View GitHub Repository Crawler-Detect

Schedule Inspection
Subscribe
Completed
Push — master ( 7281f1...737962 )
by Mark
10s
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   +433 added lines, -433 removed lines patch added patch discarded remove patch 
@@ -4,455 +4,455 @@
 
 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 
-        '008\\/',
85 
-        'A6-Indexer',
86 
-        'Aboundex',
87 
-        'Accoona-AI-Agent',
88 
-        'acoon',
89 
-        'AddThis',
90 
-        'ADmantX',
91 
-        'AHC',
92 
-        'Airmail',
93 
-        'Anemone',
94 
-        'Arachmo',
95 
-        'archive-com',
96 
-        'B-l-i-t-z-B-O-T',
97 
-        'bibnum\.bnf',
98 
-        'biglotron',
99 
-        'binlar',
100 
-        'BingPreview',
101 
-        'boitho\.com-dc',
102 
-        'BrokenLinkCheck\.com',
103 
-        'BUbiNG',
104 
-        'Butterfly\\/',
105 
-        'BuzzSumo',
106 
-        'CapsuleChecker',
107 
-        'CC Metadata Scaper',
108 
-        'Cerberian Drtrs',
109 
-        'changedetection',
110 
-        'Charlotte',
111 
-        'clips\.ua\.ac\.be',
112 
-        'CloudFlare-AlwaysOnline',
113 
-        'coccoc',
114 
-        'Commons-HttpClient',
115 
-        'convera',
116 
-        'cosmos',
117 
-        'Covario-IDS',
118 
-        'curl',
119 
-        'CyberPatrol',
120 
-        'Dragonfly File Reader',
121 
-        'DataparkSearch',
122 
-        'dataprovider',
123 
-        'Digg',
124 
-        'DomainAppender',
125 
-        'drupact',
126 
-        'EARTHCOM',
127 
-        'ECCP',
128 
-        'ec2linkfinder',
129 
-        'ElectricMonk',
130 
-        'Embedly',
131 
-        'europarchive\.org',
132 
-        'EventMachine HttpClient',
133 
-        'ExactSearch',
134 
-        'ezooms',
135 
-        'eZ Publish Link Validator',
136 
-        'facebookexternalhit',
137 
-        'FeedBurner',
138 
-        'Feedfetcher-Google',
139 
-        'FeedValidator',
140 
-        'FindLinks',
141 
-        'findlink',
142 
-        'findthatfile',
143 
-        'Flamingo_SearchEngine',
144 
-        'fluffy',
145 
-        'getprismatic\.com',
146 
-        'g00g1e\.net',
147 
-        'GigablastOpenSource',
148 
-        'grub-client',
149 
-        'Genieo',
150 
-        'Go-http-client',
151 
-        'Google-HTTP-Java-Client',
152 
-        'Google favicon',
153 
-        'Google Keyword Suggestion',
154 
-        'GoogleProducer',
155 
-        'heritrix',
156 
-        'Holmes',
157 
-        'htdig',
158 
-        'httpunit',
159 
-        'httrack',
160 
-        'HubSpot Marketing Grader',
161 
-        'ichiro',
162 
-        'infegy',
163 
-        'igdeSpyder',
164 
-        'InAGist',
165 
-        'InfoWizards Reciprocal Link System PRO',
166 
-        'integromedb',
167 
-        'IODC',
168 
-        'IOI',
169 
-        'ips-agent',
170 
-        'iZSearch',
171 
-        'Jobrapido',
172 
-        'L\.webis',
173 
-        'Larbin',
174 
-        'libwww',
175 
-        'Link Valet',
176 
-        'linkdex',
177 
-        'LinkExaminer',
178 
-        'LinkWalker',
179 
-        'Lipperhey Link Explorer',
180 
-        'Lipperhey SEO Service',
181 
-        'LongURL API',
182 
-        'ltx71',
183 
-        'lwp-trivial',
184 
-        'MegaIndex\.ru',
185 
-        'mabontland',
186 
-        'MagpieRSS',
187 
-        'Mediapartners-Google',
188 
-        'MetaURI',
189 
-        'Mnogosearch',
190 
-        'mogimogi',
191 
-        'Morning Paper',
192 
-        'Mrcgiguy',
193 
-        'MVAClient',
194 
-        'Netcraft Web Server Survey',
195 
-        'netresearchserver',
196 
-        'Netvibes',
