet',
281 
+		'ScoutURLMonitor',
282 
+		'Scrapy',
283 
+		'Scrubby',
284 
+		'SearchSight',
285 
+		'semanticdiscovery',
286 
+		'SEOstats',
287 
+		'Server Density Service Monitoring.*',
288 
+		'servernfo\.com',
289 
+		'Seznam screenshot-generator',
290 
+		'ShopWiki',
291 
+		'SilverReader',
292 
+		'SimplePie',
293 
+		'Site24x7',
294 
+		'SiteBar',
295 
+		'siteexplorer\.info',
296 
+		'Siteimprove\.com',
297 
+		'SkypeUriPreview',
298 
+		'slider\.com',
299 
+		'slurp',
300 
+		'Snappy',
301 
+		'SNK Siteshooter B0t',
302 
+		'sogou',
303 
+		'SortSite',
304 
+		'speedy',
305 
+		'Spinn3r',
306 
+		'Springshare Link Checker',
307 
+		'Sqworm',
308 
+		'StackRambler',
309 
+		'Stratagems Kumo',
310 
+		'summify',
311 
+		'teoma',
312 
+		'theoldreader\.com',
313 
+		'TinEye',
314 
+		'Tiny Tiny RSS',
315 
+		'Traackr.com',
316 
+		'truwoGPS',
317 
+		'tweetedtimes\.com',
318 
+		'Twikle',
319 
+		'Typhoeus',
320 
+		'ubermetrics-technologies',
321 
+		'UdmSearch',
322 
+		'UnwindFetchor',
323 
+		'updated',
324 
+		'URLChecker',
325 
+		'urlresolver',
326 
+		'Vagabondo',
327 
+		'Validator\.nu\\/LV',
328 
+		'via ggpht\.com GoogleImageProxy',
329 
+		'Vivante Link Checker',
330 
+		'Vortex',
331 
+		'voyager\\/',
332 
+		'VYU2',
333 
+		'W3C-checklink',
334 
+		'W3C-mobileOK',
335 
+		'W3C_CSS_Validator_JFouffa',
336 
+		'W3C_I18n-Checker',
337 
+		'W3C_Unicorn',
338 
+		'W3C_Validator',
339 
+		'web-capture\.net',
340 
+		'webcollage',
341 
+		'WebIndex',
342 
+		'webmon ',
343 
+		'websitepulse[+ ]checker',
344 
+		'Websquash\.com',
345 
+		'WebThumbnail',
346 
+		'WeSEE:Search',
347 
+		'wf84',
348 
+		'wget',
349 
+		'WomlpeFactory',
350 
+		'wotbox',
351 
+		'www\.monitor\.us',
352 
+		'XaxisSemanticsClassifier',
353 
+		'Xenu Link Sleuth',
354 
+		'XML Sitemaps Generator',
355 
+		'Y!J-ASR',
356 
+		'yacy',
357 
+		'Yahoo Ad monitoring',
358 
+		'Yahoo Link Preview',
359 
+		'YahooSeeker',
360 
+		'yandex',
361 
+		'yanga',
362 
+		'yeti',
363 
+		'yoogliFetchAgent',
364 
+		'YottaaMonitor',
365 
+		'Zao',
366 
+		'ZyBorg',
367 
+		'[a-z0-9\\-_]*((?<!cu)bot|crawler|archiver|transcoder|spider)',
368 
+	);
369 369
370 
-    /**
371 
-     * All possible HTTP headers that represent the
372 
-     * User-Agent string.
373 
-     *
374 
-     * @var array
375 
-     */
376 
-    protected static $uaHttpHeaders = array(
377 
-        // The default User-Agent string.
378 
-        'HTTP_USER_AGENT',
379 
-        // Header can occur on devices using Opera Mini.
380 
-        'HTTP_X_OPERAMINI_PHONE_UA',
381 
-        // Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/
382 
-        'HTTP_X_DEVICE_USER_AGENT',
383 
-        'HTTP_X_ORIGINAL_USER_AGENT',
384 
-        'HTTP_X_SKYFIRE_PHONE',
385 
-        'HTTP_X_BOLT_PHONE_UA',
386 
-        'HTTP_DEVICE_STOCK_UA',
387 
-        'HTTP_X_UCBROWSER_DEVICE_UA',
388 
-    );
370 
+	/**
371 
+	 * All possible HTTP headers that represent the
372 
+	 * User-Agent string.
373 
+	 *
374 
+	 * @var array
375 
+	 */
376 
+	protected static $uaHttpHeaders = array(
377 
+		// The default User-Agent string.
