PluginProbe ʕ •ᴥ•ʔ
Post Views Counter / 1.5.4
Post Views Counter v1.5.4
1.7.13 1.7.12 1.7.11 trunk 1.0.0 1.0.1 1.0.10 1.0.11 1.0.12 1.0.2 1.0.3 1.0.4 1.0.5 1.0.6 1.0.7 1.0.8 1.0.9 1.1.0 1.1.1 1.1.2 1.1.3 1.1.4 1.2.0 1.2.1 1.2.10 1.2.11 1.2.12 1.2.13 1.2.14 1.2.2 1.2.3 1.2.4 1.2.5 1.2.6 1.2.7 1.2.8 1.2.9 1.3 1.3.1 1.3.10 1.3.11 1.3.12 1.3.13 1.3.2 1.3.2.1 1.3.3 1.3.4 1.3.5 1.3.6 1.3.7 1.3.8 1.3.9 1.4 1.4.1 1.4.2 1.4.3 1.4.4 1.4.5 1.4.6 1.4.7 1.4.8 1.5.0 1.5.1 1.5.2 1.5.3 1.5.4 1.5.5 1.5.6 1.5.7 1.5.8 1.5.9 1.6.0 1.6.1 1.7.0 1.7.1 1.7.10 1.7.2 1.7.3 1.7.4 1.7.5 1.7.6 1.7.7 1.7.8 1.7.9
post-views-counter / includes / class-crawler-detect.php
post-views-counter / includes Last commit date
class-admin.php 1 year ago class-columns.php 1 year ago class-counter.php 1 year ago class-crawler-detect.php 1 year ago class-cron.php 1 year ago class-dashboard.php 1 year ago class-frontend.php 1 year ago class-functions.php 1 year ago class-query.php 1 year ago class-settings-api.php 1 year ago class-settings.php 1 year ago class-update.php 1 year ago class-widgets.php 1 year ago functions.php 1 year ago
class-crawler-detect.php
1714 lines
1 <?php
2 // exit if accessed directly
3 if ( ! defined( 'ABSPATH' ) )
4 exit;
5
6 /**
7 * Post_Views_Counter_Crawler_Detect class.
8 *
9 * Based on CrawlerDetect php class adjusted to PHP 5.2
10 * https://github.com/JayBizzle/Crawler-Detect/blob/master/src/CrawlerDetect.php
11 *
12 * @since 1.2.4
13 * @version 1.3.0
14 * @class Post_Views_Counter_Crawler_Detect
15 */
16 class Post_Views_Counter_Crawler_Detect {
17
18 /**
19 * The user agent.
20 *
21 * @var null
22 */
23 protected $user_agent = null;
24
25 /**
26 * Headers that contain a user agent.
27 *
28 * @var array
29 */
30 protected $http_headers = [];
31
32 /**
33 * Store regex matches.
34 *
35 * @var array
36 */
37 protected $matches = [];
38
39 /**
40 * Crawlers object.
41 *
42 * @var object
43 */
44 protected $crawlers = [];
45
46 /**
47 * Exclusions object.
48 *
49 * @var object
50 */
51 protected $exclusions = [];
52
53 /**
54 * Headers object.
55 *
56 * @var object
57 */
58 protected $ua_http_headers;
59
60 /**
61 * Class constructor.
62 *
63 * @return void
64 */
65 public function __construct() {
66 $this->crawlers = $this->get_crawlers_list();
67 $this->exclusions = $this->get_exclusions_list();
68
69 add_action( 'after_setup_theme', [ $this, 'init' ] );
70 }
71
72 /**
73 * Initialize class.
74 *
75 * @return void
76 */
77 public function init() {
78 // break on admin side
79 if ( is_admin() && ! wp_doing_ajax() )
80 return;
81
82 $this->ua_http_headers = $this->get_headers_list();
83 $this->set_http_headers();
84 $this->set_user_agent();
85 }
86
87 /**
88 * Set HTTP headers.
89 *
90 * @param array $http_headers
91 * @return void
92 */
93 public function set_http_headers( $http_headers = null ) {
94 // use global _SERVER if $http_headers aren't defined
95 if ( ! is_array( $http_headers ) || ! count( $http_headers ) )
96 $http_headers = $_SERVER;
97
98 // clear existing headers
99 $this->http_headers = [];
100
101 // only save HTTP headers - in PHP land, that means only _SERVER vars that start with HTTP_.
102 foreach ( $http_headers as $key => $value ) {
103 if ( substr( $key, 0, 5 ) === 'HTTP_' )
104 $this->http_headers[$key] = $value;
105 }
106 }
107
108 /**
109 * Return user agent headers.
110 *
111 * @return array
112 */
113 public function get_ua_http_headers() {
114 return $this->ua_http_headers;
115 }
116
117 /**
118 * Return the user agent.
119 *
120 * @return string
121 */
122 public function get_user_agent() {
123 return $this->user_agent;
124 }
125
126 /**
127 * Set the user agent.
128 *
129 * @param string $user_agent
130 * @return string
131 */
132 public function set_user_agent( $user_agent = null ) {
133 if ( false === empty( $user_agent ) )
134 return $this->user_agent = $user_agent;
135 else {
136 $this->user_agent = null;
137
138 foreach ( $this->get_ua_http_headers() as $alt_header ) {
139 if ( false === empty( $this->http_headers[$alt_header] ) ) // @todo: should use get_http_header(), but it would be slow.
140 $this->user_agent .= $this->http_headers[$alt_header] . ' ';
141 }
142
143 return $this->user_agent = ( ! empty( $this->user_agent ) ? trim( $this->user_agent ) : null );
144 }
145 }
146
147 /**
148 * Build the user agent regex.
149 *
150 * @param array $crawlers
151 *
152 * @return string
153 */
154 public function get_regex( $crawlers = [] ) {
155 return '(' . implode( '|', empty( $crawlers ) ? $this->crawlers : $crawlers ) . ')';
156 }
157
158 /**
159 * Build the replacement regex.
160 *
161 * @return string
162 */
163 public function get_exclusions() {
164 return '(' . implode( '|', $this->exclusions ) . ')';
165 }
166
167 /**
168 * Check user agent string against the regex.
169 *
170 * @param string $user_agent
171 * @return bool
172 */
173 public function is_crawler( $user_agent = null ) {
174 // update crawlers
175 $crawlers = apply_filters( 'pvc_crawlers_list', $this->crawlers );
176
177 $agent = (string)( is_null( $user_agent ) ? $this->user_agent : $user_agent );
178 $agent = preg_replace( '/' . $this->get_exclusions() . '/i', '', $agent );
179
180 if ( strlen( trim( $agent ) ) === 0 )
181 return false;
182 else
183 $result = preg_match( '/' . $this->get_regex( $crawlers ) . '/i', trim( $agent ), $matches );
184
185 if ( $matches )
186 $this->matches = $matches;
187
188 return (bool) $result;
189 }
190
191 /**
192 * Return the matches.