197 
-        'NewsGator',
198 
-        'newsme',
199 
-        'NG-Search',
200 
-        '^NING\\/',
201 
-        'nineconnections\.com',
202 
-        'nominet\.org\.uk',
203 
-        'Notifixious',
204 
-        'nutch',
205 
-        'NutchCVS',
206 
-        'Nymesis',
207 
-        'oegp',
208 
-        'Omea Reader',
209 
-        'online link validator',
210 
-        'Online Website Link Checker',
211 
-        'Orbiter',
212 
-        'ow\.ly',
213 
-        'Ploetz \+ Zeller',
214 
-        'PagePeeker',
215 
-        'page2rss',
216 
-        'panscient',
217 
-        'Peew',
218 
-        'phpcrawl',
219 
-        'Pinterest',
220 
-        'Pizilla',
221 
-        'Plukkie',
222 
-        'Pompos',
223 
-        'postano',
224 
-        'PostPost',
225 
-        'postrank',
226 
-        'proximic',
227 
-        'Pulsepoint XT3 web scraper',
228 
-        'PycURL',
229 
-        'Python-httplib2',
230 
-        'python-requests',
231 
-        'Python-urllib',
232 
-        'Qseero',
233 
-        'Qwantify',
234 
-        'Radian6',
235 
-        'RebelMouse',
236 
-        'REL Link Checker',
237 
-        'RetrevoPageAnalyzer',
238 
-        'Riddler',
239 
-        'Robosourcer',
240 
-        'Ruby',
241 
-        'SBIder',
242 
-        'ScoutJet',
243 
-        'ScoutURLMonitor',
244 
-        'Scrapy',
245 
-        'Scrubby',
246 
-        'SearchSight',
247 
-        'semanticdiscovery',
248 
-        'SEOstats',
249 
-        'Seznam screenshot-generator',
250 
-        'ShopWiki',
251 
-        'SimplePie',
252 
-        'SiteBar',
253 
-        'siteexplorer\.info',
254 
-        'Siteimprove\.com',
255 
-        'slider\.com',
256 
-        'slurp',
257 
-        'Snappy',
258 
-        'sogou',
259 
-        'speedy',
260 
-        'Springshare Link Checker',
261 
-        'Sqworm',
262 
-        'StackRambler',
263 
-        'Stratagems Kumo',
264 
-        'summify',
265 
-        'teoma',
266 
-        'theoldreader\.com',
267 
-        'TinEye',
268 
-        'Traackr.com',
269 
-        'truwoGPS',
270 
-        'Typhoeus',
271 
-        'tweetedtimes\.com',
272 
-        'Twikle',
273 
-        'UdmSearch',
274 
-        'UnwindFetchor',
275 
-        'updated',
276 
-        'URLChecker',
277 
-        'urlresolver',
278 
-        'Validator\.nu\\/LV',
279 
-        'Vagabondo',
280 
-        'Vivante Link Checker',
281 
-        'Vortex',
282 
-        'voyager\\/',
283 
-        'VYU2',
284 
-        'W3C-checklink',
285 
-        'W3C_CSS_Validator_JFouffa',
286 
-        'W3C_I18n-Checker',
287 
-        'W3C-mobileOK',
288 
-        'W3C_Unicorn',
289 
-        'W3C_Validator',
290 
-        'WebIndex',
291 
-        'Websquash\.com',
292 
-        'webcollage',
293 
-        'webmon ',
294 
-        'WeSEE:Search',
295 
-        'wf84',
296 
-        'wget',
297 
-        'WomlpeFactory',
298 
-        'wotbox',
299 
-        'Xenu Link Sleuth',
300 
-        'XML Sitemaps Generator',
301 
-        'Y!J-ASR',
302 
-        'yacy',
303 
-        'Yahoo Ad monitoring',
304 
-        'Yahoo Link Preview',
305 
-        'Yahoo! Slurp China',
306 
-        'Yahoo! Slurp',
307 
-        'YahooSeeker',
308 
-        'YahooSeeker-Testing',
309 
-        'YandexImages',
310 
-        'YandexMetrika',
311 
-        'YandexDirectDyn',
312 
-        'yandex',
313 
-        'yanga',
314 
-        'yeti',
315 
-        'yoogliFetchAgent',
316 
-        'Zao',
317 
-        'ZyBorg',
318 
-        '[a-z0-9\\-_]*((?<!cu)bot|crawler|archiver|transcoder|spider)',
319 
-    );
78 
+	/**
79 
+	 * Array of regular expressions to match against the user agent.
