| @@ -4,368 +4,368 @@ | ||
| 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 | - /** | |
| 14 | - * List of strings to remove from the user agent before running the crawler regex | |
| 15 | - * Over a large list of user agents, this gives us about a 55% speed increase! | |
| 16 | - * | |
| 17 | - * @var array | |
| 18 | - */ | |
| 19 | - protected static $ignore = array( | |
| 20 | - 'Safari.[\d\.]*', | |
| 21 | - 'Firefox.[\d\.]*', | |
| 22 | - 'Chrome.[\d\.]*', | |
| 23 | - 'Chromium.[\d\.]*', | |
| 24 | - 'MSIE.[\d\.]', | |
| 25 | - 'Opera\/[\d\.]*', | |
| 26 | - 'Mozilla.[\d\.]*', | |
| 27 | - 'AppleWebKit.[\d\.]*', | |
| 28 | - 'Trident.[\d\.]*', | |
| 29 | - 'Windows NT.[\d\.]*', | |
| 30 | - 'Android.[\d\.]*', | |
| 31 | - 'Macintosh.', | |
| 32 | - 'Ubuntu', | |
| 33 | - 'Linux', | |
| 34 | - 'Intel', | |
| 35 | - 'Mac OS X', | |
| 36 | - 'Gecko.[\d\.]*', | |
| 37 | - 'KHTML', | |
| 38 | - 'CriOS.[\d\.]*', | |
| 39 | - 'CPU iPhone OS ([0-9_])* like Mac OS X', | |
| 40 | - 'CPU OS ([0-9_])* like Mac OS X', | |
| 41 | - 'iPod', | |
| 42 | - 'like Gecko', | |
| 43 | - 'compatible', | |
| 44 | - 'x86_..', | |
| 45 | - 'i686', | |
| 46 | - 'x64', | |
| 47 | - 'X11', | |
| 48 | - 'rv:[\d\.]*', | |
| 49 | - 'Version.[\d\.]*', | |
| 50 | - 'WOW64', | |
| 51 | - 'Win64', | |
| 52 | - 'Dalvik.[\d\.]*', | |
| 53 | - '\.NET CLR [\d\.]*', | |
| 54 | - 'Presto.[\d\.]*', | |
| 55 | - 'Media Center PC', | |
| 56 | - ); | |
| 13 | + /** | |
| 14 | + * List of strings to remove from the user agent before running the crawler regex | |
| 15 | + * Over a large list of user agents, this gives us about a 55% speed increase! | |
| 16 | + * | |
| 17 | + * @var array | |
| 18 | + */ | |
| 19 | + protected static $ignore = array( | |
| 20 | + 'Safari.[\d\.]*', | |
| 21 | + 'Firefox.[\d\.]*', | |
| 22 | + 'Chrome.[\d\.]*', | |
| 23 | + 'Chromium.[\d\.]*', | |
| 24 | + 'MSIE.[\d\.]', | |
| 25 | + 'Opera\/[\d\.]*', | |
| 26 | + 'Mozilla.[\d\.]*', | |
| 27 | + 'AppleWebKit.[\d\.]*', | |
| 28 | + 'Trident.[\d\.]*', | |
| 29 | + 'Windows NT.[\d\.]*', | |
| 30 | + 'Android.[\d\.]*', | |
| 31 | + 'Macintosh.', | |
| 32 | + 'Ubuntu', | |
| 33 | + 'Linux', | |
| 34 | + 'Intel', | |
| 35 | + 'Mac OS X', | |
| 36 | + 'Gecko.[\d\.]*', | |
| 37 | + 'KHTML', | |
| 38 | + 'CriOS.[\d\.]*', | |
| 39 | + 'CPU iPhone OS ([0-9_])* like Mac OS X', | |
| 40 | + 'CPU OS ([0-9_])* like Mac OS X', | |
| 41 | + 'iPod', | |
| 42 | + 'like Gecko', | |
| 43 | + 'compatible', | |
| 44 | + 'x86_..', | |
| 45 | + 'i686', | |
| 46 | + 'x64', | |
| 47 | + 'X11', | |
| 48 | + 'rv:[\d\.]*', | |
| 49 | + 'Version.[\d\.]*', | |
| 50 | + 'WOW64', | |
| 51 | + 'Win64', | |
| 52 | + 'Dalvik.[\d\.]*', | |
| 53 | + '\.NET CLR [\d\.]*', | |
| 54 | + 'Presto.[\d\.]*', | |
| 55 | + 'Media Center PC', | |