193 *
194 * @return string
195 */
196 public function get_matches() {
197 return isset( $this->matches[0] ) ? $this->matches[0] : null;
198 }
199
200 /**
201 * Return the regular expressions to match against the user agent.
202 *
203 * @return array
204 */
205 protected function get_crawlers_list() {
206 return [
207 ' YLT',
208 '^Aether',
209 '^Amazon Simple Notification Service Agent$',
210 '^Amazon-Route53-Health-Check-Service',
211 '^Amazon CloudFront',
212 '^b0t$',
213 '^bluefish ',
214 '^Calypso v\/',
215 '^COMODO DCV',
216 '^Corax',
217 '^DangDang',
218 '^DavClnt',
219 '^DHSH',
220 '^docker\/[0-9]',
221 '^Expanse',
222 '^FDM ',
223 '^git\/',
224 '^Goose\/',
225 '^Grabber',
226 '^Gradle\/',
227 '^HTTPClient\/',
228 '^HTTPing',
229 '^Java\/',
230 '^Jeode\/',
231 '^Jetty\/',
232 '^Mail\/',
233 '^Mget',
234 '^Microsoft URL Control',
235 '^Mikrotik\/',
236 '^Netlab360',
237 '^NG\/[0-9\.]',
238 '^NING\/',
239 '^npm\/',
240 '^Nuclei',
241 '^PHP-AYMAPI\/',
242 '^PHP\/',
243 '^pip\/',
244 '^pnpm\/',
245 '^RMA\/',
246 '^Ruby|Ruby\/[0-9]',
247 "^symbolicator\\/",
248 '^Swurl ',
249 '^TLS tester ',
250 '^twine\/',
251 '^ureq',
252 '^VSE\/[0-9]',
253 '^WordPress\.com',
254 '^XRL\/[0-9]',
255 '^ZmEu',
256 '008\/',
257 '13TABS',
258 '192\.comAgent',
259 '2GDPR\/',
260 '2ip\.ru',
261 '404enemy',
262 '7Siters',
263 '80legs',
264 'a3logics\.in',
265 'A6-Indexer',
266 'Abonti',
267 'Aboundex',
268 'aboutthedomain',
269 'Accoona-AI-Agent',
270 'acebookexternalhit\/',
271 'acoon',
272 'acrylicapps\.com\/pulp',
273 'Acunetix',
274 'AdAuth\/',
275 'adbeat',
276 'AddThis',
277 'ADmantX',
278 'AdminLabs',
279 'adressendeutschland',
280 'adreview\/',
281 'adscanner',
282 'adstxt-worker',
283 'Adstxtaggregator',
284 'adstxt\.com',
285 'Adyen HttpClient',
286 'AffiliateLabz\/',
287 'affilimate-puppeteer',
288 'agentslug',
289 'AHC',
290 'aihit',
291 'aiohttp\/',
292 'Airmail',
293 'akka-http\/',
294 'akula\/',
295 'alertra',
296 'alexa site audit',
297 'Alibaba\.Security\.Heimdall',
298 'Alligator',
299 'allloadin',
300 'AllSubmitter',
301 'alyze\.info',
302 'amagit',
303 'Anarchie',
304 'AndroidDownloadManager',
305 'Anemone',
306 'AngleSharp',
307 'annotate_google',
308 'Anthill',
309 'Anturis Agent',
310 'Ant\.com',
311 'AnyEvent-HTTP\/',
312 'Apache Ant\/',
313 'Apache Droid',
314 'Apache OpenOffice',
315 'Apache-HttpAsyncClient',
316 'Apache-HttpClient',
317 'ApacheBench',
318 'Apexoo',
319 'apimon\.de',
320 'APIs-Google',
321 'AportWorm\/',
322 'AppBeat\/',
323 'AppEngine-Google',
324 'AppleSyndication',
325 'Aprc\/[0-9]',
326 'Arachmo',
327 'arachnode',
328 'Arachnophilia',
329 'aria2',
330 'Arukereso',
331 'asafaweb',
332 'Asana\/',
333 'Ask Jeeves',
334 'AskQuickly',
335 'ASPSeek',
336 'Asterias',
337 'Astute',
338 'asynchttp',
339 'Attach',
340 'attohttpc',
341 'autocite',
342 'AutomaticWPTester',
343 'Autonomy',
344 'awin\.com',
345 'AWS Security Scanner',
346 'axios\/',
347 'a\.pr-cy\.ru',
348 'B-l-i-t-z-B-O-T',
349 'Backlink-Ceck',
350 'BacklinkHttpStatus',
351 'BackStreet',
352 'BackupLand',
353 'BackWeb',
354 'Bad-Neighborhood',
355 'Badass',
356 'baidu\.com',
357 'Bandit',
358 'Barracuda Sentinel \(EE\)',
359 'basicstate',
360 'BatchFTP',
361 'Battleztar Bazinga',
362 'baypup\/',
363 'BazQux',
364 'BBBike',
365 'BCKLINKS',
366 'BDFetch',
367 'BegunAdvertising',
368 'Bewica-security-scan',
369 'Bidtellect',
370 'BigBozz',
371 'Bigfoot',
372 'biglotron',
373 'BingLocalSearch',
374 'BingPreview',
375 'binlar',
376 'biNu image cacher',
377 'Bitacle',
378 'Bitrix link preview',
379 'biz_Directory',
380 'BKCTwitterUnshortener\/',
381 'Black Hole',
382 'Blackboard Safeassign',
383 'BlackWidow',
384 'BlockNote\.Net',
385 'BlogBridge',
386 'Bloglines',
387 'Bloglovin',
388 'BlogPulseLive',
389 'BlogSearch',
390 'Blogtrottr',
391 'BlowFish',
392 'boitho\.com-dc',
393 'Boost\.Beast',
394 'BPImageWalker',
395 'Braintree-Webhooks',
396 'Branch Metrics API',
397 'Branch-Passthrough',
398 'Brandprotect',
399 'Brandwatch',
400 'Brodie\/',
401 'Browsershots',
402 'BUbiNG',
403 'Buck\/',
404 'Buddy',
405 'BuiltWith',
406 'Bullseye',
407 'BunnySlippers',
408 'Burf Search',
409 'Butterfly\/',
410 'BuzzSumo',
411 'CAAM\/[0-9]',
412 'caam dot crwlr at gmail dot com',
413 'CakePHP',
414 'Calculon',
415 'Canary%20Mail',
416 'CaretNail',
417 'catexplorador',
418 'CC Metadata Scaper',
419 'Cegbfeieh',