80 
+	 *
81 
+	 * @var array
82 
+	 */
83 
+	protected static $crawlers = array(
84 
+		'008\\/',
85 
+		'A6-Indexer',
86 
+		'Aboundex',
87 
+		'Accoona-AI-Agent',
88 
+		'acoon',
89 
+		'AddThis',
90 
+		'ADmantX',
91 
+		'AHC',
92 
+		'Airmail',
93 
+		'Anemone',
94 
+		'Arachmo',
95 
+		'archive-com',
96 
+		'B-l-i-t-z-B-O-T',
97 
+		'bibnum\.bnf',
98 
+		'biglotron',
99 
+		'binlar',
100 
+		'BingPreview',
101 
+		'boitho\.com-dc',
102 
+		'BrokenLinkCheck\.com',
103 
+		'BUbiNG',
104 
+		'Butterfly\\/',
105 
+		'BuzzSumo',
106 
+		'CapsuleChecker',
107 
+		'CC Metadata Scaper',
108 
+		'Cerberian Drtrs',
109 
+		'changedetection',
110 
+		'Charlotte',
111 
+		'clips\.ua\.ac\.be',
112 
+		'CloudFlare-AlwaysOnline',
113 
+		'coccoc',
114 
+		'Commons-HttpClient',
115 
+		'convera',
116 
+		'cosmos',
117 
+		'Covario-IDS',
118 
+		'curl',
119 
+		'CyberPatrol',
120 
+		'Dragonfly File Reader',
121 
+		'DataparkSearch',
122 
+		'dataprovider',
123 
+		'Digg',
124 
+		'DomainAppender',
125 
+		'drupact',
126 
+		'EARTHCOM',
127 
+		'ECCP',
128 
+		'ec2linkfinder',
129 
+		'ElectricMonk',
130 
+		'Embedly',
131 
+		'europarchive\.org',
132 
+		'EventMachine HttpClient',
133 
+		'ExactSearch',
134 
+		'ezooms',
135 
+		'eZ Publish Link Validator',
136 
+		'facebookexternalhit',
137 
+		'FeedBurner',
138 
+		'Feedfetcher-Google',
139 
+		'FeedValidator',
140 
+		'FindLinks',
141 
+		'findlink',
142 
+		'findthatfile',
143 
+		'Flamingo_SearchEngine',
144 
+		'fluffy',
145 
+		'getprismatic\.com',
146 
+		'g00g1e\.net',
147 
+		'GigablastOpenSource',
148 
+		'grub-client',
149 
+		'Genieo',
150 
+		'Go-http-client',
151 
+		'Google-HTTP-Java-Client',
152 
+		'Google favicon',
153 
+		'Google Keyword Suggestion',
154 
+		'GoogleProducer',
155 
+		'heritrix',
156 
+		'Holmes',
157 
+		'htdig',
158 
+		'httpunit',
159 
+		'httrack',
160 
+		'HubSpot Marketing Grader',
161 
+		'ichiro',
162 
+		'infegy',
163 
+		'igdeSpyder',
164 
+		'InAGist',
165 
+		'InfoWizards Reciprocal Link System PRO',
166 
+		'integromedb',
167 
+		'IODC',
168 
+		'IOI',
169 
+		'ips-agent',
170 
+		'iZSearch',
171 
+		'Jobrapido',
172 
+		'L\.webis',
173 
+		'Larbin',
174 
+		'libwww',
175 
+		'Link Valet',
176 
+		'linkdex',
177 
+		'LinkExaminer',
178 
+		'LinkWalker',
179 
+		'Lipperhey Link Explorer',
180 
+		'Lipperhey SEO Service',
181 
+		'LongURL API',
182 
+		'ltx71',
183 
+		'lwp-trivial',
184 
+		'MegaIndex\.ru',
185 
+		'mabontland',
186 
+		'MagpieRSS',
187 