| 56 | + ); | |
| 57 | 57 | |
| 58 | - protected static $crawlers = array( | |
| 59 | - '007ac9 Crawler', | |
| 60 | - '008\\/', | |
| 61 | - 'A6-Indexer', | |
| 62 | - 'Aboundex', | |
| 63 | - 'Accoona-AI-Agent', | |
| 64 | - 'acoon', | |
| 65 | - 'AddThis', | |
| 66 | - 'ADmantX', | |
| 67 | - 'AHC', | |
| 68 | - 'Airmail', | |
| 69 | - 'Anemone', | |
| 70 | - 'Arachmo', | |
| 71 | - 'archive-com', | |
| 72 | - 'B-l-i-t-z-B-O-T', | |
| 73 | - 'bibnum\.bnf', | |
| 74 | - 'biglotron', | |
| 75 | - 'binlar', | |
| 76 | - 'boitho\.com-dc', | |
| 77 | - 'BUbiNG', | |
| 78 | - 'Butterfly\\/', | |
| 79 | - 'BuzzSumo', | |
| 80 | - 'CC Metadata Scaper', | |
| 81 | - 'Cerberian Drtrs', | |
| 82 | - 'changedetection', | |
| 83 | - 'Charlotte', | |
| 84 | - 'clips\.ua\.ac\.be', | |
| 85 | - 'CloudFlare-AlwaysOnline', | |
| 86 | - 'coccoc', | |
| 87 | - 'Commons-HttpClient', | |
| 88 | - 'convera', | |
| 89 | - 'cosmos', | |
| 90 | - 'Covario-IDS', | |
| 91 | - 'crawler4j', | |
| 92 | - 'curl', | |
| 93 | - 'CyberPatrol', | |
| 94 | - 'DataparkSearch', | |
| 95 | - 'dataprovider', | |
| 96 | - 'Digg', | |
| 97 | - 'DomainAppender', | |
| 98 | - 'drupact', | |
| 99 | - 'EARTHCOM', | |
| 100 | - 'ec2linkfinder', | |
| 101 | - 'ElectricMonk', | |
| 102 | - 'Embedly', | |
| 103 | - 'europarchive\.org', | |
| 104 | - 'EventMachine HttpClient', | |
| 105 | - 'ezooms', | |
| 106 | - 'eZ Publish Link Validator', | |
| 107 | - 'facebookexternalhit', | |
| 108 | - 'Feedfetcher-Google', | |
| 109 | - 'FeedValidator', | |
| 110 | - 'FindLinks', | |
| 111 | - 'findlink', | |
| 112 | - 'findthatfile', | |
| 113 | - 'Flamingo_SearchEngine', | |
| 114 | - 'fluffy', | |
| 115 | - 'getprismatic\.com', | |
| 116 | - 'g00g1e\.net', | |
| 117 | - 'GigablastOpenSource', | |
| 118 | - 'grub-client', | |
| 119 | - 'Genieo', | |
| 120 | - 'Go-http-client', | |
| 121 | - 'Googlebot-Image', | |
| 122 | - 'Googlebot-Mobile', | |
| 123 | - 'Google-HTTP-Java-Client', | |
| 124 | - 'Google favicon', | |
| 125 | - 'heritrix', | |
| 126 | - 'Holmes', | |
| 127 | - 'htdig', | |
| 128 | - 'httpunit', | |
| 129 | - 'httrack', | |
| 130 | - 'ia_archiver', | |
| 131 | - 'ichiro', | |
| 132 | - 'igdeSpyder', | |
| 133 | - 'InAGist', | |
| 134 | - 'InfoWizards Reciprocal Link System PRO', | |
| 135 | - 'integromedb', | |
| 136 | - 'IODC', | |
| 137 | - 'IOI', | |
| 138 | - 'ips-agent', | |
| 139 | - 'iZSearch', | |
| 140 | - 'L\.webis', | |
| 141 | - 'Larbin', | |
| 142 | - 'libwww', | |
| 143 | - 'Link Valet', | |
| 144 | - 'linkdex', | |
| 145 | - 'LinkExaminer', | |
| 146 | - 'LinkWalker', | |
| 147 | - 'Lipperhey Link Explorer', | |
| 148 | - 'Lipperhey SEO Service', | |
| 149 | - 'LongURL API', | |
| 150 | - 'ltx71', | |
| 151 | - 'lwp-trivial', | |
| 152 | - 'MegaIndex\.ru', | |