378 
+		'HTTP_USER_AGENT',
379 
+		// Header can occur on devices using Opera Mini.
380 
+		'HTTP_X_OPERAMINI_PHONE_UA',
381 
+		// Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/
382 
+		'HTTP_X_DEVICE_USER_AGENT',
383 
+		'HTTP_X_ORIGINAL_USER_AGENT',
384 
+		'HTTP_X_SKYFIRE_PHONE',
385 
+		'HTTP_X_BOLT_PHONE_UA',
386 
+		'HTTP_DEVICE_STOCK_UA',
387 
+		'HTTP_X_UCBROWSER_DEVICE_UA',
388 
+	);
389 389
390 
-    /**
391 
-     * Class constructor.
392 
-     */
393 
-    public function __construct(array $headers = null, $userAgent = null)
394 
-    {
395 
-        $this->setHttpHeaders($headers);
396 
-        $this->setUserAgent($userAgent);
397 
-    }
390 
+	/**
391 
+	 * Class constructor.
392 
+	 */
393 
+	public function __construct(array $headers = null, $userAgent = null)
394 
+	{
395 
+		$this->setHttpHeaders($headers);
396 
+		$this->setUserAgent($userAgent);
397 
+	}
398 398
399 
-    /**
400 
-     * Set HTTP headers.
401 
-     *
402 
-     * @param array $httpHeaders
403 
-     */
404 
-    public function setHttpHeaders($httpHeaders = null)
405 
-    {
406 
-        // use global _SERVER if $httpHeaders aren't defined
407 
-        if (!is_array($httpHeaders) || !count($httpHeaders)) {
408 
-            $httpHeaders = $_SERVER;
409 
-        }
410 
-        // clear existing headers
411 
-        $this->httpHeaders = array();
412 
-        // Only save HTTP headers. In PHP land, that means only _SERVER vars that
413 
-        // start with HTTP_.
414 
-        foreach ($httpHeaders as $key => $value) {
415 
-            if (substr($key, 0, 5) === 'HTTP_') {
416 
-                $this->httpHeaders[$key] = $value;
417 
-            }
418 
-        }
419 
-    }
399 
+	/**
400 
+	 * Set HTTP headers.
401 
+	 *
402 
+	 * @param array $httpHeaders
403 
+	 */
404 
+	public function setHttpHeaders($httpHeaders = null)
405 
+	{
406 
+		// use global _SERVER if $httpHeaders aren't defined
407 
+		if (!is_array($httpHeaders) || !count($httpHeaders)) {
408 
+			$httpHeaders = $_SERVER;
409 
+		}
410 
+		// clear existing headers
411 
+		$this->httpHeaders = array();
412 
+		// Only save HTTP headers. In PHP land, that means only _SERVER vars that
413 
+		// start with HTTP_.
414 
+		foreach ($httpHeaders as $key => $value) {
415 
+			if (substr($key, 0, 5) === 'HTTP_') {
416 
+				$this->httpHeaders[$key] = $value;
417 
+			}
418 
+		}
419 
+	}
420 420
421 
-    /**
422 
-     * Return user agent headers.
423 
-     *
424 
-     * @return array
425 
-     */
426 
-    public function getUaHttpHeaders()
427 
-    {
428 
-        return self::$uaHttpHeaders;
429 
-    }
421 
+	/**
422 
+	 * Return user agent headers.
423 
+	 *
424 
+	 * @return array
425 
+	 */
426 
+	public function getUaHttpHeaders()
427 
+	{
428 
+		return self::$uaHttpHeaders;
429 
+	}
430 430
431 
-    /**
432 
-     * Set the user agent.
433 
-     *
434 
-     * @param string $userAgent
435 
-     */
436 
-    public function setUserAgent($userAgent = null)
437 
-    {
438 
-        if (false === empty($userAgent)) {
439 
-            return $this->userAgent = $userAgent;
440 
-        } else {
441 
-            $this->userAgent = null;
442 
-            foreach ($this->getUaHttpHeaders() as $altHeader) {
443 
-                if (false === empty($this->httpHeaders[$altHeader])) { // @todo: should use getHttpHeader(), but it would be slow.
444 
-                    $this->userAgent .= $this->httpHeaders[$altHeader].' ';
445 
-                }
446 
-            }
431 
+	/**
432 
+	 * Set the user agent.
433 
+	 *
434 
+	 * @param string $userAgent
435 
+	 */
436 
+	public function setUserAgent($userAgent = null)
437 
+	{
438 
+		if (false === empty($userAgent)) {
439 
+			return $this->userAgent = $userAgent;
440 
+		} else {
441 
+			$this->userAgent = null;
442 
+			foreach ($this->getUaHttpHeaders() as $altHeader) {
443 
+				if (false === empty($this->httpHeaders[$altHeader])) { // @todo: should use getHttpHeader(), but it would be slow.
