PluginProbe ʕ •ᴥ•ʔ
Post Views Counter / 1.4.5
Post Views Counter v1.4.5
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 2 years ago class-columns.php 2 years ago class-counter.php 2 years ago class-crawler-detect.php 2 years ago class-cron.php 2 years ago class-dashboard.php 2 years ago class-frontend.php 2 years ago class-functions.php 2 years ago class-query.php 2 years ago class-settings-api.php 2 years ago class-settings.php 2 years ago class-update.php 2 years ago class-widgets.php 2 years ago functions.php 2 years ago
class-crawler-detect.php
1687 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 * @class Post_Views_Counter_Crawler_Detect
14 */
15 class Post_Views_Counter_Crawler_Detect {
16
17 /**
18 * The user agent.
19 *
20 * @var null
21 */
22 protected $user_agent = null;
23
24 /**
25 * Headers that contain a user agent.
26 *
27 * @var array
28 */
29 protected $http_headers = [];
30
31 /**
32 * Store regex matches.
33 *
34 * @var array
35 */
36 protected $matches = [];
37
38 /**
39 * Crawlers object.
40 *
41 * @var object
42 */
43 protected $crawlers = [];
44
45 /**
46 * Exclusions object.
47 *
48 * @var object
49 */
50 protected $exclusions = [];
51
52 /**
53 * Headers object.
54 *
55 * @var object
56 */
57 protected $ua_http_headers;
58
59 /**
60 * Class constructor.
61 *
62 * @return void
63 */
64 public function __construct() {
65 $this->crawlers = $this->get_crawlers_list();
66 $this->exclusions = $this->get_exclusions_list();
67
68 add_action( 'after_setup_theme', [ $this, 'init' ] );
69 }
70
71 /**
72 * Initialize class.
73 *
74 * @return void
75 */
76 public function init() {
77 // break on admin side
78 if ( is_admin() && ! wp_doing_ajax() )
79 return;
80
81 $this->ua_http_headers = $this->get_headers_list();
82 $this->set_http_headers();
83 $this->set_user_agent();
84 }
85
86 /**
87 * Set HTTP headers.
88 *
89 * @param array $http_headers
90 * @return void
91 */
92 public function set_http_headers( $http_headers = null ) {
93 // use global _SERVER if $http_headers aren't defined
94 if ( ! is_array( $http_headers ) || ! count( $http_headers ) )
95 $http_headers = $_SERVER;
96
97 // clear existing headers
98 $this->http_headers = [];
99
100 // only save HTTP headers - in PHP land, that means only _SERVER vars that start with HTTP_.
101 foreach ( $http_headers as $key => $value ) {
102 if ( substr( $key, 0, 5 ) === 'HTTP_' )
103 $this->http_headers[$key] = $value;
104 }
105 }
106
107 /**
108 * Return user agent headers.
109 *
110 * @return array
111 */
112 public function get_ua_http_headers() {
113 return $this->ua_http_headers;
114 }
115
116 /**
117 * Return the user agent.
118 *
119 * @return string
120 */
121 public function get_user_agent() {
122 return $this->user_agent;
123 }
124
125 /**
126 * Set the user agent.
127 *
128 * @param string $user_agent
129 * @return string
130 */
131 public function set_user_agent( $user_agent = null ) {
132 if ( false === empty( $user_agent ) )
133 return $this->user_agent = $user_agent;
134 else {
135 $this->user_agent = null;
136
137 foreach ( $this->get_ua_http_headers() as $alt_header ) {
138 if ( false === empty( $this->http_headers[$alt_header] ) ) // @todo: should use get_http_header(), but it would be slow.
139 $this->user_agent .= $this->http_headers[$alt_header] . ' ';
140 }
141
142 return $this->user_agent = ( ! empty( $this->user_agent ) ? trim( $this->user_agent ) : null );
143 }
144 }
145
146 /**
147 * Build the user agent regex.
148 *
149 * @return string
150 */
151 public function get_regex() {
152 return '(' . implode( '|', $this->crawlers ) . ')';
153 }
154
155 /**
156 * Build the replacement regex.
157 *
158 * @return string
159 */
160 public function get_exclusions() {
161 return '(' . implode( '|', $this->exclusions ) . ')';
162 }
163
164 /**
165 * Check user agent string against the regex.
166 *
167 * @param string $user_agent
168 * @return bool
169 */
170 public function is_crawler( $user_agent = null ) {
171 $agent = (string)( is_null( $user_agent ) ? $this->user_agent : $user_agent );
172 $agent = preg_replace( '/' . $this->get_exclusions() . '/i', '', $agent );
173
174 if ( strlen( trim( $agent ) ) === 0 )
175 return false;
176 else
177 $result = preg_match( '/' . $this->get_regex() . '/i', trim( $agent ), $matches );
178
179 if ( $matches )
180 $this->matches = $matches;
181
182 return (bool) $result;
183 }
184
185 /**
186 * Return the matches.
187 *
188 * @return string
189 */
190 public function get_matches() {
191 return isset( $this->matches[0] ) ? $this->matches[0] : null;
192 }
193
194 /**
195 * Return the regular expressions to match against the user agent.