420 'censys',
421 'centuryb.o.t9[at]gmail.com',
422 'Cerberian Drtrs',
423 'CERT\.at-Statistics-Survey',
424 'cf-facebook',
425 'cg-eye',
426 'changedetection',
427 'ChangesMeter',
428 'Charlotte',
429 'chatterino-api-cache',
430 'CheckHost',
431 'checkprivacy',
432 'CherryPicker',
433 'ChinaClaw',
434 'Chirp\/',
435 'chkme\.com',
436 'Chlooe',
437 'Chromaxa',
438 'CirrusExplorer',
439 'CISPA Vulnerability Notification',
440 'CISPA Web Analyser',
441 'Citoid',
442 'CJNetworkQuality',
443 'Clarsentia',
444 'clips\.ua\.ac\.be',
445 'Cloud mapping',
446 'CloudEndure',
447 'CloudFlare-AlwaysOnline',
448 'Cloudflare-Healthchecks',
449 'Cloudinary',
450 'cmcm\.com',
451 'coccoc',
452 'cognitiveseo',
453 'ColdFusion',
454 'colly -',
455 'CommaFeed',
456 'Commons-HttpClient',
457 'commonscan',
458 'contactbigdatafr',
459 'contentkingapp',
460 'Contextual Code Sites Explorer',
461 'convera',
462 'CookieReports',
463 'copyright sheriff',
464 'CopyRightCheck',
465 'Copyscape',
466 'cortex\/',
467 'Cosmos4j\.feedback',
468 'Covario-IDS',
469 'Craw\/',
470 'Crescent',
471 'Criteo',
472 'Crowsnest',
473 'CSHttp',
474 'CSSCheck',
475 'Cula\/',
476 'curb',
477 'Curious George',
478 'curl',
479 'cuwhois\/',
480 'cybo\.com',
481 'DAP\/NetHTTP',
482 'DareBoost',
483 'DatabaseDriverMysqli',
484 'DataCha0s',
485 'DatadogSynthetics',
486 'Datafeedwatch',
487 'Datanyze',
488 'DataparkSearch',
489 'dataprovider',
490 'DataXu',
491 'Daum(oa)?[ \/][0-9]',
492 'dBpoweramp',
493 'ddline',
494 'deeris',
495 'delve\.ai',
496 'Demon',
497 'DeuSu',
498 'developers\.google\.com\/\+\/web\/snippet\/',
499 'Devil',
500 'Digg',
501 'Digincore',
502 'DigitalPebble',
503 'Dirbuster',
504 'Discourse Forum Onebox',
505 'Dispatch\/',
506 'Disqus\/',
507 'DittoSpyder',
508 'dlvr',
509 'DMBrowser',
510 'DNSPod-reporting',
511 'docoloc',
512 'Dolphin http client',
513 'DomainAppender',
514 'DomainLabz',
515 'Domains Project\/',
516 'Donuts Content Explorer',
517 'dotMailer content retrieval',
518 'dotSemantic',
519 'downforeveryoneorjustme',
520 'Download Wonder',
521 'downnotifier',
522 'DowntimeDetector',
523 'Drip',
524 'drupact',
525 'Drupal \(\+http:\/\/drupal\.org\/\)',
526 'DTS Agent',
527 'dubaiindex',
528 'DuplexWeb-Google',
529 'DynatraceSynthetic',
530 'EARTHCOM',
531 'Easy-Thumb',
532 'EasyDL',
533 'Ebingbong',
534 'ec2linkfinder',
535 'eCairn-Grabber',
536 'eCatch',
537 'ECCP',
538 'eContext\/',
539 'Ecxi',
540 'EirGrabber',
541 'ElectricMonk',
542 'elefent',
543 'EMail Exractor',
544 'EMail Wolf',
545 'EmailWolf',
546 'Embarcadero',
547 'Embed PHP Library',
548 'Embedly',
549 'endo\/',
550 'europarchive\.org',
551 'evc-batch',
552 'EventMachine HttpClient',
553 'Everwall Link Expander',
554 'Evidon',
555 'Evrinid',
556 'ExactSearch',
557 'ExaleadCloudview',
558 'Excel\/',
559 'exif',
560 'ExoRank',
561 'Exploratodo',
562 'Express WebPictures',
563 'Extreme Picture Finder',
564 'EyeNetIE',
565 'ezooms',
566 'facebookcatalog',
567 'facebookexternalhit',
568 'facebookexternalua',
569 'facebookplatform',
570 'fairshare',
571 'Faraday v',
572 'fasthttp',
573 'Faveeo',
574 'Favicon downloader',
575 'faviconarchive',
576 'faviconkit',
577 'FavOrg',
578 'Feed Wrangler',
579 'Feedable\/',
580 'Feedbin',
581 'FeedBooster',
582 'FeedBucket',
583 'FeedBunch\/',
584 'FeedBurner',
585 'feeder',
586 'Feedly',
587 'FeedshowOnline',
588 'Feedshow\/',
589 'Feedspot',
590 'FeedViewer\/',
591 'Feedwind\/',
592 'FeedZcollector',
593 'feeltiptop',
594 'Fetch API',
595 'Fetch\/[0-9]',
596 'Fever\/[0-9]',
597 'FHscan',
598 'Fiery%20Feeds',
599 'Filestack',
600 'Fimap',
601 'findlink',
602 'findthatfile',
603 'FlashGet',
604 'FlipboardBrowserProxy',
605 'FlipboardProxy',
606 'FlipboardRSS',
607 'Flock\/',
608 'Florienzh\/',
609 'fluffy',
610 'Flunky',
611 'flynxapp',
612 'forensiq',
613 'ForusP',
614 'FoundSeoTool',
615 'fragFINN\.de',
616 'free thumbnails',
617 'Freeuploader',
618 'FreshRSS',
619 'frontman',
620 'Funnelback',
621 'Fuzz Faster U Fool',
622 'G-i-g-a-b-o-t',
623 'g00g1e\.net',
624 'ganarvisitas',
625 'gdnplus\.com',
626 'GeedoProductSearch',
627 'geek-tools',
628 'Genieo',
629 'GentleSource',
630 'GetCode',
631 'Getintent',
632 'GetLinkInfo',
633 'getprismatic',
634 'GetRight',
635 'getroot',
636 'GetURLInfo\/',
637 'GetWeb',
638 'Geziyor',
639 'Ghost Inspector',
640 'GigablastOpenSource',
641 'GIS-LABS',
642 'github-camo',
