JayBizzle /
Crawler-Detect
@@ -4,453 +4,453 @@ |
||
| 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 | - 'L\.webis', |
|
| 172 | - 'Larbin', |
|
| 173 | - 'libwww', |
|
| 174 | - 'Link Valet', |
|
| 175 | - 'linkdex', |
|
| 176 | - 'LinkExaminer', |
|
| 177 | - 'LinkWalker', |
|
| 178 | - 'Lipperhey Link Explorer', |
|
| 179 | - 'Lipperhey SEO Service', |
|
| 180 | - 'LongURL API', |
|
| 181 | - 'ltx71', |
|
| 182 | - 'lwp-trivial', |
|
| 183 | - 'MegaIndex\.ru', |
|
| 184 | - 'mabontland', |
|
| 185 | - 'MagpieRSS', |
|
| 186 | - 'Mediapartners-Google', |
|
| 187 | - 'MetaURI', |
|
| 188 | - 'Mnogosearch', |
|
| 189 | - 'mogimogi', |
|
| 190 | - 'Morning Paper', |
|
| 191 | - 'Mrcgiguy', |
|
| 192 | - 'MVAClient', |
|
| 193 | - 'Netcraft Web Server Survey', |
|
| 194 | - 'netresearchserver', |
|
| 195 | - 'Netvibes', |
|
| 196 | - 'NewsGator', |
|
| 197 | - 'newsme', |
|
| 198 | - 'NG-Search', |
|
| 199 | - '^NING\\/', |
|
| 200 | - 'nineconnections\.com', |
|
| 201 | - 'nominet\.org\.uk', |
|
| 202 | - 'Notifixious', |
|
| 203 | - 'nutch', |
|
| 204 | - 'NutchCVS', |
|
| 205 | - 'Nymesis', |
|
| 206 | - 'oegp', |
|
| 207 | - 'Omea Reader', |
|
| 208 | - 'online link validator', |
|
| 209 | - 'Online Website Link Checker', |
|
| 210 | - 'Orbiter', |
|
| 211 | - 'ow\.ly', |
|
| 212 | - 'Ploetz \+ Zeller', |
|
| 213 | - 'PagePeeker', |
|
| 214 | - 'page2rss', |
|
| 215 | - 'panscient', |
|
| 216 | - 'Peew', |
|
| 217 | - 'phpcrawl', |
|
| 218 | - 'Pinterest', |
|
| 219 | - 'Pizilla', |
|
| 220 | - 'Plukkie', |
|
| 221 | - 'Pompos', |
|
| 222 | - 'postano', |
|
| 223 | - 'PostPost', |
|
| 224 | - 'postrank', |
|
| 225 | - 'proximic', |
|
| 226 | - 'Pulsepoint XT3 web scraper', |
|
| 227 | - 'PycURL', |
|
| 228 | - 'Python-httplib2', |
|
| 229 | - 'python-requests', |
|
| 230 | - 'Python-urllib', |
|
| 231 | - 'Qseero', |
|
| 232 | - 'Qwantify', |
|
| 233 | - 'Radian6', |
|
| 234 | - 'RebelMouse', |
|
| 235 | - 'REL Link Checker', |
|
| 236 | - 'RetrevoPageAnalyzer', |
|
| 237 | - 'Riddler', |
|
| 238 | - 'Robosourcer', |
|
| 239 | - 'Ruby', |
|
| 240 | - 'SBIder', |
|
| 241 | - 'ScoutJet', |
|
| 242 | - 'ScoutURLMonitor', |
|
| 243 | - 'Scrapy', |
|
| 244 | - 'Scrubby', |
|
| 245 | - 'SearchSight', |
|
| 246 | - 'semanticdiscovery', |
|
| 247 | - 'SEOstats', |
|
| 248 | - 'Seznam screenshot-generator', |
|
| 249 | - 'ShopWiki', |
|
| 250 | - 'SimplePie', |
|
| 251 | - 'SiteBar', |
|
| 252 | - 'siteexplorer\.info', |
|
| 253 | - 'slider\.com', |
|
| 254 | - 'slurp', |
|
| 255 | - 'Snappy', |
|
| 256 | - 'sogou', |
|
| 257 | - 'speedy', |
|
| 258 | - 'Springshare Link Checker', |
|
| 259 | - 'Sqworm', |
|
| 260 | - 'StackRambler', |
|
| 261 | - 'Stratagems Kumo', |
|
| 262 | - 'summify', |
|
| 263 | - 'teoma', |
|
| 264 | - 'theoldreader\.com', |
|
| 265 | - 'TinEye', |
|
| 266 | - 'Traackr.com', |
|
| 267 | - 'truwoGPS', |
|
| 268 | - 'Typhoeus', |
|
| 269 | - 'tweetedtimes\.com', |
|
| 270 | - 'Twikle', |