| 153 | - 'mabontland', | |
| 154 | - 'MagpieRSS', | |
| 155 | - 'Mediapartners-Google', | |
| 156 | - 'MetaURI', | |
| 157 | - 'Mnogosearch', | |
| 158 | - 'mogimogi', | |
| 159 | - 'Morning Paper', | |
| 160 | - 'Mrcgiguy', | |
| 161 | - 'MVAClient', | |
| 162 | - 'netresearchserver', | |
| 163 | - 'NewsGator', | |
| 164 | - 'newsme', | |
| 165 | - 'NG-Search', | |
| 166 | - '^NING\\/', | |
| 167 | - 'Notifixious', | |
| 168 | - 'nutch', | |
| 169 | - 'NutchCVS', | |
| 170 | - 'Nymesis', | |
| 171 | - 'oegp', | |
| 172 | - 'online link validator', | |
| 173 | - 'Online Website Link Checker', | |
| 174 | - 'Orbiter', | |
| 175 | - 'ow\.ly', | |
| 176 | - 'Ploetz \+ Zeller', | |
| 177 | - 'page2rss', | |
| 178 | - 'panscient', | |
| 179 | - 'Peew', | |
| 180 | - 'phpcrawl', | |
| 181 | - 'Pizilla', | |
| 182 | - 'Plukkie', | |
| 183 | - 'Pompos', | |
| 184 | - 'postano', | |
| 185 | - 'PostPost', | |
| 186 | - 'postrank', | |
| 187 | - 'proximic', | |
| 188 | - 'PycURL', | |
| 189 | - 'Python-httplib2', | |
| 190 | - 'python-requests', | |
| 191 | - 'Python-urllib', | |
| 192 | - 'Qseero', | |
| 193 | - 'Qwantify', | |
| 194 | - 'Radian6', | |
| 195 | - 'RebelMouse', | |
| 196 | - 'REL Link Checker', | |
| 197 | - 'RetrevoPageAnalyzer', | |
| 198 | - 'Riddler', | |
| 199 | - 'Robosourcer', | |
| 200 | - 'Ruby', | |
| 201 | - 'SandCrawler', | |
| 202 | - 'SBIder', | |
| 203 | - 'ScoutJet', | |
| 204 | - 'ScoutURLMonitor', | |
| 205 | - 'Scrapy', | |
| 206 | - 'Scrubby', | |
| 207 | - 'SearchSight', | |
| 208 | - 'semanticdiscovery', | |
| 209 | - 'SEOstats', | |
| 210 | - 'Seznam screenshot-generator', | |
| 211 | - 'ShopWiki', | |
| 212 | - 'SiteBar', | |
| 213 | - 'siteexplorer\.info', | |
| 214 | - 'slider\.com', | |
| 215 | - 'slurp', | |
| 216 | - 'Snappy', | |
| 217 | - 'sogou', | |
| 218 | - 'speedy', | |
| 219 | - 'Sqworm', | |
| 220 | - 'StackRambler', | |
| 221 | - 'Stratagems Kumo', | |
| 222 | - 'summify', | |
| 223 | - 'teoma', | |
| 224 | - 'theoldreader\.com', | |
| 225 | - 'TinEye', | |
| 226 | - 'Traackr.com', | |
| 227 | - 'truwoGPS', | |
| 228 | - 'tweetedtimes\.com', | |
| 229 | - 'Twikle', | |
| 230 | - 'UnwindFetchor', | |
| 231 | - 'updated', | |
| 232 | - 'urlresolver', | |
| 233 | - 'Validator\.nu\\/LV', | |
| 234 | - 'Vagabondo', | |
| 235 | - 'Vivante Link Checker', | |
| 236 | - 'Vortex', | |
| 237 | - 'voyager\\/', | |
| 238 | - 'VYU2', | |
| 239 | - 'W3C-checklink', | |
| 240 | - 'W3C_CSS_Validator_JFouffa', | |
| 241 | - 'W3C_I18n-Checker', | |
| 242 | - 'W3C-mobileOK', | |
| 243 | - 'W3C_Unicorn', | |
| 244 | - 'W3C_Validator', | |
| 245 | - 'WebIndex', | |
| 246 | - 'Websquash\.com', | |
| 247 | - 'webcollage', | |
| 248 | - 'webmon ', | |
| 249 | - 'WeSEE:Search', | |
| 250 | - 'wf84', | |
| 251 | - 'wget', | |