643 'GitHub-Hookshot',
644 'github\.com',
645 'Go http package',
646 'Go [\d\.]* package http',
647 'Go!Zilla',
648 'Go-Ahead-Got-It',
649 'Go-http-client',
650 'go-mtasts\/',
651 'gobuster',
652 'gobyus',
653 'Gofeed',
654 'gofetch',
655 'Goldfire Server',
656 'GomezAgent',
657 'gooblog',
658 'Goodzer\/',
659 'Google AppsViewer',
660 'Google Desktop',
661 'Google favicon',
662 'Google Keyword Suggestion',
663 'Google Keyword Tool',
664 'Google Page Speed Insights',
665 'Google PP Default',
666 'Google Search Console',
667 'Google Web Preview',
668 'Google-Ads',
669 'Google-Adwords',
670 'Google-Apps-Script',
671 'Google-Calendar-Importer',
672 'Google-HotelAdsVerifier',
673 'Google-HTTP-Java-Client',
674 'Google-InspectionTool',
675 'Google-Podcast',
676 'Google-Publisher-Plugin',
677 'Google-Read-Aloud',
678 'Google-SearchByImage',
679 'Google-Site-Verification',
680 'Google-SMTP-STS',
681 'Google-speakr',
682 'Google-Structured-Data-Testing-Tool',
683 'Google-Transparency-Report',
684 'google-xrawler',
685 'Google-Youtube-Links',
686 'GoogleDocs',
687 'GoogleHC\/',
688 'GoogleOther',
689 'GoogleProber',
690 'GoogleProducer',
691 'GoogleSites',
692 'Gookey',
693 'GoSpotCheck',
694 'gosquared-thumbnailer',
695 'Gotit',
696 'GoZilla',
697 'grabify',
698 'GrabNet',
699 'Grafula',
700 'Grammarly',
701 'GrapeFX',
702 'GreatNews',
703 'Gregarius',
704 'GRequests',
705 'grokkit',
706 'grouphigh',
707 'grub-client',
708 'gSOAP\/',
709 'GT::WWW',
710 'GTmetrix',
711 'GuzzleHttp',
712 'gvfs\/',
713 'HAA(A)?RTLAND http client',
714 'Haansoft',
715 'hackney\/',
716 'Hadi Agent',
717 'HappyApps-WebCheck',
718 'Hardenize',
719 'Hatena',
720 'Havij',
721 'HaxerMen',
722 'HEADMasterSEO',
723 'HeartRails_Capture',
724 'help@dataminr\.com',
725 'heritrix',
726 'Hexometer',
727 'historious',
728 'hkedcity',
729 'hledejLevne\.cz',
730 'Hloader',
731 'HMView',
732 'Holmes',
733 'HonesoSearchEngine',
734 'HootSuite Image proxy',
735 'Hootsuite-WebFeed',
736 'hosterstats',
737 'HostTracker',
738 'ht:\/\/check',
739 'htdig',
740 'HTMLparser',
741 'htmlyse',
742 'HTTP Banner Detection',
743 'http-get',
744 'HTTP-Header-Abfrage',
745 'http-kit',
746 'http-request\/',
747 'HTTP-Tiny',
748 'HTTP::Lite',
749 'http:\/\/www.neomo.de\/', // 'Francis [Bot]'
750 'HttpComponents',
751 'httphr',
752 'HTTPie',
753 'HTTPMon',
754 'httpRequest',
755 'httpscheck',
756 'httpssites_power',
757 'httpunit',
758 'HttpUrlConnection',
759 'http\.rb\/',
760 'HTTP_Compression_Test',
761 'http_get',
762 'http_request2',
763 'http_requester',
764 'httrack',
765 'huaweisymantec',
766 'HubSpot ',
767 'HubSpot-Link-Resolver',
768 'Humanlinks',
769 'i2kconnect\/',
770 'Iblog',
771 'ichiro',
772 'Id-search',
773 'IdeelaborPlagiaat',
774 'IDG Twitter Links Resolver',
775 'IDwhois\/',
776 'Iframely',
777 'igdeSpyder',
778 'iGooglePortal',
779 'IlTrovatore',
780 'Image Fetch',
781 'Image Sucker',
782 'ImageEngine\/',
783 'ImageVisu\/',
784 'Imagga',
785 'imagineeasy',
786 'imgsizer',
787 'InAGist',
788 'inbound\.li parser',
789 'InDesign%20CC',
790 'Indy Library',
791 'InetURL',
792 'infegy',
793 'infohelfer',
794 'InfoTekies',
795 'InfoWizards Reciprocal Link',
796 'inpwrd\.com',
797 'instabid',
798 'Instapaper',
799 'Integrity',
800 'integromedb',
801 'Intelliseek',
802 'InterGET',
803 'Internet Ninja',
804 'InternetSeer',
805 'internetVista monitor',
806 'internetwache',
807 'internet_archive',
808 'intraVnews',
809 'IODC',
810 'IOI',
811 'Inboxb0t',
812 'iplabel',
813 'ips-agent',
814 'IPS\/[0-9]',
815 'IPWorks HTTP\/S Component',
816 'iqdb\/',
817 'Iria',
818 'Irokez',
819 'isitup\.org',
820 'iskanie',
821 'isUp\.li',
822 'iThemes Sync\/',
823 'IZaBEE',
824 'iZSearch',
825 'JAHHO',
826 'janforman',
827 'Jaunt\/',
828 'Java.*outbrain',
829 'javelin\.io',
830 'Jbrofuzz',
831 'Jersey\/',
832 'JetCar',
833 'Jigsaw',
834 'Jobboerse',
835 'JobFeed discovery',
836 'Jobg8 URL Monitor',
837 'jobo',
838 'Jobrapido',
839 'Jobsearch1\.5',
840 'JoinVision Generic',
841 'JolokiaPwn',
842 'Joomla',
843 'Jorgee',
844 'JS-Kit',
845 'JungleKeyThumbnail',
846 'JustView',
847 'Kaspersky Lab CFR link resolver',
848 'Kelny\/',
849 'Kerrigan\/',
850 'KeyCDN',
851 'Keyword Density',
852 'Keywords Research',
853 'khttp\/',
854 'KickFire',
855 'KimonoLabs\/',
856 'Kml-Google',
857 'knows\.is',
858 'KOCMOHABT',
859 'kouio',
860 'krawler\.dk',