+		'Mediapartners-Google',
188 
+		'MetaURI',
189 
+		'Mnogosearch',
190 
+		'mogimogi',
191 
+		'Morning Paper',
192 
+		'Mrcgiguy',
193 
+		'MVAClient',
194 
+		'Netcraft Web Server Survey',
195 
+		'netresearchserver',
196 
+		'Netvibes',
197 
+		'NewsGator',
198 
+		'newsme',
199 
+		'NG-Search',
200 
+		'^NING\\/',
201 
+		'nineconnections\.com',
202 
+		'nominet\.org\.uk',
203 
+		'Notifixious',
204 
+		'nutch',
205 
+		'NutchCVS',
206 
+		'Nymesis',
207 
+		'oegp',
208 
+		'Omea Reader',
209 
+		'online link validator',
210 
+		'Online Website Link Checker',
211 
+		'Orbiter',
212 
+		'ow\.ly',
213 
+		'Ploetz \+ Zeller',
214 
+		'PagePeeker',
215 
+		'page2rss',
216 
+		'panscient',
217 
+		'Peew',
218 
+		'phpcrawl',
219 
+		'Pinterest',
220 
+		'Pizilla',
221 
+		'Plukkie',
222 
+		'Pompos',
223 
+		'postano',
224 
+		'PostPost',
225 
+		'postrank',
226 
+		'proximic',
227 
+		'Pulsepoint XT3 web scraper',
228 
+		'PycURL',
229 
+		'Python-httplib2',
230 
+		'python-requests',
231 
+		'Python-urllib',
232 
+		'Qseero',
233 
+		'Qwantify',
234 
+		'Radian6',
235 
+		'RebelMouse',
236 
+		'REL Link Checker',
237 
+		'RetrevoPageAnalyzer',
238 
+		'Riddler',
239 
+		'Robosourcer',
240 
+		'Ruby',
241 
+		'SBIder',
242 
+		'ScoutJet',
243 
+		'ScoutURLMonitor',
244 
+		'Scrapy',
245 
+		'Scrubby',
246 
+		'SearchSight',
247 
+		'semanticdiscovery',
248 
+		'SEOstats',
249 
+		'Seznam screenshot-generator',
250 
+		'ShopWiki',
251 
+		'SimplePie',
252 
+		'SiteBar',
253 
+		'siteexplorer\.info',
254 
+		'Siteimprove\.com',
255 
+		'slider\.com',
256 
+		'slurp',
257 
+		'Snappy',
258 
+		'sogou',
259 
+		'speedy',
260 
+		'Springshare Link Checker',
261 
+		'Sqworm',
262 
+		'StackRambler',
263 
+		'Stratagems Kumo',
264 
+		'summify',
265 
+		'teoma',
266 
+		'theoldreader\.com',
267 
+		'TinEye',
268 
+		'Traackr.com',
269 
+		'truwoGPS',
270 
+		'Typhoeus',
271 
+		'tweetedtimes\.com',
272 
+		'Twikle',
273 
+		'UdmSearch',
274 
+		'UnwindFetchor',
275 
+		'updated',
276 
+		'URLChecker',
277 
+		'urlresolver',
278 
+		'Validator\.nu\\/LV',
279 
+		'Vagabondo',
280 
+		'Vivante Link Checker',
281 
+		'Vortex',
282 
+		'voyager\\/',
283 
+		'VYU2',
284 
+		'W3C-checklink',
285 
+		'W3C_CSS_Validator_JFouffa',
286 
+		'W3C_I18n-Checker',
287 
+		'W3C-mobileOK',
288 
+		'W3C_Unicorn',
289 
+		'W3C_Validator',
290 
+		'WebIndex',
291 
+		'Websquash\.com',
292 
+		'webcollage',
293 
+		'webmon ',
294 
+		'WeSEE:Search',
295 
+		'wf84',
296 
+		'wget',