| 252 | - 'WomlpeFactory', | |
| 253 | - 'wotbox', | |
| 254 | - 'Xenu Link Sleuth', | |
| 255 | - 'XML Sitemaps Generator', | |
| 256 | - 'Y!J-ASR', | |
| 257 | - 'yacy', | |
| 258 | - 'yacybot', | |
| 259 | - 'Yahoo Link Preview', | |
| 260 | - 'Yahoo! Slurp China', | |
| 261 | - 'Yahoo! Slurp', | |
| 262 | - 'YahooSeeker', | |
| 263 | - 'YahooSeeker-Testing', | |
| 264 | - 'YandexImages', | |
| 265 | - 'YandexMetrika', | |
| 266 | - 'yandex', | |
| 267 | - 'yanga', | |
| 268 | - 'yeti', | |
| 269 | - 'yoogliFetchAgent', | |
| 270 | - 'Zao', | |
| 271 | - 'ZyBorg', | |
| 272 | - '[a-z0-9\\-_]*((?<!cu)bot|crawler|archiver|transcoder|spider)', | |
| 273 | - ); | |
| 58 | + protected static $crawlers = array( | |
| 59 | + '007ac9 Crawler', | |
| 60 | + '008\\/', | |
| 61 | + 'A6-Indexer', | |
| 62 | + 'Aboundex', | |
| 63 | + 'Accoona-AI-Agent', | |
| 64 | + 'acoon', | |
| 65 | + 'AddThis', | |
| 66 | + 'ADmantX', | |
| 67 | + 'AHC', | |
| 68 | + 'Airmail', | |
| 69 | + 'Anemone', | |
| 70 | + 'Arachmo', | |
| 71 | + 'archive-com', | |
| 72 | + 'B-l-i-t-z-B-O-T', | |
| 73 | + 'bibnum\.bnf', | |
| 74 | + 'biglotron', | |
| 75 | + 'binlar', | |
| 76 | + 'boitho\.com-dc', | |
| 77 | + 'BUbiNG', | |
| 78 | + 'Butterfly\\/', | |
| 79 | + 'BuzzSumo', | |
| 80 | + 'CC Metadata Scaper', | |
| 81 | + 'Cerberian Drtrs', | |
| 82 | + 'changedetection', | |
| 83 | + 'Charlotte', | |
| 84 | + 'clips\.ua\.ac\.be', | |
| 85 | + 'CloudFlare-AlwaysOnline', | |
| 86 | + 'coccoc', | |
| 87 | + 'Commons-HttpClient', | |
| 88 | + 'convera', | |
| 89 | + 'cosmos', | |
| 90 | + 'Covario-IDS', | |
| 91 | + 'crawler4j', | |
| 92 | + 'curl', | |
| 93 | + 'CyberPatrol', | |
| 94 | + 'DataparkSearch', | |
| 95 | + 'dataprovider', | |
| 96 | + 'Digg', | |
| 97 | + 'DomainAppender', | |
| 98 | + 'drupact', | |
| 99 | + 'EARTHCOM', | |
| 100 | + 'ec2linkfinder', | |
| 101 | + 'ElectricMonk', | |
| 102 | + 'Embedly', | |
| 103 | + 'europarchive\.org', | |
| 104 | + 'EventMachine HttpClient', | |
| 105 | + 'ezooms', | |
| 106 | + 'eZ Publish Link Validator', | |
| 107 | + 'facebookexternalhit', | |
| 108 | + 'Feedfetcher-Google', | |
| 109 | + 'FeedValidator', | |
| 110 | + 'FindLinks', | |
| 111 | + 'findlink', | |
| 112 | + 'findthatfile', | |
| 113 | + 'Flamingo_SearchEngine', | |
| 114 | + 'fluffy', | |
| 115 | + 'getprismatic\.com', | |
| 116 | + 'g00g1e\.net', | |
| 117 | + 'GigablastOpenSource', | |
| 118 | + 'grub-client', | |
| 119 | + 'Genieo', | |
| 120 | + 'Go-http-client', | |
| 121 | + 'Googlebot-Image', | |
| 122 | + 'Googlebot-Mobile', | |
| 123 | + 'Google-HTTP-Java-Client', | |
| 124 | + 'Google favicon', | |
| 125 | + 'heritrix', | |
| 126 | + 'Holmes', | |
| 127 | + 'htdig', | |
| 128 | + 'httpunit', | |
| 129 | + 'httrack', | |
| 130 | + 'ia_archiver', | |