|
| 271 | - 'UdmSearch', |
|
| 272 | - 'UnwindFetchor', |
|
| 273 | - 'updated', |
|
| 274 | - 'URLChecker', |
|
| 275 | - 'urlresolver', |
|
| 276 | - 'Validator\.nu\\/LV', |
|
| 277 | - 'Vagabondo', |
|
| 278 | - 'Vivante Link Checker', |
|
| 279 | - 'Vortex', |
|
| 280 | - 'voyager\\/', |
|
| 281 | - 'VYU2', |
|
| 282 | - 'W3C-checklink', |
|
| 283 | - 'W3C_CSS_Validator_JFouffa', |
|
| 284 | - 'W3C_I18n-Checker', |
|
| 285 | - 'W3C-mobileOK', |
|
| 286 | - 'W3C_Unicorn', |
|
| 287 | - 'W3C_Validator', |
|
| 288 | - 'WebIndex', |
|
| 289 | - 'Websquash\.com', |
|
| 290 | - 'webcollage', |
|
| 291 | - 'webmon ', |
|
| 292 | - 'WeSEE:Search', |
|
| 293 | - 'wf84', |
|
| 294 | - 'wget', |
|
| 295 | - 'WomlpeFactory', |
|
| 296 | - 'wotbox', |
|
| 297 | - 'Xenu Link Sleuth', |
|
| 298 | - 'XML Sitemaps Generator', |
|
| 299 | - 'Y!J-ASR', |
|
| 300 | - 'yacy', |
|
| 301 | - 'Yahoo Ad monitoring', |
|
| 302 | - 'Yahoo Link Preview', |
|
| 303 | - 'Yahoo! Slurp China', |
|
| 304 | - 'Yahoo! Slurp', |
|
| 305 | - 'YahooSeeker', |
|
| 306 | - 'YahooSeeker-Testing', |
|
| 307 | - 'YandexImages', |
|
| 308 | - 'YandexMetrika', |
|
| 309 | - 'YandexDirectDyn', |
|
| 310 | - 'yandex', |
|
| 311 | - 'yanga', |
|
| 312 | - 'yeti', |
|
| 313 | - 'yoogliFetchAgent', |
|
| 314 | - 'Zao', |
|
| 315 | - 'ZyBorg', |
|
| 316 | - '[a-z0-9\\-_]*((?<!cu)bot|crawler|archiver|transcoder|spider)', |
|
| 317 | - ); |
|
| 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 | + 'L\.webis', |
|
| 172 | + 'Larbin', |
|
| 173 | + 'libwww', |
|
| 174 | + 'Link Valet', |
|
| 175 | + 'linkdex', |
|
| 176 | + 'LinkExaminer', |
|
| 177 | + 'LinkWalker', |
|
| 178 | + 'Lipperhey Link Explorer', |
|
| 179 | + 'Lipperhey SEO Service', |
|
| 180 | + 'LongURL API', |
|
| 181 | + 'ltx71', |
|
| 182 | + 'lwp-trivial', |
|
| 183 | + 'MegaIndex\.ru', |
|
| 184 | + 'mabontland', |
|
| 185 | + 'MagpieRSS', |
|
| 186 | + 'Mediapartners-Google', |
|
| 187 | + 'MetaURI', |
|
| 188 | + 'Mnogosearch', |
|
| 189 | + 'mogimogi', |
|
| 190 | + 'Morning Paper', |
|
| 191 | + 'Mrcgiguy', |
|
| 192 | + 'MVAClient', |
|
| 193 | + 'Netcraft Web Server Survey', |
|
| 194 | + 'netresearchserver', |
|
| 195 | + 'Netvibes', |
|
| 196 | + 'NewsGator', |
|
| 197 | + 'newsme', |
|
| 198 | + 'NG-Search', |
|
| 199 | + '^NING\\/', |
|
| 200 | + 'nineconnections\.com', |
|
| 201 | + 'nominet\.org\.uk', |
|
| 202 | + 'Notifixious', |
|
| 203 | + 'nutch', |
|
| 204 | + 'NutchCVS', |
|
| 205 | + 'Nymesis', |
|
| 206 | + 'oegp', |
|
| 207 | + 'Omea Reader', |
|
| 208 | + 'online link validator', |
|
| 209 | + 'Online Website Link Checker', |
|
| 210 | + 'Orbiter', |
|
| 211 | + 'ow\.ly', |
|
| 212 | + 'Ploetz \+ Zeller', |
|
| 213 | + 'PagePeeker', |
|
| 214 | + 'page2rss', |
|
| 215 | + 'panscient', |
|
| 216 | + 'Peew', |
|
| 217 | + 'phpcrawl', |
|
| 218 | + 'Pinterest', |
|
| 219 | + 'Pizilla', |
|
| 220 | + 'Plukkie', |
|
| 221 | + 'Pompos', |
|
| 222 | + 'postano', |