297 
+		'WomlpeFactory',
298 
+		'wotbox',
299 
+		'Xenu Link Sleuth',
300 
+		'XML Sitemaps Generator',
301 
+		'Y!J-ASR',
302 
+		'yacy',
303 
+		'Yahoo Ad monitoring',
304 
+		'Yahoo Link Preview',
305 
+		'Yahoo! Slurp China',
306 
+		'Yahoo! Slurp',
307 
+		'YahooSeeker',
308 
+		'YahooSeeker-Testing',
309 
+		'YandexImages',
310 
+		'YandexMetrika',
311 
+		'YandexDirectDyn',
312 
+		'yandex',
313 
+		'yanga',
314 
+		'yeti',
315 
+		'yoogliFetchAgent',
316 
+		'Zao',
317 
+		'ZyBorg',
318 
+		'[a-z0-9\\-_]*((?<!cu)bot|crawler|archiver|transcoder|spider)',
319 
+	);
320 320
321 
-    /**
322 
-     * All possible HTTP headers that represent the
323 
-     * User-Agent string.
324 
-     *
325 
-     * @var array
326 
-     */
327 
-    protected static $uaHttpHeaders = array(
328 
-        // The default User-Agent string.
329 
-        'HTTP_USER_AGENT',
330 
-        // Header can occur on devices using Opera Mini.
331 
-        'HTTP_X_OPERAMINI_PHONE_UA',
332 
-        // Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/
333 
-        'HTTP_X_DEVICE_USER_AGENT',
334 
-        'HTTP_X_ORIGINAL_USER_AGENT',
335 
-        'HTTP_X_SKYFIRE_PHONE',
336 
-        'HTTP_X_BOLT_PHONE_UA',
337 
-        'HTTP_DEVICE_STOCK_UA',
338 
-        'HTTP_X_UCBROWSER_DEVICE_UA',
339 
-    );
321 
+	/**
322 
+	 * All possible HTTP headers that represent the
323 
+	 * User-Agent string.
324 
+	 *
325 
+	 * @var array
326 
+	 */
327 
+	protected static $uaHttpHeaders = array(
328 
+		// The default User-Agent string.
329 
+		'HTTP_USER_AGENT',
330 
+		// Header can occur on devices using Opera Mini.
331 
+		'HTTP_X_OPERAMINI_PHONE_UA',
332 
+		// Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/
333 
+		'HTTP_X_DEVICE_USER_AGENT',
334 
+		'HTTP_X_ORIGINAL_USER_AGENT',
335 
+		'HTTP_X_SKYFIRE_PHONE',
336 
+		'HTTP_X_BOLT_PHONE_UA',
337 
+		'HTTP_DEVICE_STOCK_UA',
338 
+		'HTTP_X_UCBROWSER_DEVICE_UA',
339 
+	);
340 340
341 
-    /**
342 
-     * Class constructor.
343 
-     */
344 
-    public function __construct(array $headers = null, $userAgent = null)
345 
-    {
346 
-        $this->setHttpHeaders($headers);
347 
-        $this->setUserAgent($userAgent);
348 
-    }
341 
+	/**
342 
+	 * Class constructor.
343 
+	 */
344 
+	public function __construct(array $headers = null, $userAgent = null)
345 
+	{
346 
+		$this->setHttpHeaders($headers);
347 
+		$this->setUserAgent($userAgent);
348 
+	}
349 349
350 
-    /**
351 
-     * Set HTTP headers.