| 131 | + 'ichiro', | |
| 132 | + 'igdeSpyder', | |
| 133 | + 'InAGist', | |
| 134 | + 'InfoWizards Reciprocal Link System PRO', | |
| 135 | + 'integromedb', | |
| 136 | + 'IODC', | |
| 137 | + 'IOI', | |
| 138 | + 'ips-agent', | |
| 139 | + 'iZSearch', | |
| 140 | + 'L\.webis', | |
| 141 | + 'Larbin', | |
| 142 | + 'libwww', | |
| 143 | + 'Link Valet', | |
| 144 | + 'linkdex', | |
| 145 | + 'LinkExaminer', | |
| 146 | + 'LinkWalker', | |
| 147 | + 'Lipperhey Link Explorer', | |
| 148 | + 'Lipperhey SEO Service', | |
| 149 | + 'LongURL API', | |
| 150 | + 'ltx71', | |
| 151 | + 'lwp-trivial', | |
| 152 | + 'MegaIndex\.ru', | |
| 153 | + 'mabontland', | |
| 154 | + 'MagpieRSS', | |
| 155 | + 'Mediapartners-Google', | |
| 156 | + 'MetaURI', | |
| 157 | + 'Mnogosearch', | |
| 158 | + 'mogimogi', | |
| 159 | + 'Morning Paper', | |
| 160 | + 'Mrcgiguy', | |
| 161 | + 'MVAClient', | |
| 162 | + 'netresearchserver', | |
| 163 | + 'NewsGator', | |
| 164 | + 'newsme', | |
| 165 | + 'NG-Search', | |
| 166 | + '^NING\\/', | |
| 167 | + 'Notifixious', | |
| 168 | + 'nutch', | |
| 169 | + 'NutchCVS', | |
| 170 | + 'Nymesis', | |
| 171 | + 'oegp', | |
| 172 | + 'online link validator', | |
| 173 | + 'Online Website Link Checker', | |
| 174 | + 'Orbiter', | |
| 175 | + 'ow\.ly', | |
| 176 | + 'Ploetz \+ Zeller', | |
| 177 | + 'page2rss', | |
| 178 | + 'panscient', | |
| 179 | + 'Peew', | |
| 180 | + 'phpcrawl', | |
| 181 | + 'Pizilla', | |
| 182 | + 'Plukkie', | |
| 183 | + 'Pompos', | |
| 184 | + 'postano', | |
| 185 | + 'PostPost', | |
| 186 | + 'postrank', | |
| 187 | + 'proximic', | |
| 188 | + 'PycURL', | |
| 189 | + 'Python-httplib2', | |
| 190 | + 'python-requests', | |
| 191 | + 'Python-urllib', | |
| 192 | + 'Qseero', | |
| 193 | + 'Qwantify', | |
| 194 | + 'Radian6', | |
| 195 | + 'RebelMouse', | |
| 196 | + 'REL Link Checker', | |
| 197 | + 'RetrevoPageAnalyzer', | |
| 198 | + 'Riddler', | |
| 199 | + 'Robosourcer', | |
| 200 | + 'Ruby', | |
| 201 | + 'SandCrawler', | |
| 202 | + 'SBIder', | |
| 203 | + 'ScoutJet', | |
| 204 | + 'ScoutURLMonitor', | |
| 205 | + 'Scrapy', | |
| 206 | + 'Scrubby', | |
| 207 | + 'SearchSight', | |
| 208 | + 'semanticdiscovery', | |
| 209 | + 'SEOstats', | |
| 210 | + 'Seznam screenshot-generator', | |
| 211 | + 'ShopWiki', | |
| 212 | + 'SiteBar', | |
| 213 | + 'siteexplorer\.info', | |
| 214 | + 'slider\.com', | |
| 215 | + 'slurp', | |
| 216 | + 'Snappy', | |
| 217 | + 'sogou', | |
| 218 | + 'speedy', | |
| 219 | + 'Sqworm', | |
| 220 | + 'StackRambler', | |
| 221 | + 'Stratagems Kumo', | |
| 222 | + 'summify', | |
| 223 | + 'teoma', | |
| 224 | + 'theoldreader\.com', | |
| 225 | + 'TinEye', | |
| 226 | + 'Traackr.com', | |
| 227 | + 'truwoGPS', | |
| 228 | + 'tweetedtimes\.com', | |
| 229 | + 'Twikle', | |