196 *
197 * @return array
198 */
199 protected function get_crawlers_list() {
200 return [
201 ' YLT',
202 '^Aether',
203 '^Amazon Simple Notification Service Agent$',
204 '^Amazon-Route53-Health-Check-Service',
205 '^Amazon CloudFront',
206 '^b0t$',
207 '^bluefish ',
208 '^Calypso v\/',
209 '^COMODO DCV',
210 '^Corax',
211 '^DangDang',
212 '^DavClnt',
213 '^DHSH',
214 '^docker\/[0-9]',
215 '^Expanse',
216 '^FDM ',
217 '^git\/',
218 '^Goose\/',
219 '^Grabber',
220 '^Gradle\/',
221 '^HTTPClient\/',
222 '^HTTPing',
223 '^Java\/',
224 '^Jeode\/',
225 '^Jetty\/',
226 '^Mail\/',
227 '^Mget',
228 '^Microsoft URL Control',
229 '^Mikrotik\/',
230 '^Netlab360',
231 '^NG\/[0-9\.]',
232 '^NING\/',
233 '^npm\/',
234 '^Nuclei',
235 '^PHP-AYMAPI\/',
236 '^PHP\/',
237 '^pip\/',
238 '^pnpm\/',
239 '^RMA\/',
240 '^Ruby|Ruby\/[0-9]',
241 '^Swurl ',
242 '^TLS tester ',
243 '^twine\/',
244 '^ureq',
245 '^VSE\/[0-9]',
246 '^WordPress\.com',
247 '^XRL\/[0-9]',
248 '^ZmEu',
249 '008\/',
250 '13TABS',
251 '192\.comAgent',
252 '2GDPR\/',
253 '2ip\.ru',
254 '404enemy',
255 '7Siters',
256 '80legs',
257 'a3logics\.in',
258 'A6-Indexer',
259 'Abonti',
260 'Aboundex',
261 'aboutthedomain',
262 'Accoona-AI-Agent',
263 'acebookexternalhit\/',
264 'acoon',
265 'acrylicapps\.com\/pulp',
266 'Acunetix',
267 'AdAuth\/',
268 'adbeat',
269 'AddThis',
270 'ADmantX',
271 'AdminLabs',
272 'adressendeutschland',
273 'adreview\/',
274 'adscanner',
275 'adstxt-worker',
276 'Adstxtaggregator',
277 'adstxt\.com',
278 'Adyen HttpClient',
279 'AffiliateLabz\/',
280 'affilimate-puppeteer',
281 'agentslug',
282 'AHC',
283 'aihit',
284 'aiohttp\/',
285 'Airmail',
286 'akka-http\/',
287 'akula\/',
288 'alertra',
289 'alexa site audit',
290 'Alibaba\.Security\.Heimdall',
291 'Alligator',
292 'allloadin',
293 'AllSubmitter',
294 'alyze\.info',
295 'amagit',
296 'Anarchie',
297 'AndroidDownloadManager',
298 'Anemone',
299 'AngleSharp',
300 'annotate_google',
301 'Anthill',
302 'Anturis Agent',
303 'Ant\.com',
304 'AnyEvent-HTTP\/',
305 'Apache Ant\/',
306 'Apache Droid',
307 'Apache OpenOffice',
308 'Apache-HttpAsyncClient',
309 'Apache-HttpClient',
310 'ApacheBench',
311 'Apexoo',
312 'apimon\.de',
313 'APIs-Google',
314 'AportWorm\/',
315 'AppBeat\/',
316 'AppEngine-Google',
317 'AppleSyndication',
318 'Aprc\/[0-9]',
319 'Arachmo',
320 'arachnode',
321 'Arachnophilia',
322 'aria2',
323 'Arukereso',
324 'asafaweb',
325 'Asana\/',
326 'Ask Jeeves',
327 'AskQuickly',
328 'ASPSeek',
329 'Asterias',
330 'Astute',
331 'asynchttp',
332 'Attach',
333 'attohttpc',
334 'autocite',
335 'AutomaticWPTester',
336 'Autonomy',
337 'awin\.com',
338 'AWS Security Scanner',
339 'axios\/',
340 'a\.pr-cy\.ru',
341 'B-l-i-t-z-B-O-T',
342 'Backlink-Ceck',
343 'BacklinkHttpStatus',
344 'BackStreet',
345 'BackupLand',
346 'BackWeb',
347 'Bad-Neighborhood',
348 'Badass',
349 'baidu\.com',
350 'Bandit',
351 'basicstate',
352 'BatchFTP',
353 'Battleztar Bazinga',
354 'baypup\/',
355 'BazQux',
356 'BBBike',
357 'BCKLINKS',
358 'BDFetch',
359 'BegunAdvertising',
360 'Bewica-security-scan',
361 'Bidtellect',
362 'BigBozz',
363 'Bigfoot',
364 'biglotron',
365 'BingLocalSearch',
366 'BingPreview',
367 'binlar',
368 'biNu image cacher',
369 'Bitacle',
370 'Bitrix link preview',
371 'biz_Directory',
372 'BKCTwitterUnshortener\/',
373 'Black Hole',
374 'Blackboard Safeassign',
375 'BlackWidow',
376 'BlockNote\.Net',
377 'BlogBridge',
378 'Bloglines',
379 'Bloglovin',
380 'BlogPulseLive',
381 'BlogSearch',
382 'Blogtrottr',
383 'BlowFish',
384 'boitho\.com-dc',
385 'Boost\.Beast',
386 'BPImageWalker',