|
| 223 | + 'PostPost', |
|
| 224 | + 'postrank', |
|
| 225 | + 'proximic', |
|
| 226 | + 'Pulsepoint XT3 web scraper', |
|
| 227 | + 'PycURL', |
|
| 228 | + 'Python-httplib2', |
|
| 229 | + 'python-requests', |
|
| 230 | + 'Python-urllib', |
|
| 231 | + 'Qseero', |
|
| 232 | + 'Qwantify', |
|
| 233 | + 'Radian6', |
|
| 234 | + 'RebelMouse', |
|
| 235 | + 'REL Link Checker', |
|
| 236 | + 'RetrevoPageAnalyzer', |
|
| 237 | + 'Riddler', |
|
| 238 | + 'Robosourcer', |
|
| 239 | + 'Ruby', |
|
| 240 | + 'SBIder', |
|
| 241 | + 'ScoutJet', |
|
| 242 | + 'ScoutURLMonitor', |
|
| 243 | + 'Scrapy', |
|
| 244 | + 'Scrubby', |
|
| 245 | + 'SearchSight', |
|
| 246 | + 'semanticdiscovery', |
|
| 247 | + 'SEOstats', |
|
| 248 | + 'Seznam screenshot-generator', |
|
| 249 | + 'ShopWiki', |
|
| 250 | + 'SimplePie', |
|
| 251 | + 'SiteBar', |
|
| 252 | + 'siteexplorer\.info', |
|
| 253 | + 'slider\.com', |
|
| 254 | + 'slurp', |
|
| 255 | + 'Snappy', |
|
| 256 | + 'sogou', |
|
| 257 | + 'speedy', |
|
| 258 | + 'Springshare Link Checker', |
|
| 259 | + 'Sqworm', |
|
| 260 | + 'StackRambler', |
|
| 261 | + 'Stratagems Kumo', |
|
| 262 | + 'summify', |
|
| 263 | + 'teoma', |
|
| 264 | + 'theoldreader\.com', |
|
| 265 | + 'TinEye', |
|
| 266 | + 'Traackr.com', |
|
| 267 | + 'truwoGPS', |
|
| 268 | + 'Typhoeus', |
|
| 269 | + 'tweetedtimes\.com', |
|
| 270 | + 'Twikle', |
|
| 271 | + 'UdmSearch', |
|
| 272 | + 'UnwindFetchor', |
|
| 273 | + 'updated', |
|
| 274 | + 'URLChecker', |
|
| 275 | + 'urlresolver', |
|
| 276 | + 'Validator\.nu\\/LV', |
|
| 277 | + 'Vagabondo', |
|
| 278 | + 'Vivante Link Checker', |
|
| 279 | + 'Vortex', |
|
| 280 | + 'voyager\\/', |
|
| 281 | + 'VYU2', |
|
| 282 | + 'W3C-checklink', |
|
| 283 | + 'W3C_CSS_Validator_JFouffa', |
|
| 284 | + 'W3C_I18n-Checker', |
|
| 285 | + 'W3C-mobileOK', |
|
| 286 | + 'W3C_Unicorn', |
|
| 287 | + 'W3C_Validator', |
|
| 288 | + 'WebIndex', |
|
| 289 | + 'Websquash\.com', |
|
| 290 | + 'webcollage', |
|
| 291 | + 'webmon ', |
|
| 292 | + 'WeSEE:Search', |
|
| 293 | + 'wf84', |
|
| 294 | + 'wget', |
|
| 295 | + 'WomlpeFactory', |
|
| 296 | + 'wotbox', |
|
| 297 | + 'Xenu Link Sleuth', |
|
| 298 | + 'XML Sitemaps Generator', |
|
| 299 | + 'Y!J-ASR', |
|
| 300 | + 'yacy', |
|
| 301 | + 'Yahoo Ad monitoring', |
|
| 302 | + 'Yahoo Link Preview', |
|
| 303 | + 'Yahoo! Slurp China', |
|
| 304 | + 'Yahoo! Slurp', |
|
| 305 | + 'YahooSeeker', |
|
| 306 | + 'YahooSeeker-Testing', |
|
| 307 | + 'YandexImages', |
|
| 308 | + 'YandexMetrika', |
|
| 309 | + 'YandexDirectDyn', |
|
| 310 | + 'yandex', |
|
| 311 | + 'yanga', |
|
| 312 | + 'yeti', |
|
| 313 | + 'yoogliFetchAgent', |
|
| 314 | + 'Zao', |
|
| 315 | + 'ZyBorg', |
|
| 316 | + '[a-z0-9\\-_]*((?<!cu)bot|crawler|archiver|transcoder|spider)', |
|
| 317 | + ); |
|
| 318 | 318 | |
| 319 | - /** |
|
| 320 | - * All possible HTTP headers that represent the |
|
| 321 | - * User-Agent string. |
|
| 322 | - * |
|
| 323 | - * @var array |