| 230 | + 'UnwindFetchor', | |
| 231 | + 'updated', | |
| 232 | + 'urlresolver', | |
| 233 | + 'Validator\.nu\\/LV', | |
| 234 | + 'Vagabondo', | |
| 235 | + 'Vivante Link Checker', | |
| 236 | + 'Vortex', | |
| 237 | + 'voyager\\/', | |
| 238 | + 'VYU2', | |
| 239 | + 'W3C-checklink', | |
| 240 | + 'W3C_CSS_Validator_JFouffa', | |
| 241 | + 'W3C_I18n-Checker', | |
| 242 | + 'W3C-mobileOK', | |
| 243 | + 'W3C_Unicorn', | |
| 244 | + 'W3C_Validator', | |
| 245 | + 'WebIndex', | |
| 246 | + 'Websquash\.com', | |
| 247 | + 'webcollage', | |
| 248 | + 'webmon ', | |
| 249 | + 'WeSEE:Search', | |
| 250 | + 'wf84', | |
| 251 | + 'wget', | |
| 252 | + 'WomlpeFactory', | |
| 253 | + 'wotbox', | |
| 254 | + 'Xenu Link Sleuth', | |
| 255 | + 'XML Sitemaps Generator', | |
| 256 | + 'Y!J-ASR', | |
| 257 | + 'yacy', | |
| 258 | + 'yacybot', | |
| 259 | + 'Yahoo Link Preview', | |
| 260 | + 'Yahoo! Slurp China', | |
| 261 | + 'Yahoo! Slurp', | |
| 262 | + 'YahooSeeker', | |
| 263 | + 'YahooSeeker-Testing', | |
| 264 | + 'YandexImages', | |
| 265 | + 'YandexMetrika', | |
| 266 | + 'yandex', | |
| 267 | + 'yanga', | |
| 268 | + 'yeti', | |
| 269 | + 'yoogliFetchAgent', | |
| 270 | + 'Zao', | |
| 271 | + 'ZyBorg', | |
| 272 | + '[a-z0-9\\-_]*((?<!cu)bot|crawler|archiver|transcoder|spider)', | |
| 273 | + ); | |
| 274 | 274 | |
| 275 | - /** | |
| 276 | - * All possible HTTP headers that represent the | |
| 277 | - * User-Agent string. | |
| 278 | - * | |
| 279 | - * @var array | |
| 280 | - */ | |
| 281 | - protected static $uaHttpHeaders = array( | |
| 282 | - // The default User-Agent string. | |
| 283 | - 'HTTP_USER_AGENT', | |
| 284 | - // Header can occur on devices using Opera Mini. | |
| 285 | - 'HTTP_X_OPERAMINI_PHONE_UA', | |
| 286 | - // Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/ | |
| 287 | - 'HTTP_X_DEVICE_USER_AGENT', | |
| 288 | - 'HTTP_X_ORIGINAL_USER_AGENT', | |
| 289 | - 'HTTP_X_SKYFIRE_PHONE', | |
| 290 | - 'HTTP_X_BOLT_PHONE_UA', | |
| 291 | - 'HTTP_DEVICE_STOCK_UA', | |
| 292 | - 'HTTP_X_UCBROWSER_DEVICE_UA', | |
| 293 | - ); | |
| 275 | + /** | |
| 276 | + * All possible HTTP headers that represent the | |
| 277 | + * User-Agent string. | |
| 278 | + * | |
| 279 | + * @var array | |
| 280 | + */ | |
| 281 | + protected static $uaHttpHeaders = array( | |
| 282 | + // The default User-Agent string. | |
| 283 | + 'HTTP_USER_AGENT', | |
| 284 | + // Header can occur on devices using Opera Mini. | |
| 285 | + 'HTTP_X_OPERAMINI_PHONE_UA', | |
| 286 | + // Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/ | |
| 287 | + 'HTTP_X_DEVICE_USER_AGENT', | |
| 288 | + 'HTTP_X_ORIGINAL_USER_AGENT', | |
| 289 | + 'HTTP_X_SKYFIRE_PHONE', | |
| 290 | + 'HTTP_X_BOLT_PHONE_UA', | |
| 291 | + 'HTTP_DEVICE_STOCK_UA', | |
| 292 | + 'HTTP_X_UCBROWSER_DEVICE_UA', | |