387 'Braintree-Webhooks',
388 'Branch Metrics API',
389 'Branch-Passthrough',
390 'Brandprotect',
391 'BrandVerity',
392 'Brandwatch',
393 'Brodie\/',
394 'Browsershots',
395 'BUbiNG',
396 'Buck\/',
397 'Buddy',
398 'BuiltWith',
399 'Bullseye',
400 'BunnySlippers',
401 'Burf Search',
402 'Butterfly\/',
403 'BuzzSumo',
404 'CAAM\/[0-9]',
405 'CakePHP',
406 'Calculon',
407 'Canary%20Mail',
408 'CaretNail',
409 'catexplorador',
410 'CC Metadata Scaper',
411 'Cegbfeieh',
412 'censys',
413 'centuryb.o.t9[at]gmail.com',
414 'Cerberian Drtrs',
415 'CERT\.at-Statistics-Survey',
416 'cf-facebook',
417 'cg-eye',
418 'changedetection',
419 'ChangesMeter',
420 'Charlotte',
421 'chatterino-api-cache',
422 'CheckHost',
423 'checkprivacy',
424 'CherryPicker',
425 'ChinaClaw',
426 'Chirp\/',
427 'chkme\.com',
428 'Chlooe',
429 'Chromaxa',
430 'CirrusExplorer',
431 'CISPA Vulnerability Notification',
432 'CISPA Web Analyser',
433 'Citoid',
434 'CJNetworkQuality',
435 'Clarsentia',
436 'clips\.ua\.ac\.be',
437 'Cloud mapping',
438 'CloudEndure',
439 'CloudFlare-AlwaysOnline',
440 'Cloudflare-Healthchecks',
441 'Cloudinary',
442 'cmcm\.com',
443 'coccoc',
444 'cognitiveseo',
445 'ColdFusion',
446 'colly -',
447 'CommaFeed',
448 'Commons-HttpClient',
449 'commonscan',
450 'contactbigdatafr',
451 'contentkingapp',
452 'Contextual Code Sites Explorer',
453 'convera',
454 'CookieReports',
455 'copyright sheriff',
456 'CopyRightCheck',
457 'Copyscape',
458 'cortex\/',
459 'Cosmos4j\.feedback',
460 'Covario-IDS',
461 'Craw\/',
462 'Crescent',
463 'Criteo',
464 'Crowsnest',
465 'CSHttp',
466 'CSSCheck',
467 'Cula\/',
468 'curb',
469 'Curious George',
470 'curl',
471 'cuwhois\/',
472 'cybo\.com',
473 'DAP\/NetHTTP',
474 'DareBoost',
475 'DatabaseDriverMysqli',
476 'DataCha0s',
477 'DatadogSynthetics',
478 'Datafeedwatch',
479 'Datanyze',
480 'DataparkSearch',
481 'dataprovider',
482 'DataXu',
483 'Daum(oa)?[ \/][0-9]',
484 'dBpoweramp',
485 'ddline',
486 'deeris',
487 'delve\.ai',
488 'Demon',
489 'DeuSu',
490 'developers\.google\.com\/\+\/web\/snippet\/',
491 'Devil',
492 'Digg',
493 'Digincore',
494 'DigitalPebble',
495 'Dirbuster',
496 'Discourse Forum Onebox',
497 'Dispatch\/',
498 'Disqus\/',
499 'DittoSpyder',
500 'dlvr',
501 'DMBrowser',
502 'DNSPod-reporting',
503 'docoloc',
504 'Dolphin http client',
505 'DomainAppender',
506 'DomainLabz',
507 'Domains Project\/',
508 'Donuts Content Explorer',
509 'dotMailer content retrieval',
510 'dotSemantic',
511 'downforeveryoneorjustme',
512 'Download Wonder',
513 'downnotifier',
514 'DowntimeDetector',
515 'Drip',
516 'drupact',
517 'Drupal \(\+http:\/\/drupal\.org\/\)',
518 'DTS Agent',
519 'dubaiindex',
520 'DuplexWeb-Google',
521 'DynatraceSynthetic',
522 'EARTHCOM',
523 'Easy-Thumb',
524 'EasyDL',
525 'Ebingbong',
526 'ec2linkfinder',
527 'eCairn-Grabber',
528 'eCatch',
529 'ECCP',
530 'eContext\/',
531 'Ecxi',
532 'EirGrabber',
533 'ElectricMonk',
534 'elefent',
535 'EMail Exractor',
536 'EMail Wolf',
537 'EmailWolf',
538 'Embarcadero',
539 'Embed PHP Library',
540 'Embedly',
541 'endo\/',
542 'europarchive\.org',
543 'evc-batch',
544 'EventMachine HttpClient',
545 'Everwall Link Expander',
546 'Evidon',
547 'Evrinid',
548 'ExactSearch',
549 'ExaleadCloudview',
550 'Excel\/',
551 'exif',
552 'ExoRank',
553 'Exploratodo',
554 'Express WebPictures',
555 'Extreme Picture Finder',
556 'EyeNetIE',
557 'ezooms',
558 'facebookexternalhit',
559 'facebookexternalua',
560 'facebookplatform',
561 'fairshare',
562 'Faraday v',
563 'fasthttp',
564 'Faveeo',
565 'Favicon downloader',
566 'faviconarchive',