444 
+					$this->userAgent .= $this->httpHeaders[$altHeader].' ';
445 
+				}
446 
+			}
447 447
448 
-            return $this->userAgent = (!empty($this->userAgent) ? trim($this->userAgent) : null);
449 
-        }
450 
-    }
448 
+			return $this->userAgent = (!empty($this->userAgent) ? trim($this->userAgent) : null);
449 
+		}
450 
+	}
451 451
452 
-    /**
453 
-     * Return the array of crawler regexs.
454 
-     *
455 
-     * @return array
456 
-     */
457 
-    public function getCrawlers()
458 
-    {
459 
-        return self::$crawlers;
460 
-    }
452 
+	/**
453 
+	 * Return the array of crawler regexs.
454 
+	 *
455 
+	 * @return array
456 
+	 */
457 
+	public function getCrawlers()
458 
+	{
459 
+		return self::$crawlers;
460 
+	}
461 461
462 
-    /**
463 
-     * Build the user agent regex.
464 
-     *
465 
-     * @return string
466 
-     */
467 
-    public function getRegex()
468 
-    {
469 
-        return '('.implode('|', self::$crawlers).')';
470 
-    }
462 
+	/**
463 
+	 * Build the user agent regex.
464 
+	 *
465 
+	 * @return string
466 
+	 */
467 
+	public function getRegex()
468 
+	{
469 
+		return '('.implode('|', self::$crawlers).')';
470 
+	}
471 471
472 
-    /**
473 
-     * Build the replacement regex.
474 
-     *
475 
-     * @return string
476 
-     */
477 
-    public function getIgnored()
478 
-    {
479 
-        return '('.implode('|', self::$ignore).')';
480 
-    }
472 
+	/**
473 
+	 * Build the replacement regex.
474 
+	 *
475 
+	 * @return string
476 
+	 */
477 
+	public function getIgnored()
478 
+	{
479 
+		return '('.implode('|', self::$ignore).')';
480 
+	}
481 481
482 
-    /**
483 
-     * Check user agent string against the regex.
484 
-     *
485 
-     * @param string $userAgent
486 
-     *
487 
-     * @return bool
488 
-     */
489 
-    public function isCrawler($userAgent = null)
490 
-    {
491 
-        $agent = is_null($userAgent) ? $this->userAgent : $userAgent;
482 
+	/**
483 
+	 * Check user agent string against the regex.
484 
+	 *
485 
+	 * @param string $userAgent
486 
+	 *
487 
+	 * @return bool
488 
+	 */
489 
+	public function isCrawler($userAgent = null)
490 
+	{
491 
+		$agent = is_null($userAgent) ? $this->userAgent : $userAgent;
492 492
493 
-        $agent = preg_replace('/'.$this->getIgnored().'/i', '', $agent);
493 
+		$agent = preg_replace('/'.$this->getIgnored().'/i', '', $agent);
494 494
495 
-        if (trim($agent) === false) {
496 
-            return false;
497 
-        } else {
498 
-            $result = preg_match('/'.$this->getRegex().'/i', trim($agent), $matches);
499 
-        }
495 
+		if (trim($agent) === false) {
496 
+			return false;
497 
+		} else {
498 
+			$result = preg_match('/'.$this->getRegex().'/i', trim($agent), $matches);
499 
+		}
500 500
501 
-        if ($matches) {
502 
-            $this->matches = $matches;
503 
-        }
501 
+		if ($matches) {
502 
+			$this->matches = $matches;
503 
+		}
504 504
505 
-        return (bool) $result;
506 
-    }
505 
+		return (bool) $result;
506 
+	}
507 507
508 
-    /**
509 
-     * Return the matches.
510 
-     *
511 
-     * @return string
512 
-     */
513 
-    public function getMatches()
514 
-    {
515 
-        return $this->matches[0];
516 
-    }
508 
+	/**
509 
+	 * Return the matches.