| 293 | + ); | |
| 294 | 294 | |
| 295 | - /** | |
| 296 | - * Class constructor. | |
| 297 | - */ | |
| 298 | - public function __construct(array $headers = null, $userAgent = null) | |
| 299 | -    { | |
| 300 | - $this->setHttpHeaders($headers); | |
| 301 | - $this->setUserAgent($userAgent); | |
| 302 | - } | |
| 295 | + /** | |
| 296 | + * Class constructor. | |
| 297 | + */ | |
| 298 | + public function __construct(array $headers = null, $userAgent = null) | |
| 299 | +	{ | |
| 300 | + $this->setHttpHeaders($headers); | |
| 301 | + $this->setUserAgent($userAgent); | |
| 302 | + } | |
| 303 | 303 | |
| 304 | - public function setHttpHeaders($httpHeaders = null) | |
| 305 | -    { | |
| 306 | - // use global _SERVER if $httpHeaders aren't defined | |
| 307 | -        if (!is_array($httpHeaders) || !count($httpHeaders)) { | |
| 308 | - $httpHeaders = $_SERVER; | |
| 309 | - } | |
| 310 | - // clear existing headers | |
| 311 | - $this->httpHeaders = array(); | |
| 312 | - // Only save HTTP headers. In PHP land, that means only _SERVER vars that | |
| 313 | - // start with HTTP_. | |
| 314 | -        foreach ($httpHeaders as $key => $value) { | |
| 315 | -            if (substr($key, 0, 5) === 'HTTP_') { | |
| 316 | - $this->httpHeaders[$key] = $value; | |
| 317 | - } | |
| 318 | - } | |
| 319 | - } | |
| 304 | + public function setHttpHeaders($httpHeaders = null) | |
| 305 | +	{ | |
| 306 | + // use global _SERVER if $httpHeaders aren't defined | |
| 307 | +		if (!is_array($httpHeaders) || !count($httpHeaders)) { | |
| 308 | + $httpHeaders = $_SERVER; | |
| 309 | + } | |
| 310 | + // clear existing headers | |
| 311 | + $this->httpHeaders = array(); | |
| 312 | + // Only save HTTP headers. In PHP land, that means only _SERVER vars that | |
| 313 | + // start with HTTP_. | |
| 314 | +		foreach ($httpHeaders as $key => $value) { | |
| 315 | +			if (substr($key, 0, 5) === 'HTTP_') { | |
| 316 | + $this->httpHeaders[$key] = $value; | |
| 317 | + } | |
| 318 | + } | |
| 319 | + } | |
| 320 | 320 | |
| 321 | - public function getUaHttpHeaders() | |
| 322 | -    { | |
| 323 | - return self::$uaHttpHeaders; | |
| 324 | - } | |
| 321 | + public function getUaHttpHeaders() | |
| 322 | +	{ | |
| 323 | + return self::$uaHttpHeaders; | |
| 324 | + } | |
| 325 | 325 | |
| 326 | - public function setUserAgent($userAgent = null) | |
| 327 | -    { | |
| 328 | -        if (false === empty($userAgent)) { | |
| 329 | - return $this->userAgent = $userAgent; | |
| 330 | -        } else { | |
| 331 | - $this->userAgent = null; | |
| 332 | -            foreach ($this->getUaHttpHeaders() as $altHeader) { | |
| 333 | -                if (false === empty($this->httpHeaders[$altHeader])) { // @todo: should use getHttpHeader(), but it would be slow. (Serban) | |