352 
-     *
353 
-     * @param array $httpHeaders
354 
-     */
355 
-    public function setHttpHeaders($httpHeaders = null)
356 
-    {
357 
-        // use global _SERVER if $httpHeaders aren't defined
358 
-        if (!is_array($httpHeaders) || !count($httpHeaders)) {
359 
-            $httpHeaders = $_SERVER;
360 
-        }
361 
-        // clear existing headers
362 
-        $this->httpHeaders = array();
363 
-        // Only save HTTP headers. In PHP land, that means only _SERVER vars that
364 
-        // start with HTTP_.
365 
-        foreach ($httpHeaders as $key => $value) {
366 
-            if (substr($key, 0, 5) === 'HTTP_') {
367 
-                $this->httpHeaders[$key] = $value;
368 
-            }
369 
-        }
370 
-    }
350 
+	/**
351 
+	 * Set HTTP headers.
352 
+	 *
353 
+	 * @param array $httpHeaders
354 
+	 */
355 
+	public function setHttpHeaders($httpHeaders = null)
356 
+	{
357 
+		// use global _SERVER if $httpHeaders aren't defined
358 
+		if (!is_array($httpHeaders) || !count($httpHeaders)) {
359 
+			$httpHeaders = $_SERVER;
360 
+		}
361 
+		// clear existing headers
362 
+		$this->httpHeaders = array();
363 
+		// Only save HTTP headers. In PHP land, that means only _SERVER vars that
364 
+		// start with HTTP_.
365 
+		foreach ($httpHeaders as $key => $value) {
366 
+			if (substr($key, 0, 5) === 'HTTP_') {
367 
+				$this->httpHeaders[$key] = $value;
368 
+			}
369 
+		}
370 
+	}
371 371
372 
-    /**
373 
-     * Return user agent headers.
374 
-     *
375 
-     * @return array
376 
-     */
377 
-    public function getUaHttpHeaders()
378 
-    {
379 
-        return self::$uaHttpHeaders;
380 
-    }
372 
+	/**
373 
+	 * Return user agent headers.
374 
+	 *
375 
+	 * @return array
376 
+	 */
377 
+	public function getUaHttpHeaders()
378 
+	{
379 
+		return self::$uaHttpHeaders;
380 
+	}
381 381
382 
-    /**
383 
-     * Set the user agent.
384 
-     *
385 
-     * @param string $userAgent
386 
-     */
387 
-    public function setUserAgent($userAgent = null)
388 
-    {
389 
-        if (false === empty($userAgent)) {
390 
-            return $this->userAgent = $userAgent;
391 
-        } else {
392 
-            $this->userAgent = null;
393 
-            foreach ($this->getUaHttpHeaders() as $altHeader) {
394 
-                if (false === empty($this->httpHeaders[$altHeader])) { // @todo: should use getHttpHeader(), but it would be slow.
395 
-                    $this->userAgent .= $this->httpHeaders[$altHeader].' ';
396 
-                }
397 
-            }
382 
+	/**
383 
+	 * Set the user agent.
384 
+	 *
385 
+	 * @param string $userAgent
386 
+	 */
387 
+	public function setUserAgent($userAgent = null)
388 
+	{
389 
+		if (false === empty($userAgent)) {
390 
+			return $this->userAgent = $userAgent;
391 
+		} else {
392 
+			$this->userAgent = null;
393 
+			foreach ($this->getUaHttpHeaders() as $altHeader) {
394 
+				if (false === empty($this->httpHeaders[$altHeader])) { // @todo: should use getHttpHeader(), but it would be slow.
395 
+					$this->userAgent .= $this->httpHeaders[$altHeader].' ';
396 
+				}
397 
+			}
398 398
399 
-            return $this->userAgent = (!empty($this->userAgent) ? trim($this->userAgent) : null);
400 
-        }
401 
-    }
399 
+			return $this->userAgent = (!empty($this->userAgent) ? trim($this->userAgent) : null);
400 
+		}
401 
+	}
402 402
403 
-    /**
404 
-     * Build the user agent regex.