567 'faviconkit',
568 'FavOrg',
569 'Feed Wrangler',
570 'Feedable\/',
571 'Feedbin',
572 'FeedBooster',
573 'FeedBucket',
574 'FeedBunch\/',
575 'FeedBurner',
576 'feeder',
577 'Feedly',
578 'FeedshowOnline',
579 'Feedshow\/',
580 'Feedspot',
581 'FeedViewer\/',
582 'Feedwind\/',
583 'FeedZcollector',
584 'feeltiptop',
585 'Fetch API',
586 'Fetch\/[0-9]',
587 'Fever\/[0-9]',
588 'FHscan',
589 'Fiery%20Feeds',
590 'Filestack',
591 'Fimap',
592 'findlink',
593 'findthatfile',
594 'FlashGet',
595 'FlipboardBrowserProxy',
596 'FlipboardProxy',
597 'FlipboardRSS',
598 'Flock\/',
599 'Florienzh\/',
600 'fluffy',
601 'Flunky',
602 'flynxapp',
603 'forensiq',
604 'ForusP',
605 'FoundSeoTool',
606 'fragFINN\.de',
607 'free thumbnails',
608 'Freeuploader',
609 'FreshRSS',
610 'frontman',
611 'Funnelback',
612 'Fuzz Faster U Fool',
613 'G-i-g-a-b-o-t',
614 'g00g1e\.net',
615 'ganarvisitas',
616 'gdnplus\.com',
617 'geek-tools',
618 'Genieo',
619 'GentleSource',
620 'GetCode',
621 'Getintent',
622 'GetLinkInfo',
623 'getprismatic',
624 'GetRight',
625 'getroot',
626 'GetURLInfo\/',
627 'GetWeb',
628 'Geziyor',
629 'Ghost Inspector',
630 'GigablastOpenSource',
631 'GIS-LABS',
632 'github-camo',
633 'GitHub-Hookshot',
634 'github\.com',
635 'Go http package',
636 'Go [\d\.]* package http',
637 'Go!Zilla',
638 'Go-Ahead-Got-It',
639 'Go-http-client',
640 'go-mtasts\/',
641 'gobuster',
642 'gobyus',
643 'Gofeed',
644 'gofetch',
645 'Goldfire Server',
646 'GomezAgent',
647 'gooblog',
648 'Goodzer\/',
649 'Google AppsViewer',
650 'Google Desktop',
651 'Google favicon',
652 'Google Keyword Suggestion',
653 'Google Keyword Tool',
654 'Google Page Speed Insights',
655 'Google PP Default',
656 'Google Search Console',
657 'Google Web Preview',
658 'Google-Ads',
659 'Google-Adwords',
660 'Google-Apps-Script',
661 'Google-Calendar-Importer',
662 'Google-HotelAdsVerifier',
663 'Google-HTTP-Java-Client',
664 'Google-InspectionTool',
665 'Google-Podcast',
666 'Google-Publisher-Plugin',
667 'Google-Read-Aloud',
668 'Google-SearchByImage',
669 'Google-Site-Verification',
670 'Google-SMTP-STS',
671 'Google-speakr',
672 'Google-Structured-Data-Testing-Tool',
673 'Google-Transparency-Report',
674 'google-xrawler',
675 'Google-Youtube-Links',
676 'GoogleDocs',
677 'GoogleHC\/',
678 'GoogleProber',
679 'GoogleProducer',
680 'GoogleSites',
681 'Gookey',
682 'GoSpotCheck',
683 'gosquared-thumbnailer',
684 'Gotit',
685 'GoZilla',
686 'grabify',
687 'GrabNet',
688 'Grafula',
689 'Grammarly',
690 'GrapeFX',
691 'GreatNews',
692 'Gregarius',
693 'GRequests',
694 'grokkit',
695 'grouphigh',
696 'grub-client',
697 'gSOAP\/',
698 'GT::WWW',
699 'GTmetrix',
700 'GuzzleHttp',
701 'gvfs\/',
702 'HAA(A)?RTLAND http client',
703 'Haansoft',
704 'hackney\/',
705 'Hadi Agent',
706 'HappyApps-WebCheck',
707 'Hardenize',
708 'Hatena',
709 'Havij',
710 'HaxerMen',
711 'HeadlessChrome',
712 'HEADMasterSEO',
713 'HeartRails_Capture',
714 'help@dataminr\.com',
715 'heritrix',
716 'Hexometer',
717 'historious',
718 'hkedcity',
719 'hledejLevne\.cz',
720 'Hloader',
721 'HMView',
722 'Holmes',
723 'HonesoSearchEngine',
724 'HootSuite Image proxy',
725 'Hootsuite-WebFeed',
726 'hosterstats',
727 'HostTracker',
728 'ht:\/\/check',
729 'htdig',
730 'HTMLparser',
731 'htmlyse',
732 'HTTP Banner Detection',
733 'http-get',
734 'HTTP-Header-Abfrage',
735 'http-kit',
736 'http-request\/',
737 'HTTP-Tiny',
738 'HTTP::Lite',
739 'http:\/\/www.neomo.de\/', //'Francis [Bot]'
740 'HttpComponents',
741 'httphr',
742 'HTTPie',
743 'HTTPMon',
744 'httpRequest',
745 'httpscheck',