|
| 324 | - */ |
|
| 325 | - protected static $uaHttpHeaders = array( |
|
| 326 | - // The default User-Agent string. |
|
| 327 | - 'HTTP_USER_AGENT', |
|
| 328 | - // Header can occur on devices using Opera Mini. |
|
| 329 | - 'HTTP_X_OPERAMINI_PHONE_UA', |
|
| 330 | - // Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/ |
|
| 331 | - 'HTTP_X_DEVICE_USER_AGENT', |
|
| 332 | - 'HTTP_X_ORIGINAL_USER_AGENT', |
|
| 333 | - 'HTTP_X_SKYFIRE_PHONE', |
|
| 334 | - 'HTTP_X_BOLT_PHONE_UA', |
|
| 335 | - 'HTTP_DEVICE_STOCK_UA', |
|
| 336 | - 'HTTP_X_UCBROWSER_DEVICE_UA', |
|
| 337 | - ); |
|
| 319 | + /** |
|
| 320 | + * All possible HTTP headers that represent the |
|
| 321 | + * User-Agent string. |
|
| 322 | + * |
|
| 323 | + * @var array |
|
| 324 | + */ |
|
| 325 | + protected static $uaHttpHeaders = array( |
|
| 326 | + // The default User-Agent string. |
|
| 327 | + 'HTTP_USER_AGENT', |
|
| 328 | + // Header can occur on devices using Opera Mini. |
|
| 329 | + 'HTTP_X_OPERAMINI_PHONE_UA', |
|
| 330 | + // Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/ |
|
| 331 | + 'HTTP_X_DEVICE_USER_AGENT', |
|
| 332 | + 'HTTP_X_ORIGINAL_USER_AGENT', |
|
| 333 | + 'HTTP_X_SKYFIRE_PHONE', |
|
| 334 | + 'HTTP_X_BOLT_PHONE_UA', |
|
| 335 | + 'HTTP_DEVICE_STOCK_UA', |
|
| 336 | + 'HTTP_X_UCBROWSER_DEVICE_UA', |
|
| 337 | + ); |
|
| 338 | 338 | |
| 339 | - /** |
|
| 340 | - * Class constructor. |
|
| 341 | - */ |
|
| 342 | - public function __construct(array $headers = null, $userAgent = null) |
|
| 343 | - { |
|
| 344 | - $this->setHttpHeaders($headers); |
|
| 345 | - $this->setUserAgent($userAgent); |
|
| 346 | - } |
|
| 339 | + /** |
|
| 340 | + * Class constructor. |
|
| 341 | + */ |
|
| 342 | + public function __construct(array $headers = null, $userAgent = null) |
|
| 343 | + { |
|
| 344 | + $this->setHttpHeaders($headers); |
|
| 345 | + $this->setUserAgent($userAgent); |
|
| 346 | + } |
|
| 347 | 347 | |
| 348 | - /** |
|
| 349 | - * Set HTTP headers. |
|
| 350 | - * |
|
| 351 | - * @param array $httpHeaders |
|
| 352 | - */ |
|
| 353 | - public function setHttpHeaders($httpHeaders = null) |
|
| 354 | - { |
|
| 355 | - // use global _SERVER if $httpHeaders aren't defined |
|
| 356 | - if (!is_array($httpHeaders) || !count($httpHeaders)) { |
|
| 357 | - $httpHeaders = $_SERVER; |
|
| 358 | - } |
|
| 359 | - // clear existing headers |
|
| 360 | - $this->httpHeaders = array(); |
|
| 361 | - // Only save HTTP headers. In PHP land, that means only _SERVER vars that |
|
| 362 | - // start with HTTP_. |
|
| 363 | - foreach ($httpHeaders as $key => $value) { |
|
| 364 | - if (substr($key, 0, 5) === 'HTTP_') { |
|
| 365 | - $this->httpHeaders[$key] = $value; |
|
| 366 | - } |
|
| 367 | - } |
|
| 368 | - } |
|
| 348 | + /** |
|
| 349 | + * Set HTTP headers. |
|
| 350 | + * |
|
| 351 | + * @param array $httpHeaders |
|
| 352 | + */ |
|
| 353 | + public function setHttpHeaders($httpHeaders = null) |
|
| 354 | + { |
|