405 
-     *
406 
-     * @return string
407 
-     */
408 
-    public function getRegex()
409 
-    {
410 
-        return '('.implode('|', self::$crawlers).')';
411 
-    }
403 
+	/**
404 
+	 * Build the user agent regex.
405 
+	 *
406 
+	 * @return string
407 
+	 */
408 
+	public function getRegex()
409 
+	{
410 
+		return '('.implode('|', self::$crawlers).')';
411 
+	}
412 412
413 
-    /**
414 
-     * Build the replacement regex.
415 
-     *
416 
-     * @return string
417 
-     */
418 
-    public function getIgnored()
419 
-    {
420 
-        return '('.implode('|', self::$ignore).')';
421 
-    }
413 
+	/**
414 
+	 * Build the replacement regex.
415 
+	 *
416 
+	 * @return string
417 
+	 */
418 
+	public function getIgnored()
419 
+	{
420 
+		return '('.implode('|', self::$ignore).')';
421 
+	}
422 422
423 
-    /**
424 
-     * Check user agent string against the regex.
425 
-     *
426 
-     * @param string $userAgent
427 
-     *
428 
-     * @return bool
429 
-     */
430 
-    public function isCrawler($userAgent = null)
431 
-    {
432 
-        $agent = is_null($userAgent) ? $this->userAgent : $userAgent;
423 
+	/**
424 
+	 * Check user agent string against the regex.
425 
+	 *
426 
+	 * @param string $userAgent
427 
+	 *
428 
+	 * @return bool
429 
+	 */
430 
+	public function isCrawler($userAgent = null)
431 
+	{
432 
+		$agent = is_null($userAgent) ? $this->userAgent : $userAgent;
433 433
434 
-        $agent = preg_replace('/'.$this->getIgnored().'/i', '', $agent);
434 
+		$agent = preg_replace('/'.$this->getIgnored().'/i', '', $agent);
435 435
436 
-        if (trim($agent) === false) {
437 
-            return false;
438 
-        } else {
439 
-            $result = preg_match('/'.$this->getRegex().'/i', trim($agent), $matches);
440 
-        }
436 
+		if (trim($agent) === false) {
437 
+			return false;
438 
+		} else {
439 
+			$result = preg_match('/'.$this->getRegex().'/i', trim($agent), $matches);
440 
+		}
441 441
442 
-        if ($matches) {
443 
-            $this->matches = $matches;
444 
-        }
442 
+		if ($matches) {
443 
+			$this->matches = $matches;
444 
+		}
445 445
446 
-        return (bool) $result;
447 
-    }
446 
+		return (bool) $result;
447 
+	}
448 448
449 
-    /**
450 
-     * Return the matches.
451 
-     *
452 
-     * @return string
453 
-     */
454 
-    public function getMatches()
455 
-    {
456 
-        return $this->matches[0];
457 
-    }
449 
+	/**
450 
+	 * Return the matches.
451 
+	 *
452 
+	 * @return string
453 
+	 */
454 
+	public function getMatches()
455 
+	{
456 
+		return $this->matches[0];
457 
+	}
458 458 
 }
Please login to merge, or discard this patch.
tests/UATests.php 1 patch
Indentation   +27 added lines, -27 removed lines patch added patch discarded remove patch 
@@ -2,39 +2,39 @@
 
 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', FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
12 
+	public function testBots()
13 
+	{
14 
+		$lines = file(__DIR__.'/crawlers.txt', FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
15 15
16 
-        foreach ($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', FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
22 
+	public function testDevices()
23 
+	{
24 
+		$lines = file(__DIR__.'/devices.txt', FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
25 25
26 
-        foreach ($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
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)');
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 35
36 
-        $matches = $this->CrawlerDetect->getMatches();
36 
+		$matches = $this->CrawlerDetect->getMatches();
37 37
38 
-        $this->assertEquals($this->CrawlerDetect->getMatches(), 'Yahoo Ad monitoring', $matches);
39 
-    }
38 
+		$this->assertEquals($this->CrawlerDetect->getMatches(), 'Yahoo Ad monitoring', $matches);
39 
+	}
40 40 
 }
Please login to merge, or discard this patch.