746 'httpssites_power',
747 'httpunit',
748 'HttpUrlConnection',
749 'http\.rb\/',
750 'HTTP_Compression_Test',
751 'http_get',
752 'http_request2',
753 'http_requester',
754 'httrack',
755 'huaweisymantec',
756 'HubSpot ',
757 'HubSpot-Link-Resolver',
758 'Humanlinks',
759 'i2kconnect\/',
760 'Iblog',
761 'ichiro',
762 'Id-search',
763 'IdeelaborPlagiaat',
764 'IDG Twitter Links Resolver',
765 'IDwhois\/',
766 'Iframely',
767 'igdeSpyder',
768 'iGooglePortal',
769 'IlTrovatore',
770 'Image Fetch',
771 'Image Sucker',
772 'ImageEngine\/',
773 'ImageVisu\/',
774 'Imagga',
775 'imagineeasy',
776 'imgsizer',
777 'InAGist',
778 'inbound\.li parser',
779 'InDesign%20CC',
780 'Indy Library',
781 'InetURL',
782 'infegy',
783 'infohelfer',
784 'InfoTekies',
785 'InfoWizards Reciprocal Link',
786 'inpwrd\.com',
787 'instabid',
788 'Instapaper',
789 'Integrity',
790 'integromedb',
791 'Intelliseek',
792 'InterGET',
793 'Internet Ninja',
794 'InternetSeer',
795 'internetVista monitor',
796 'internetwache',
797 'internet_archive',
798 'intraVnews',
799 'IODC',
800 'IOI',
801 'Inboxb0t',
802 'iplabel',
803 'ips-agent',
804 'IPS\/[0-9]',
805 'IPWorks HTTP\/S Component',
806 'iqdb\/',
807 'Iria',
808 'Irokez',
809 'isitup\.org',
810 'iskanie',
811 'isUp\.li',
812 'iThemes Sync\/',
813 'IZaBEE',
814 'iZSearch',
815 'JAHHO',
816 'janforman',
817 'Jaunt\/',
818 'Java.*outbrain',
819 'javelin\.io',
820 'Jbrofuzz',
821 'Jersey\/',
822 'JetCar',
823 'Jigsaw',
824 'Jobboerse',
825 'JobFeed discovery',
826 'Jobg8 URL Monitor',
827 'jobo',
828 'Jobrapido',
829 'Jobsearch1\.5',
830 'JoinVision Generic',
831 'JolokiaPwn',
832 'Joomla',
833 'Jorgee',
834 'JS-Kit',
835 'JungleKeyThumbnail',
836 'JustView',
837 'Kaspersky Lab CFR link resolver',
838 'Kelny\/',
839 'Kerrigan\/',
840 'KeyCDN',
841 'Keyword Density',
842 'Keywords Research',
843 'khttp\/',
844 'KickFire',
845 'KimonoLabs\/',
846 'Kml-Google',
847 'knows\.is',
848 'KOCMOHABT',
849 'kouio',
850 'kube-probe',
851 'kubectl',
852 'kulturarw3',
853 'KumKie',
854 'Larbin',
855 'Lavf\/',
856 'leakix\.net',
857 'LeechFTP',
858 'LeechGet',
859 'letsencrypt',
860 'Lftp',
861 'LibVLC',
862 'LibWeb',
863 'Libwhisker',
864 'libwww',
865 'Licorne',
866 'Liferea\/',
867 'Lighthouse',
868 'Lightspeedsystems',
869 'Likse',
870 'limber\.io',
871 'Link Valet',
872 'LinkAlarm\/',
873 'LinkAnalyser',
874 'link-check',
875 'linkCheck',
876 'linkdex',
877 'LinkExaminer',
878 'linkfluence',
879 'linkpeek',
880 'LinkPreview',
881 'LinkScan',
882 'LinksManager',
883 'LinkTiger',
884 'LinkWalker',
885 'link_thumbnailer',
886 'Lipperhey',
887 'Litemage_walker',
888 'livedoor ScreenShot',
889 'LoadImpactRload',
890 'localsearch-web',
891 'LongURL API',
892 'longurl-r-package',
893 'looid\.com',
894 'looksystems\.net',
895 'ltx71',
896 'lua-resty-http',
897 'Lucee \(CFML Engine\)',
898 'Lush Http Client',
899 'lwp-request',
900 'lwp-trivial',
901 'LWP::Simple',
902 'lycos',
903 'LYT\.SR',
904 'L\.webis',
905 'mabontland',
906 'MacOutlook\/',
907 'Mag-Net',
908 'MagpieRSS',
909 'Mail::STS',
910 'MailChimp',
911 'Mail\.Ru',
912 'Majestic12',
913 'makecontact\/',
914 'Mandrill',
915 'MapperCmd',
916 'marketinggrader',
917 'MarkMonitor',
918 'MarkWatch',
919 'Mass Downloader',
920 'masscan\/',
921 'Mata Hari',
922 'mattermost',
923 'Mediametric',
924 'Mediapartners-Google',
925 'mediawords',
926 'MegaIndex\.ru',
927 'MeltwaterNews',
928 'Melvil Rawi',
929 'MemGator',
930 'Metaspinner',
931 'MetaURI',
932 'MFC_Tear_Sample',
933 'Microsearch',
934 'Microsoft Data Access',
935 'Microsoft Office',
936 'Microsoft Outlook',