510 
+	 *
511 
+	 * @return string
512 
+	 */
513 
+	public function getMatches()
514 
+	{
515 
+		return $this->matches[0];
516 
+	}
517 517 
 }
Please login to merge, or discard this patch.
tests/UATests.php 1 patch
Indentation   +51 added lines, -51 removed lines patch added patch discarded remove patch 
@@ -2,55 +2,55 @@
 
 block discarded – undo
2 2
3 3 
 class UserAgentTest extends PHPUnit_Framework_TestCase
4 4 
 {
5 
-    protected $CrawlerDetect;
6 
-
7 
-    public function setUp()
8 
-    {
9 
-        $this->CrawlerDetect = new Jaybizzle\CrawlerDetect\CrawlerDetect();
10 
-    }
11 
-
12 
-    public function testBots()
13 
-    {
14 
-        $lines = file(__DIR__.'/crawlers.txt', FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
15 
-
16 
-        foreach ($lines as $line) {
17 
-            $test = $this->CrawlerDetect->isCrawler($line);
18 
-            $this->assertEquals($test, true, $line);
19 
-        }
20 
-    }
21 
-
22 
-    public function testDevices()
23 
-    {
24 
-        $lines = file(__DIR__.'/devices.txt', FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
25 
-
26 
-        foreach ($lines as $line) {
27 
-            $test = $this->CrawlerDetect->isCrawler($line);
28 
-            $this->assertEquals($test, false, $line);
29 
-        }
30 
-    }
31 
-
32 
-    public function testReturnsCorrectMatchedBotName()
33 
-    {
34 
-        $test = $this->CrawlerDetect->isCrawler('Mozilla/5.0 (iPhone; CPU iPhone OS 7_1 like Mac OS X) AppleWebKit (KHTML, like Gecko) Mobile (compatible; Yahoo Ad monitoring; https://help.yahoo.com/kb/yahoo-ad-monitoring-SLN24857.html)');
35 
-
36 
-        $matches = $this->CrawlerDetect->getMatches();
37 
-
38 
-        $this->assertEquals($this->CrawlerDetect->getMatches(), 'Yahoo Ad monitoring', $matches);
39 
-    }
40 
-
41 
-    public function testForRegexCollision()
42 
-    {
43 
-        $crawlers = $this->CrawlerDetect->getCrawlers();
44 
-
45 
-        foreach ($crawlers as $regex) {
46 
-            foreach ($crawlers as $compare) {
47 
-                // Dont check this regex against itself
48 
-                if ($regex != $compare) {
49 
-                    preg_match('/'.$regex.'/i', stripslashes($compare), $matches);
50 
-
51 
-                    $this->assertEmpty($matches, $regex.' collided with '.$compare);
52 
-                }
53 
-            }
54 
-        }
55 
-    }
5 
+	protected $CrawlerDetect;
6 
+
7 
+	public function setUp()
8 
+	{
9 
+		$this->CrawlerDetect = new Jaybizzle\CrawlerDetect\CrawlerDetect();
10 
+	}
11 
+
12 
+	public function testBots()
13 
+	{
14 
+		$lines = file(__DIR__.'/crawlers.txt', FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
15 
+
16 
+		foreach ($lines as $line) {
17 
+			$test = $this->CrawlerDetect->isCrawler($line);
18 
+			$this->assertEquals($test, true, $line);
19 
+		}
20 
+	}
21 
+
22 
+	public function testDevices()
23 
+	{
24 
+		$lines = file(__DIR__.'/devices.txt', FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
25 
+
26 
+		foreach ($lines as $line) {
27 
+			$test = $this->CrawlerDetect->isCrawler($line);
28 
+			$this->assertEquals($test, false, $line);
29 
+		}
30 
+	}
31 
+
32 
+	public function testReturnsCorrectMatchedBotName()
33 
+	{
34 
+		$test = $this->CrawlerDetect->isCrawler('Mozilla/5.0 (iPhone; CPU iPhone OS 7_1 like Mac OS X) AppleWebKit (KHTML, like Gecko) Mobile (compatible; Yahoo Ad monitoring; https://help.yahoo.com/kb/yahoo-ad-monitoring-SLN24857.html)');
35 
+
36 
+		$matches = $this->CrawlerDetect->getMatches();
37 
+
38 
+		$this->assertEquals($this->CrawlerDetect->getMatches(), 'Yahoo Ad monitoring', $matches);
39 
+	}
40 
+
41 
+	public function testForRegexCollision()
42 
+	{
43 
+		$crawlers = $this->CrawlerDetect->getCrawlers();
44 
+
45 
+		foreach ($crawlers as $regex) {
46 
+			foreach ($crawlers as $compare) {
47 
+				// Dont check this regex against itself
48 
+				if ($regex != $compare) {
49 
+					preg_match('/'.$regex.'/i', stripslashes($compare), $matches);
50 
+
51 
+					$this->assertEmpty($matches, $regex.' collided with '.$compare);
52 
+				}
53 
+			}
54 
+		}
55 
+	}
56 56 
 }
Please login to merge, or discard this patch.