| 355 | + // use global _SERVER if $httpHeaders aren't defined |
|
| 356 | + if (!is_array($httpHeaders) || !count($httpHeaders)) { |
|
| 357 | + $httpHeaders = $_SERVER; |
|
| 358 | + } |
|
| 359 | + // clear existing headers |
|
| 360 | + $this->httpHeaders = array(); |
|
| 361 | + // Only save HTTP headers. In PHP land, that means only _SERVER vars that |
|
| 362 | + // start with HTTP_. |
|
| 363 | + foreach ($httpHeaders as $key => $value) { |
|
| 364 | + if (substr($key, 0, 5) === 'HTTP_') { |
|
| 365 | + $this->httpHeaders[$key] = $value; |
|
| 366 | + } |
|
| 367 | + } |
|
| 368 | + } |
|
| 369 | 369 | |
| 370 | - /** |
|
| 371 | - * Return user agent headers. |
|
| 372 | - * |
|
| 373 | - * @return array |
|
| 374 | - */ |
|
| 375 | - public function getUaHttpHeaders() |
|
| 376 | - { |
|
| 377 | - return self::$uaHttpHeaders; |
|
| 378 | - } |
|
| 370 | + /** |
|
| 371 | + * Return user agent headers. |
|
| 372 | + * |
|
| 373 | + * @return array |
|
| 374 | + */ |
|
| 375 | + public function getUaHttpHeaders() |
|
| 376 | + { |
|
| 377 | + return self::$uaHttpHeaders; |
|
| 378 | + } |
|
| 379 | 379 | |
| 380 | - /** |
|
| 381 | - * Set the user agent. |
|
| 382 | - * |
|
| 383 | - * @param string $userAgent |
|
| 384 | - */ |
|
| 385 | - public function setUserAgent($userAgent = null) |
|
| 386 | - { |
|
| 387 | - if (false === empty($userAgent)) { |
|
| 388 | - return $this->userAgent = $userAgent; |
|
| 389 | - } else { |
|
| 390 | - $this->userAgent = null; |
|
| 391 | - foreach ($this->getUaHttpHeaders() as $altHeader) { |
|
| 392 | - if (false === empty($this->httpHeaders[$altHeader])) { // @todo: should use getHttpHeader(), but it would be slow. |
|
| 393 | - $this->userAgent .= $this->httpHeaders[$altHeader].' '; |
|
| 394 | - } |
|
| 395 | - } |
|
| 380 | + /** |
|
| 381 | + * Set the user agent. |
|
| 382 | + * |
|
| 383 | + * @param string $userAgent |
|
| 384 | + */ |
|
| 385 | + public function setUserAgent($userAgent = null) |
|
| 386 | + { |
|
| 387 | + if (false === empty($userAgent)) { |
|
| 388 | + return $this->userAgent = $userAgent; |
|
| 389 | + } else { |
|
| 390 | + $this->userAgent = null; |
|
| 391 | + foreach ($this->getUaHttpHeaders() as $altHeader) { |
|
| 392 | + if (false === empty($this->httpHeaders[$altHeader])) { // @todo: should use getHttpHeader(), but it would be slow. |
|
| 393 | + $this->userAgent .= $this->httpHeaders[$altHeader].' '; |
|
| 394 | + } |
|
| 395 | + } |
|
| 396 | 396 | |
| 397 | - return $this->userAgent = (!empty($this->userAgent) ? trim($this->userAgent) : null); |
|
| 398 | - } |
|
| 399 | - } |
|
| 397 | + return $this->userAgent = (!empty($this->userAgent) ? trim($this->userAgent) : null); |
|
| 398 | + } |
|
| 399 | + } |
|
| 400 | 400 | |
| 401 | - /** |
|
| 402 | - * Build the user agent regex. |
|
| 403 | - * |
|
| 404 | - * @return string |
|
| 405 | - */ |
|
| 406 | - public function getRegex() |
|
| 407 | - { |
|