937 'Microsoft Windows Network Diagnostics',
938 'Microsoft-WebDAV-MiniRedir',
939 'Microsoft\.Data\.Mashup',
940 'MIDown tool',
941 'MIIxpc',
942 'Mindjet',
943 'Miniature\.io',
944 'Miniflux',
945 'mio_httpc',
946 'Miro-HttpClient',
947 'Mister PiX',
948 'mixdata dot com',
949 'mixed-content-scan',
950 'mixnode',
951 'Mnogosearch',
952 'mogimogi',
953 'Mojeek',
954 'Mojolicious \(Perl\)',
955 'Mollie',
956 'monitis',
957 'Monitority\/',
958 'Monit\/',
959 'montastic',
960 'MonTools',
961 'Moreover',
962 'Morfeus Fucking Scanner',
963 'Morning Paper',
964 'MovableType',
965 'mowser',
966 'Mrcgiguy',
967 'Mr\.4x3 Powered',
968 'MS Web Services Client Protocol',
969 'MSFrontPage',
970 'mShots',
971 'MuckRack\/',
972 'muhstik-scan',
973 'MVAClient',
974 'MxToolbox\/',
975 'myseosnapshot',
976 'nagios',
977 'Najdi\.si',
978 'Name Intelligence',
979 'NameFo\.com',
980 'Nameprotect',
981 'nationalarchives',
982 'Navroad',
983 'nbertaupete95',
984 'NearSite',
985 'Needle',
986 'Nessus',
987 'Net Vampire',
988 'NetAnts',
989 'NETCRAFT',
990 'NetLyzer',
991 'NetMechanic',
992 'NetNewsWire',
993 'Netpursual',
994 'netresearch',
995 'NetShelter ContentScan',
996 'Netsparker',
997 'NetSystemsResearch',
998 'nettle',
999 'NetTrack',
1000 'Netvibes',
1001 'NetZIP',
1002 'Neustar WPM',
1003 'NeutrinoAPI',
1004 'NewRelicPinger',
1005 'NewsBlur .*Finder',
1006 'NewsGator',
1007 'newsme',
1008 'newspaper\/',
1009 'Nexgate Ruby Client',
1010 'NG-Search',
1011 'nghttp2',
1012 'Nibbler',
1013 'NICErsPRO',
1014 'NihilScio',
1015 'Nikto',
1016 'nineconnections',
1017 'NLNZ_IAHarvester',
1018 'Nmap Scripting Engine',
1019 'node-fetch',
1020 'node-superagent',
1021 'node-urllib',
1022 'Nodemeter',
1023 'NodePing',
1024 'node\.io',
1025 'nominet\.org\.uk',
1026 'nominet\.uk',
1027 'Norton-Safeweb',
1028 'Notifixious',
1029 'notifyninja',
1030 'NotionEmbedder',
1031 'nuhk',
1032 'nutch',
1033 'Nuzzel',
1034 'nWormFeedFinder',
1035 'nyawc\/',
1036 'Nymesis',
1037 'NYU',
1038 'Observatory\/',
1039 'Ocelli\/',
1040 'Octopus',
1041 'oegp',
1042 'Offline Explorer',
1043 'Offline Navigator',
1044 'OgScrper',
1045 'okhttp',
1046 'omgili',
1047 'OMSC',
1048 'Online Domain Tools',
1049 'Open Source RSS',
1050 'OpenCalaisSemanticProxy',
1051 'Openfind',
1052 'OpenLinkProfiler',
1053 'Openstat\/',
1054 'OpenVAS',
1055 'OPPO A33',
1056 'Optimizer',
1057 'Orbiter',
1058 'OrgProbe\/',
1059 'orion-semantics',
1060 'Outlook-Express',
1061 'Outlook-iOS',
1062 'Owler',
1063 'Owlin',
1064 'ownCloud News',
1065 'ow\.ly',
1066 'OxfordCloudService',
1067 'page scorer',
1068 'Page Valet',
1069 'page2rss',
1070 'PageFreezer',
1071 'PageGrabber',
1072 'PagePeeker',
1073 'PageScorer',
1074 'Pagespeed\/',
1075 'PageThing',
1076 'page_verifier',
1077 'Panopta',
1078 'panscient',
1079 'Papa Foto',
1080 'parsijoo',
1081 'Pavuk',
1082 'PayPal IPN',
1083 'pcBrowser',
1084 'Pcore-HTTP',
1085 'PDF24 URL To PDF',
1086 'Pearltrees',
1087 'PECL::HTTP',
1088 'peerindex',
1089 'Peew',
1090 'PeoplePal',
1091 'Perlu -',
1092 'PhantomJS Screenshoter',
1093 'PhantomJS\/',
1094 'Photon\/',
1095 'php-requests',
1096 'phpservermon',
1097 'Pi-Monster',
1098 'Picscout',
1099 'Picsearch',
1100 'PictureFinder',
1101 'Pimonster',
1102 'Pingability',
1103 'PingAdmin\.Ru',
1104 'Pingdom',
1105 'Pingoscope',
1106 'PingSpot',
1107 'ping\.blo\.gs',
1108 'pinterest\.com',
1109 'Pixray',
1110 'Pizilla',
1111 'Plagger\/',
1112 'Pleroma ',
1113 'Ploetz \+ Zeller',
1114 'Plukkie',
1115 'plumanalytics',
1116 'PocketImageCache',
1117 'PocketParser',
1118 'Pockey',
1119 'PodcastAddict\/',