861 'kube-probe',
862 'kubectl',
863 'kulturarw3',
864 'KumKie',
865 'Larbin',
866 'Lavf\/',
867 'leakix\.net',
868 'LeechFTP',
869 'LeechGet',
870 'letsencrypt',
871 'Lftp',
872 'LibVLC',
873 'LibWeb',
874 'Libwhisker',
875 'libwww',
876 'Licorne',
877 'Liferea\/',
878 'Lighthouse',
879 'Lightspeedsystems',
880 'Likse',
881 'limber\.io',
882 'Link Valet',
883 'LinkAlarm\/',
884 'LinkAnalyser',
885 'link-check',
886 'linkCheck',
887 'linkdex',
888 'LinkExaminer',
889 'linkfluence',
890 'linkpeek',
891 'LinkPreview',
892 'LinkScan',
893 'LinksManager',
894 'LinkTiger',
895 'LinkWalker',
896 'link_thumbnailer',
897 'Lipperhey',
898 'Litemage_walker',
899 'livedoor ScreenShot',
900 'LoadImpactRload',
901 'localsearch-web',
902 'LongURL API',
903 'longurl-r-package',
904 'looid\.com',
905 'looksystems\.net',
906 'lscache_runner',
907 'ltx71',
908 'lua-resty-http',
909 'Lucee \(CFML Engine\)',
910 'Lush Http Client',
911 'lwp-request',
912 'lwp-trivial',
913 'LWP::Simple',
914 'lycos',
915 'LYT\.SR',
916 'L\.webis',
917 'mabontland',
918 'MacOutlook\/',
919 'MagentaNews\/',
920 'Mag-Net',
921 'MagpieRSS',
922 'Mail::STS',
923 'MailChimp',
924 'Mail\.Ru',
925 'Majestic12',
926 'makecontact\/',
927 'Mandrill',
928 'MapperCmd',
929 'marketinggrader',
930 'MarkMonitor',
931 'MarkWatch',
932 'Mass Downloader',
933 'masscan\/',
934 'Mata Hari',
935 'mattermost',
936 'MatchorySearch\/',
937 'Mediametric',
938 'Mediapartners-Google',
939 'mediawords',
940 'MegaIndex\.ru',
941 'MeltwaterNews',
942 'Melvil Rawi',
943 'MemGator',
944 'Metaspinner',
945 'MetaURI',
946 'MFC_Tear_Sample',
947 'Microsearch',
948 'Microsoft Data Access',
949 'Microsoft Office',
950 'Microsoft Outlook',
951 'Microsoft Windows Network Diagnostics',
952 'Microsoft-WebDAV-MiniRedir',
953 'Microsoft\.Data\.Mashup',
954 'MicrosoftPreview',
955 'MIDown tool',
956 'MIIxpc',
957 'Mindjet',
958 'Miniature\.io',
959 'Miniflux',
960 'mio_httpc',
961 'Miro-HttpClient',
962 'Mister PiX',
963 'mixdata dot com',
964 'mixed-content-scan',
965 'mixnode',
966 'Mnogosearch',
967 'mogimogi',
968 'Mojeek',
969 'Mojolicious \(Perl\)',
970 'Mollie',
971 'monitis',
972 'Monitority\/',
973 'Monit\/',
974 'montastic',
975 'MonSpark',
976 'MonTools',
977 'Moreover',
978 'Morfeus Fucking Scanner',
979 'Morning Paper',
980 'MovableType',
981 'mowser',
982 'Mrcgiguy',
983 'Mr\.4x3 Powered',
984 'MS Web Services Client Protocol',
985 'MSFrontPage',
986 'mShots',
987 'MuckRack\/',
988 'muhstik-scan',
989 'MVAClient',
990 'MxToolbox\/',
991 'myseosnapshot',
992 'nagios',
993 'Najdi\.si',
994 'Name Intelligence',
995 'NameFo\.com',
996 'Nameprotect',
997 'nationalarchives',
998 'Navroad',
999 'nbertaupete95',
1000 'NearSite',
1001 'Needle',
1002 'Nessus',
1003 'Net Vampire',
1004 'NetAnts',
1005 'NETCRAFT',
1006 'NetLyzer',
1007 'NetMechanic',
1008 'NetNewsWire',
1009 'Netpursual',
1010 'netresearch',
1011 'NetShelter ContentScan',
1012 'Netsparker',
1013 'NetSystemsResearch',
1014 'nettle',
1015 'NetTrack',
1016 'Netvibes',
1017 'NetZIP',
1018 'Neustar WPM',
1019 'NeutrinoAPI',
1020 'NewRelicPinger',
1021 'NewsBlur .*Finder',
1022 'NewsGator',
1023 'newsme',
1024 'newspaper\/',
1025 'Nexgate Ruby Client',
1026 'NG-Search',
1027 'nghttp2',
1028 'Nibbler',
1029 'NICErsPRO',
1030 'NihilScio',
1031 'Nikto',
1032 'nineconnections',
1033 'NLNZ_IAHarvester',
1034 'Nmap Scripting Engine',
1035 'node-fetch',
1036 'node-superagent',
1037 'node-urllib',
1038 'Nodemeter',
1039 'NodePing',
1040 'node\.io',
1041 'nominet\.org\.uk',
1042 'nominet\.uk',
1043 'Norton-Safeweb',
1044 'Notifixious',
1045 'notifyninja',
1046 'NotionEmbedder',
1047 'nuhk',
1048 'nutch',
1049 'Nuzzel',
1050 'nWormFeedFinder',
1051 'nyawc\/',
1052 'Nymesis',
1053 'NYU',
1054 'Observatory\/',
1055 'Ocelli\/',
1056 'Octopus',
1057 'oegp',
1058 'Offline Explorer',
1059 'Offline Navigator',
1060 'OgScrper',
1061 'okhttp',
1062 'omgili',
1063 'OMSC',
1064 'Online Domain Tools',
1065 'Open Source RSS',
1066 'OpenCalaisSemanticProxy',
1067 'Openfind',
1068 'OpenLinkProfiler',
1069 'Openstat\/',
1070 'OpenVAS',
1071 'OPPO A33',
1072 'Optimizer',
1073 'Orbiter',
1074 'OrgProbe\/',
1075 'orion-semantics',
1076 'Outlook-Express',
1077 'Outlook-iOS',
1078 'Owler',
1079 'Owlin',
1080 'ownCloud News',
1081 'ow\.ly',
1082 'OxfordCloudService',
1083 'page scorer',
1084 'Page Valet',
1085 'page2rss',