| 408 | - return '('.implode('|', self::$crawlers).')'; |
|
| 409 | - } |
|
| 401 | + /** |
|
| 402 | + * Build the user agent regex. |
|
| 403 | + * |
|
| 404 | + * @return string |
|
| 405 | + */ |
|
| 406 | + public function getRegex() |
|
| 407 | + { |
|
| 408 | + return '('.implode('|', self::$crawlers).')'; |
|
| 409 | + } |
|
| 410 | 410 | |
| 411 | - /** |
|
| 412 | - * Build the replacement regex. |
|
| 413 | - * |
|
| 414 | - * @return string |
|
| 415 | - */ |
|
| 416 | - public function getIgnored() |
|
| 417 | - { |
|
| 418 | - return '('.implode('|', self::$ignore).')'; |
|
| 419 | - } |
|
| 411 | + /** |
|
| 412 | + * Build the replacement regex. |
|
| 413 | + * |
|
| 414 | + * @return string |
|
| 415 | + */ |
|
| 416 | + public function getIgnored() |
|
| 417 | + { |
|
| 418 | + return '('.implode('|', self::$ignore).')'; |
|
| 419 | + } |
|
| 420 | 420 | |
| 421 | - /** |
|
| 422 | - * Check user agent string against the regex. |
|
| 423 | - * |
|
| 424 | - * @param string $userAgent |
|
| 425 | - * |
|
| 426 | - * @return bool |
|
| 427 | - */ |
|
| 428 | - public function isCrawler($userAgent = null) |
|
| 429 | - { |
|
| 430 | - $agent = is_null($userAgent) ? $this->userAgent : $userAgent; |
|
| 421 | + /** |
|
| 422 | + * Check user agent string against the regex. |
|
| 423 | + * |
|
| 424 | + * @param string $userAgent |
|
| 425 | + * |
|
| 426 | + * @return bool |
|
| 427 | + */ |
|
| 428 | + public function isCrawler($userAgent = null) |
|
| 429 | + { |
|
| 430 | + $agent = is_null($userAgent) ? $this->userAgent : $userAgent; |
|
| 431 | 431 | |
| 432 | - $agent = preg_replace('/'.$this->getIgnored().'/i', '', $agent); |
|
| 432 | + $agent = preg_replace('/'.$this->getIgnored().'/i', '', $agent); |
|
| 433 | 433 | |
| 434 | - if (trim($agent) === false) { |
|
| 435 | - return false; |
|
| 436 | - } else { |
|
| 437 | - $result = preg_match('/'.$this->getRegex().'/i', trim($agent), $matches); |
|
| 438 | - } |
|
| 434 | + if (trim($agent) === false) { |
|
| 435 | + return false; |
|
| 436 | + } else { |
|
| 437 | + $result = preg_match('/'.$this->getRegex().'/i', trim($agent), $matches); |
|
| 438 | + } |
|
| 439 | 439 | |
| 440 | - if ($matches) { |
|
| 441 | - $this->matches = $matches; |
|
| 442 | - } |
|
| 440 | + if ($matches) { |
|
| 441 | + $this->matches = $matches; |
|
| 442 | + } |
|
| 443 | 443 | |
| 444 | - return (bool) $result; |
|
| 445 | - } |
|
| 444 | + return (bool) $result; |
|
| 445 | + } |
|
| 446 | 446 | |
| 447 | - /** |
|
| 448 | - * Return the matches. |
|
| 449 | - * |
|
| 450 | - * @return string |
|
| 451 | - */ |
|
| 452 | - public function getMatches() |
|
| 453 | - { |
|
| 454 | - return $this->matches[0]; |
|
| 455 | - } |
|
| 447 | + /** |
|
| 448 | + * Return the matches. |
|
| 449 | + * |
|
| 450 | + * @return string |
|
| 451 | + */ |
|
| 452 | + public function getMatches() |
|
| 453 | + { |
|
| 454 | + return $this->matches[0]; |
|
| 455 | + } |
|
| 456 | 456 | } |