1120 'POE-Component-Client-HTTP',
1121 'Polymail\/',
1122 'Pompos',
1123 'Porkbun',
1124 'Port Monitor',
1125 'postano',
1126 'postfix-mta-sts-resolver',
1127 'PostmanRuntime',
1128 'postplanner\.com',
1129 'PostPost',
1130 'postrank',
1131 'PowerPoint\/',
1132 'Prebid',
1133 'Prerender',
1134 'Priceonomics Analysis Engine',
1135 'PrintFriendly',
1136 'PritTorrent',
1137 'Prlog',
1138 'probethenet',
1139 'Project ?25499',
1140 'Project-Resonance',
1141 'prospectb2b',
1142 'Protopage',
1143 'ProWebWalker',
1144 'proximic',
1145 'PRTG Network Monitor',
1146 'pshtt, https scanning',
1147 'PTST ',
1148 'PTST\/[0-9]+',
1149 'Pump',
1150 'Python-httplib2',
1151 'python-httpx',
1152 'python-requests',
1153 'Python-urllib',
1154 'Qirina Hurdler',
1155 'QQDownload',
1156 'QrafterPro',
1157 'Qseero',
1158 'Qualidator',
1159 'QueryN Metasearch',
1160 'queuedriver',
1161 'quic-go-HTTP\/',
1162 'QuiteRSS',
1163 'Quora Link Preview',
1164 'Qwantify',
1165 'Radian6',
1166 'RadioPublicImageResizer',
1167 'Railgun\/',
1168 'RankActive',
1169 'RankFlex',
1170 'RankSonicSiteAuditor',
1171 'RapidLoad\/',
1172 'Re-re Studio',
1173 'ReactorNetty',
1174 'Readability',
1175 'RealDownload',
1176 'RealPlayer%20Downloader',
1177 'RebelMouse',
1178 'Recorder',
1179 'RecurPost\/',
1180 'redback\/',
1181 'ReederForMac',
1182 'Reeder\/',
1183 'ReGet',
1184 'RepoMonkey',
1185 'request\.js',
1186 'reqwest\/',
1187 'ResponseCodeTest',
1188 'RestSharp',
1189 'Riddler',
1190 'Rival IQ',
1191 'Robosourcer',
1192 'Robozilla',
1193 'ROI Hunter',
1194 'RPT-HTTPClient',
1195 'RSSMix\/',
1196 'RSSOwl',
1197 'RyowlEngine',
1198 'safe-agent-scanner',
1199 'SalesIntelligent',
1200 'Saleslift',
1201 'SAP NetWeaver Application Server',
1202 'SauceNAO',
1203 'SBIder',
1204 'sc-downloader',
1205 'scalaj-http',
1206 'Scamadviser-Frontend',
1207 'ScanAlert',
1208 'scan\.lol',
1209 'Scoop',
1210 'scooter',
1211 'ScopeContentAG-HTTP-Client',
1212 'ScoutJet',
1213 'ScoutURLMonitor',
1214 'ScrapeBox Page Scanner',
1215 'Scrapy',
1216 'Screaming',
1217 'ScreenShotService',
1218 'Scrubby',
1219 'Scrutiny\/',
1220 'Search37',
1221 'searchenginepromotionhelp',
1222 'Searchestate',
1223 'SearchExpress',
1224 'SearchSight',
1225 'SearchWP',
1226 'search\.thunderstone',
1227 'Seeker',
1228 'semanticdiscovery',
1229 'semanticjuice',
1230 'Semiocast HTTP client',
1231 'Semrush',
1232 'Sendsay\.Ru',
1233 'sentry\/',
1234 'SEO Browser',
1235 'Seo Servis',
1236 'seo-nastroj\.cz',
1237 'seo4ajax',
1238 'Seobility',
1239 'SEOCentro',
1240 'SeoCheck',
1241 'seocompany',
1242 'SEOkicks',
1243 'SEOlizer',
1244 'Seomoz',
1245 'SEOprofiler',
1246 'seoscanners',
1247 'SEOsearch',
1248 'seositecheckup',
1249 'SEOstats',
1250 'servernfo',
1251 'sexsearcher',
1252 'Seznam',
1253 'Shelob',
1254 'Shodan',
1255 'Shoppimon',
1256 'ShopWiki',
1257 'ShortLinkTranslate',
1258 'shortURL lengthener',
1259 'shrinktheweb',
1260 'Sideqik',
1261 'Siege',
1262 'SimplePie',
1263 'SimplyFast',
1264 'Siphon',
1265 'SISTRIX',
1266 'Site Sucker',
1267 'Site-Shot\/',
1268 'Site24x7',
1269 'SiteBar',
1270 'Sitebeam',
1271 'Sitebulb\/',
1272 'SiteCondor',
1273 'SiteExplorer',
1274 'SiteGuardian',
1275 'Siteimprove',
1276 'SiteIndexed',
1277 'Sitemap(s)? Generator',
1278 'SitemapGenerator',
1279 'SiteMonitor',
1280 'Siteshooter B0t',
1281 'SiteSnagger',
1282 'SiteSucker',
1283 'SiteTruth',
1284 'Sitevigil',
1285 'sitexy\.com',
1286 'SkypeUriPreview',
1287 'Slack\/',
1288 'sli-systems\.com',
1289 'slider\.com',
1290 'slurp',
1291 'SlySearch',
1292 'SmartDownload',
1293 'SMRF URL Expander',
1294 'SMUrlExpander',