1086 'PageFreezer',
1087 'PageGrabber',
1088 'PagePeeker',
1089 'PageScorer',
1090 'Pagespeed\/',
1091 'PageThing',
1092 'page_verifier',
1093 'Panopta',
1094 'panscient',
1095 'Papa Foto',
1096 'parsijoo',
1097 'Pavuk',
1098 'PayPal IPN',
1099 'pcBrowser',
1100 'Pcore-HTTP',
1101 'PDF24 URL To PDF',
1102 'Pearltrees',
1103 'PECL::HTTP',
1104 'peerindex',
1105 'Peew',
1106 'PeoplePal',
1107 'Perlu -',
1108 'PhantomJS Screenshoter',
1109 'PhantomJS\/',
1110 'Photon\/',
1111 'php-requests',
1112 'phpservermon',
1113 'Pi-Monster',
1114 'Picscout',
1115 'Picsearch',
1116 'PictureFinder',
1117 'Pimonster',
1118 'Pingability',
1119 'PingAdmin\.Ru',
1120 'Pingdom',
1121 'Pingoscope',
1122 'PingSpot',
1123 'ping\.blo\.gs',
1124 'pinterest\.com',
1125 'Pixray',
1126 'Pizilla',
1127 'Plagger\/',
1128 'Pleroma ',
1129 'Ploetz \+ Zeller',
1130 'Plukkie',
1131 'plumanalytics',
1132 'PocketImageCache',
1133 'PocketParser',
1134 'Pockey',
1135 'PodcastAddict\/',
1136 'POE-Component-Client-HTTP',
1137 'Polymail\/',
1138 'Pompos',
1139 'Porkbun',
1140 'Port Monitor',
1141 'postano',
1142 'postfix-mta-sts-resolver',
1143 'PostmanRuntime',
1144 'postplanner\.com',
1145 'PostPost',
1146 'postrank',
1147 'PowerPoint\/',
1148 'Prebid',
1149 'Prerender',
1150 'Priceonomics Analysis Engine',
1151 'PrintFriendly',
1152 'PritTorrent',
1153 'Prlog',
1154 'probely\.com',
1155 'probethenet',
1156 'Project ?25499',
1157 'Project-Resonance',
1158 'prospectb2b',
1159 'Protopage',
1160 'ProWebWalker',
1161 'proximic',
1162 'PRTG Network Monitor',
1163 'pshtt, https scanning',
1164 'PTST ',
1165 'PTST\/[0-9]+',
1166 'pulsetic\.com',
1167 'Pump',
1168 'Python-httplib2',
1169 'python-httpx',
1170 'python-requests',
1171 'Python-urllib',
1172 'Qirina Hurdler',
1173 'QQDownload',
1174 'QrafterPro',
1175 'Qseero',
1176 'Qualidator',
1177 'QueryN Metasearch',
1178 'queuedriver',
1179 'quic-go-HTTP\/',
1180 'QuiteRSS',
1181 'Quora Link Preview',
1182 'Qwantify',
1183 'Radian6',
1184 'RadioPublicImageResizer',
1185 'Railgun\/',
1186 'RankActive',
1187 'RankFlex',
1188 'RankSonicSiteAuditor',
1189 'RapidLoad\/',
1190 'Re-re Studio',
1191 'ReactorNetty',
1192 'Readability',
1193 'RealDownload',
1194 'RealPlayer%20Downloader',
1195 'RebelMouse',
1196 'Recorder',
1197 'RecurPost\/',
1198 'redback\/',
1199 'ReederForMac',
1200 'Reeder\/',
1201 'ReGet',
1202 'RepoMonkey',
1203 'request\.js',
1204 'reqwest\/',
1205 'ResponseCodeTest',
1206 'RestSharp',
1207 'Riddler',
1208 'Rival IQ',
1209 'Robosourcer',
1210 'Robozilla',
1211 'ROI Hunter',
1212 'RPT-HTTPClient',
1213 'RSSMix\/',
1214 'RSSOwl',
1215 'RuxitSynthetic',
1216 'RyowlEngine',
1217 'safe-agent-scanner',
1218 'SalesIntelligent',
1219 'Saleslift',
1220 'SAP NetWeaver Application Server',
1221 'SauceNAO',
1222 'SBIder',
1223 'sc-downloader',
1224 'scalaj-http',
1225 'Scamadviser-Frontend',
1226 'ScanAlert',
1227 'scan\.lol',
1228 'Scoop',
1229 'scooter',
1230 'ScopeContentAG-HTTP-Client',
1231 'ScoutJet',
1232 'ScoutURLMonitor',
1233 'ScrapeBox Page Scanner',
1234 'Scrapy',
1235 'Screaming',
1236 'ScreenShotService',
1237 'Scrubby',
1238 'Scrutiny\/',
1239 'Search37',
1240 'searchenginepromotionhelp',
1241 'Searchestate',
1242 'SearchExpress',
1243 'SearchSight',
1244 'SearchWP',
1245 'search\.thunderstone',
1246 'Seeker',
1247 'semanticdiscovery',
1248 'semanticjuice',
1249 'Semiocast HTTP client',
1250 'Semrush',
1251 'Sendsay\.Ru',
1252 'sentry\/',
1253 'SEO Browser',
1254 'Seo Servis',
1255 'seo-nastroj\.cz',
1256 'seo4ajax',
1257 'Seobility',
1258 'SEOCentro',
1259 'SeoCheck',
1260 'seocompany',
1261 'SEOkicks',
1262 'SEOlizer',
1263 'Seomoz',
1264 'SEOprofiler',
1265 'seoscanners',
1266 'SEOsearch',
1267 'seositecheckup',
1268 'SEOstats',
1269 'servernfo',
1270 'sexsearcher',
1271 'Seznam',
1272 'Shelob',
1273 'Shodan',
1274 'Shoppimon',
1275 'ShopWiki',
1276 'ShortLinkTranslate',
1277 'shortURL lengthener',
1278 'shrinktheweb',
1279 'Sideqik',
1280 'Siege',
1281 'SimplePie',
1282 'SimplyFast',
1283 'Siphon',
1284 'SISTRIX',
1285 'Site Sucker',
1286 'Site-Shot\/',
1287 'Site24x7',
1288 'SiteBar',
1289 'Sitebeam',
1290 'Sitebulb\/',
1291 'SiteCondor',
1292 'SiteExplorer',
1293 'SiteGuardian',
1294 'Siteimprove',
1295 'SiteIndexed',
1296 'Sitemap(s)? Generator',
1297 'SitemapGenerator',
1298 'SiteMonitor',
1299 'Siteshooter B0t',
1300 'SiteSnagger',
1301 'SiteSucker',