| 334 | - $this->userAgent .= $this->httpHeaders[$altHeader].' '; | |
| 335 | - } | |
| 336 | - } | |
| 326 | + public function setUserAgent($userAgent = null) | |
| 327 | +	{ | |
| 328 | +		if (false === empty($userAgent)) { | |
| 329 | + return $this->userAgent = $userAgent; | |
| 330 | +		} else { | |
| 331 | + $this->userAgent = null; | |
| 332 | +			foreach ($this->getUaHttpHeaders() as $altHeader) { | |
| 333 | +				if (false === empty($this->httpHeaders[$altHeader])) { // @todo: should use getHttpHeader(), but it would be slow. (Serban) | |
| 334 | + $this->userAgent .= $this->httpHeaders[$altHeader].' '; | |
| 335 | + } | |
| 336 | + } | |
| 337 | 337 | |
| 338 | - return $this->userAgent = (!empty($this->userAgent) ? trim($this->userAgent) : null); | |
| 339 | - } | |
| 340 | - } | |
| 338 | + return $this->userAgent = (!empty($this->userAgent) ? trim($this->userAgent) : null); | |
| 339 | + } | |
| 340 | + } | |
| 341 | 341 | |
| 342 | - public function getRegex() | |
| 343 | -    { | |
| 344 | -        return '('.implode('|', self::$crawlers).')'; | |
| 345 | - } | |
| 342 | + public function getRegex() | |
| 343 | +	{ | |
| 344 | +		return '('.implode('|', self::$crawlers).')'; | |
| 345 | + } | |
| 346 | 346 | |
| 347 | - public function getIgnored() | |
| 348 | -    { | |
| 349 | -        return '('.implode('|', self::$ignore).')'; | |
| 350 | - } | |
| 347 | + public function getIgnored() | |
| 348 | +	{ | |
| 349 | +		return '('.implode('|', self::$ignore).')'; | |
| 350 | + } | |
| 351 | 351 | |
| 352 | - public function isCrawler($userAgent = null) | |
| 353 | -    { | |
| 354 | - $agent = is_null($userAgent) ? $this->userAgent : $userAgent; | |
| 352 | + public function isCrawler($userAgent = null) | |
| 353 | +	{ | |
| 354 | + $agent = is_null($userAgent) ? $this->userAgent : $userAgent; | |
| 355 | 355 | |
| 356 | -        $agent = preg_replace('/'.$this->getIgnored().'/i', '', $agent); | |
| 356 | +		$agent = preg_replace('/'.$this->getIgnored().'/i', '', $agent); | |
| 357 | 357 | |
| 358 | -        $result = preg_match('/'.$this->getRegex().'/i', $agent, $matches); | |
| 358 | +		$result = preg_match('/'.$this->getRegex().'/i', $agent, $matches); | |
| 359 | 359 | |
| 360 | -        if ($matches) { | |
| 361 | - $this->matches = $matches; | |
| 362 | - } | |
| 360 | +		if ($matches) { | |
| 361 | + $this->matches = $matches; | |
| 362 | + } | |
| 363 | 363 | |
| 364 | - return (bool) $result; | |
| 365 | - } | |
| 364 | + return (bool) $result; | |
| 365 | + } | |
| 366 | 366 | |
| 367 | - public function getMatches() | |
| 368 | -    { | |
| 369 | - return $this->matches[0]; | |
| 370 | - } | |
| 367 | + public function getMatches() | |
| 368 | +	{ | |
| 369 | + return $this->matches[0]; | |
| 370 | + } | |
| 371 | 371 | } |