1302 'SiteTruth',
1303 'Sitevigil',
1304 'sitexy\.com',
1305 'SkypeUriPreview',
1306 'Slack\/',
1307 'sli-systems\.com',
1308 'slider\.com',
1309 'slurp',
1310 'SlySearch',
1311 'SmartDownload',
1312 'SMRF URL Expander',
1313 'SMUrlExpander',
1314 'Snake',
1315 'Snappy',
1316 'SnapSearch',
1317 'Snarfer\/',
1318 'SniffRSS',
1319 'sniptracker',
1320 'Snoopy',
1321 'SnowHaze Search',
1322 'sogou web',
1323 'SortSite',
1324 'Sottopop',
1325 'sovereign\.ai',
1326 'SpaceBison',
1327 'SpamExperts',
1328 'Spammen',
1329 'Spanner',
1330 'Spawning-AI',
1331 'spaziodati',
1332 'SPDYCheck',
1333 'Specificfeeds',
1334 'SpeedKit',
1335 'speedy',
1336 'SPEng',
1337 'Spinn3r',
1338 'spray-can',
1339 'Sprinklr ',
1340 'spyonweb',
1341 'sqlmap',
1342 'Sqlworm',
1343 'Sqworm',
1344 'SSL Labs',
1345 'ssl-tools',
1346 'StackRambler',
1347 'Statastico\/',
1348 'Statically-',
1349 'StatusCake',
1350 'Steeler',
1351 'Stratagems Kumo',
1352 'Stripe\/',
1353 'Stroke\.cz',
1354 'StudioFACA',
1355 'StumbleUpon',
1356 'suchen',
1357 'Sucuri',
1358 'summify',
1359 'SuperHTTP',
1360 'Surphace Scout',
1361 'Suzuran',
1362 'swcd ',
1363 'Symfony BrowserKit',
1364 'Symfony2 BrowserKit',
1365 'Synapse\/',
1366 'Syndirella\/',
1367 'SynHttpClient-Built',
1368 'Sysomos',
1369 'sysscan',
1370 'Szukacz',
1371 'T0PHackTeam',
1372 'tAkeOut',
1373 'Tarantula\/',
1374 'Taringa UGC',
1375 'TarmotGezgin',
1376 'tchelebi\.io',
1377 'techiaith\.cymru',
1378 'Teleport',
1379 'Telesoft',
1380 'Telesphoreo',
1381 'Telesphorep',
1382 'Tenon\.io',
1383 'teoma',
1384 'terrainformatica',
1385 'Test Certificate Info',
1386 'testuri',
1387 'Tetrahedron',
1388 'TextRazor Downloader',
1389 'The Drop Reaper',
1390 'The Expert HTML Source Viewer',
1391 'The Intraformant',
1392 'The Knowledge AI',
1393 'theinternetrules',
1394 'TheNomad',
1395 'Thinklab',
1396 'Thumbor',
1397 'Thumbshots',
1398 'ThumbSniper',
1399 'timewe\.net',
1400 'TinEye',
1401 'Tiny Tiny RSS',
1402 'TLSProbe\/',
1403 'Toata',
1404 'topster',
1405 'touche\.com',
1406 'Traackr\.com',
1407 'tracemyfile',
1408 'Trackuity',
1409 'TrapitAgent',
1410 'Trendiction',
1411 'Trendsmap',
1412 'trendspottr',
1413 'truwoGPS',
1414 'TryJsoup',
1415 'TulipChain',
1416 'Turingos',
1417 'Turnitin',
1418 'tweetedtimes',
1419 'Tweetminster',
1420 'Tweezler\/',
1421 'twibble',
1422 'Twice',
1423 'Twikle',
1424 'Twingly',
1425 'Twisted PageGetter',
1426 'Typhoeus',
1427 'ubermetrics-technologies',
1428 'uclassify',
1429 'UdmSearch',
1430 'ultimate_sitemap_parser',
1431 'unchaos',
1432 'unirest-java',
1433 'UniversalFeedParser',
1434 'unshortenit',
1435 'Unshorten\.It',
1436 'Untiny',
1437 'UnwindFetchor',
1438 'updated',
1439 'updown\.io daemon',
1440 'Upflow',
1441 'Uptimia',
1442 'URL Verifier',
1443 'Urlcheckr',
1444 'URLitor',
1445 'urlresolver',
1446 'Urlstat',
1447 'URLTester',
1448 'UrlTrends Ranking Updater',
1449 'URLy Warning',
1450 'URLy\.Warning',
1451 'URL\/Emacs',
1452 'Vacuum',
1453 'Vagabondo',
1454 'VB Project',
1455 'vBSEO',
1456 'VCI',
1457 'Verity',
1458 'via ggpht\.com GoogleImageProxy',
1459 'Virusdie',
1460 'visionutils',
1461 'Visual Rights Group',
1462 'vkShare',
1463 'VoidEYE',
1464 'Voil',
1465 'voltron',
1466 'voyager\/',
1467 'VSAgent\/',
1468 'VSB-TUO\/',
1469 'Vulnbusters Meter',
1470 'VYU2',
1471 'w3af\.org',
1472 'W3C-checklink',
1473 'W3C-mobileOK',
1474 'W3C_Unicorn',
1475 'WAC-OFU',
1476 'WakeletLinkExpander',
1477 'WallpapersHD',
1478 'Wallpapers\/[0-9]+',
1479 'wangling',
1480 'Wappalyzer',
1481 'WatchMouse',
1482 'WbSrch\/',
1483 'WDT\.io',
1484 'Web Auto',
1485 'Web Collage',
1486 'Web Enhancer',
1487 'Web Fetch',
1488 'Web Fuck',
1489 'Web Pix',
1490 'Web Sauger',
1491 'Web spyder',
1492 'Web Sucker',
1493 'web-capture\.net',
1494 'Web-sniffer',
1495 'Webalta',
1496 'Webauskunft',
1497 'WebAuto',
1498 'WebCapture',
1499 'WebClient\/',
1500 'webcollage',
1501 'WebCookies',
1502 'WebCopier',
1503 'WebCorp',
1504 'WebDataStats',
1505 'WebDoc',
1506 'WebEnhancer',
1507 'WebFetch',
1508 'WebFuck',
1509 'WebGazer',
1510 'WebGo IS',
1511 'WebImageCollector',
1512 'WebImages',
1513 'WebIndex',
1514 'webkit2png',
1515 'WebLeacher',
1516 'webmastercoffee',
1517 'webmon ',
1518 'WebPix',
1519 'WebReaper',
1520 'WebSauger',
1521 'webscreenie',
1522 'Webshag',
1523 'Webshot',
1524 'Website Quester',
1525 'websitepulse agent',
1526 'WebsiteQuester',
1527 'Websnapr',
1528 'WebSniffer',
1529 'Webster',
1530 'WebStripper',
1531 'WebSucker',
1532 'webtech\/',
1533 'WebThumbnail',
1534 'Webthumb\/',
1535 'WebWhacker',
1536 'WebZIP',
1537 'WeLikeLinks',
1538 'WEPA',
1539 'WeSEE',
1540 'wf84',
1541 'Wfuzz\/',
1542 'wget',
1543 'WhatCMS',
1544 'WhatsApp',
1545 'WhatsMyIP',
1546 'WhatWeb',
1547 'WhereGoes\?',
1548 'Whibse',
1549 'WhoAPI\/',
1550 'WhoRunsCoinHive',
1551 'Whynder Magnet',
1552 'Windows-RSS-Platform',
1553 'WinHttp-Autoproxy-Service',
1554 'WinHTTP\/',
1555 'WinPodder',
1556 'wkhtmlto',
1557 'wmtips',
1558 'Woko',
1559 'Wolfram HTTPClient',
1560 'woorankreview',
1561 'WordPress\/',
1562 'WordupinfoSearch',
1563 'Word\/',
1564 'worldping-api',
1565 'wotbox',
1566 'WP Engine Install Performance API',
1567 'wpif',
1568 'wprecon\.com survey',
1569 'WPScan',
1570 'wscheck',
1571 'Wtrace',
1572 'WWW-Collector-E',
1573 'WWW-Mechanize',
1574 'WWW::Document',
1575 'WWW::Mechanize',
1576 'WWWOFFLE',
1577 'www\.monitor\.us',
1578 'x09Mozilla',
1579 'x22Mozilla',
1580 'XaxisSemanticsClassifier',
1581 'XenForo\/',
1582 'Xenu Link Sleuth',
1583 'XING-contenttabreceiver',
1584 'xpymep([0-9]?)\.exe',
1585 'Y!J-[A-Z][A-Z][A-Z]',
1586 'Yaanb',
1587 'yacy',
1588 'Yahoo Link Preview',
1589 'YahooCacheSystem',
1590 'YahooMailProxy',
1591 'YahooYSMcm',
1592 'YandeG',
1593 'Yandex(?!Search)',
1594 'yanga',
1595 'yeti',
1596 'Yo-yo',
1597 'Yoleo Consumer',
1598 'yomins\.com',
1599 'yoogliFetchAgent',
1600 'YottaaMonitor',
1601 'Your-Website-Sucks',
1602 'yourls\.org',
1603 'YoYs\.net',
1604 'YP\.PL',
1605 'Zabbix',
1606 'Zade',
1607 'Zao',
1608 'Zapier',
1609 'Zauba',
1610 'Zemanta Aggregator',
1611 'Zend\\\\Http\\\\Client',
1612 'Zend_Http_Client',
1613 'Zermelo',
1614 'Zeus ',
1615 'zgrab',
1616 'ZnajdzFoto',
1617 'ZnHTTP',
1618 'Zombie\.js',
1619 'Zoom\.Mac',
1620 'ZoteroTranslationServer',
1621 'ZyBorg',
1622 '[a-z0-9\-_]*(bot|crawl|headless|archiver|transcoder|spider|uptime|validator|fetcher|cron|checker|reader|extractor|monitoring|analyzer|scraper)'
1623 ];
1624 }
1625
1626 /**
1627 * Return the list of strings to remove from the user agent before running the crawler regex.
1628 *
1629 * @return array
1630 */
1631 public function get_exclusions_list() {
1632 return [
1633 'Safari.[\d\.]*',
1634 'Firefox.[\d\.]*',
1635 ' Chrome.[\d\.]*',
1636 'Chromium.[\d\.]*',
1637 'MSIE.[\d\.]',
1638 'Opera\/[\d\.]*',
1639 'Mozilla.[\d\.]*',
1640 'AppleWebKit.[\d\.]*',
1641 'Trident.[\d\.]*',
1642 'Windows NT.[\d\.]*',
1643 'Android [\d\.]*',
1644 'Macintosh.',
1645 'Ubuntu',
1646 'Linux',
1647 '[ ]Intel',
1648 'Mac OS X [\d_]*',
1649 '(like )?Gecko(.[\d\.]*)?',
1650 'KHTML,',
1651 'CriOS.[\d\.]*',
1652 'CPU iPhone OS ([0-9_])* like Mac OS X',
1653 'CPU OS ([0-9_])* like Mac OS X',
1654 'iPod',
1655 'compatible',
1656 'x86_..',
1657 'i686',
1658 'x64',
1659 'X11',
1660 'rv:[\d\.]*',
1661 'Version.[\d\.]*',
1662 'WOW64',
1663 'Win64',
1664 'Dalvik.[\d\.]*',
1665 ' \.NET CLR [\d\.]*',
1666 'Presto.[\d\.]*',
1667 'Media Center PC',
1668 'BlackBerry',
1669 'Build',
1670 'Opera Mini\/\d{1,2}\.\d{1,2}\.[\d\.]*\/\d{1,2}\.',
1671 'Opera',
1672 ' \.NET[\d\.]*',
1673 'cubot',
1674 '; M bot',
1675 '; CRONO',
1676 '; B bot',
1677 '; IDbot',
1678 '; ID bot',
1679 '; POWER BOT',
1680 'OCTOPUS-CORE',
1681 'htc_botdugls',
1682 'super\/\d+\/Android\/\d+',
1683 '"Yandex"',
1684 'YandexModule2'
1685 ];
1686 }
1687
1688 /**
1689 * Return all possible HTTP headers that represent the User-Agent string.
1690 *
1691 * @return array
1692 */
1693 public function get_headers_list() {
1694 return [
1695 // The default User-Agent string.
1696 'HTTP_USER_AGENT',
1697 // Header can occur on devices using Opera Mini.
1698 'HTTP_X_OPERAMINI_PHONE_UA',
1699 // Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/
1700 'HTTP_X_DEVICE_USER_AGENT',
1701 'HTTP_X_ORIGINAL_USER_AGENT',
1702 'HTTP_X_SKYFIRE_PHONE',
1703 'HTTP_X_BOLT_PHONE_UA',
1704 'HTTP_DEVICE_STOCK_UA',
1705 'HTTP_X_UCBROWSER_DEVICE_UA',
1706 // Sometimes, bots (especially Google) use a genuine user agent, but fill this header in with their email address
1707 'HTTP_FROM',
1708 'HTTP_X_SCANNER', // Seen in use by Netsparker
1709 // Observed that Facebook will omit identifying itself in User Agent headers but will persist HeadlessChrome in this header for mobile requests
1710 'HTTP_SEC_CH_UA'
1711 ];
1712 }
1713 }
1714