1295 'Snake',
1296 'Snappy',
1297 'SnapSearch',
1298 'Snarfer\/',
1299 'SniffRSS',
1300 'sniptracker',
1301 'Snoopy',
1302 'SnowHaze Search',
1303 'sogou web',
1304 'SortSite',
1305 'Sottopop',
1306 'sovereign\.ai',
1307 'SpaceBison',
1308 'SpamExperts',
1309 'Spammen',
1310 'Spanner',
1311 'Spawning-AI',
1312 'spaziodati',
1313 'SPDYCheck',
1314 'Specificfeeds',
1315 'SpeedKit',
1316 'speedy',
1317 'SPEng',
1318 'Spinn3r',
1319 'spray-can',
1320 'Sprinklr ',
1321 'spyonweb',
1322 'sqlmap',
1323 'Sqlworm',
1324 'Sqworm',
1325 'SSL Labs',
1326 'ssl-tools',
1327 'StackRambler',
1328 'Statastico\/',
1329 'Statically-',
1330 'StatusCake',
1331 'Steeler',
1332 'Stratagems Kumo',
1333 'Stripe\/',
1334 'Stroke\.cz',
1335 'StudioFACA',
1336 'StumbleUpon',
1337 'suchen',
1338 'Sucuri',
1339 'summify',
1340 'SuperHTTP',
1341 'Surphace Scout',
1342 'Suzuran',
1343 'swcd ',
1344 'Symfony BrowserKit',
1345 'Symfony2 BrowserKit',
1346 'Synapse\/',
1347 'Syndirella\/',
1348 'SynHttpClient-Built',
1349 'Sysomos',
1350 'sysscan',
1351 'Szukacz',
1352 'T0PHackTeam',
1353 'tAkeOut',
1354 'Tarantula\/',
1355 'Taringa UGC',
1356 'TarmotGezgin',
1357 'tchelebi\.io',
1358 'techiaith\.cymru',
1359 'Teleport',
1360 'Telesoft',
1361 'Telesphoreo',
1362 'Telesphorep',
1363 'Tenon\.io',
1364 'teoma',
1365 'terrainformatica',
1366 'Test Certificate Info',
1367 'testuri',
1368 'Tetrahedron',
1369 'TextRazor Downloader',
1370 'The Drop Reaper',
1371 'The Expert HTML Source Viewer',
1372 'The Intraformant',
1373 'The Knowledge AI',
1374 'theinternetrules',
1375 'TheNomad',
1376 'Thinklab',
1377 'Thumbor',
1378 'Thumbshots',
1379 'ThumbSniper',
1380 'timewe\.net',
1381 'TinEye',
1382 'Tiny Tiny RSS',
1383 'TLSProbe\/',
1384 'Toata',
1385 'topster',
1386 'touche\.com',
1387 'Traackr\.com',
1388 'tracemyfile',
1389 'Trackuity',
1390 'TrapitAgent',
1391 'Trendiction',
1392 'Trendsmap',
1393 'trendspottr',
1394 'truwoGPS',
1395 'TryJsoup',
1396 'TulipChain',
1397 'Turingos',
1398 'Turnitin',
1399 'tweetedtimes',
1400 'Tweetminster',
1401 'Tweezler\/',
1402 'twibble',
1403 'Twice',
1404 'Twikle',
1405 'Twingly',
1406 'Twisted PageGetter',
1407 'Typhoeus',
1408 'ubermetrics-technologies',
1409 'uclassify',
1410 'UdmSearch',
1411 'ultimate_sitemap_parser',
1412 'unchaos',
1413 'unirest-java',
1414 'UniversalFeedParser',
1415 'unshortenit',
1416 'Unshorten\.It',
1417 'Untiny',
1418 'UnwindFetchor',
1419 'updated',
1420 'updown\.io daemon',
1421 'Upflow',
1422 'Uptimia',
1423 'URL Verifier',
1424 'Urlcheckr',
1425 'URLitor',
1426 'urlresolver',
1427 'Urlstat',
1428 'URLTester',
1429 'UrlTrends Ranking Updater',
1430 'URLy Warning',
1431 'URLy\.Warning',
1432 'URL\/Emacs',
1433 'Vacuum',
1434 'Vagabondo',
1435 'VB Project',
1436 'vBSEO',
1437 'VCI',
1438 'via ggpht\.com GoogleImageProxy',
1439 'Virusdie',
1440 'visionutils',
1441 'Visual Rights Group',
1442 'vkShare',
1443 'VoidEYE',
1444 'Voil',
1445 'voltron',
1446 'voyager\/',
1447 'VSAgent\/',
1448 'VSB-TUO\/',
1449 'Vulnbusters Meter',
1450 'VYU2',
1451 'w3af\.org',
1452 'W3C-checklink',
1453 'W3C-mobileOK',
1454 'W3C_Unicorn',
1455 'WAC-OFU',
1456 'WakeletLinkExpander',
1457 'WallpapersHD',
1458 'Wallpapers\/[0-9]+',
1459 'wangling',
1460 'Wappalyzer',
1461 'WatchMouse',
1462 'WbSrch\/',
1463 'WDT\.io',
1464 'Web Auto',
1465 'Web Collage',
1466 'Web Enhancer',
1467 'Web Fetch',
1468 'Web Fuck',
1469 'Web Pix',
1470 'Web Sauger',
1471 'Web spyder',
1472 'Web Sucker',
1473 'web-capture\.net',
1474 'Web-sniffer',
1475 'Webalta',
1476 'Webauskunft',
1477 'WebAuto',
1478 'WebCapture',
1479 'WebClient\/',
1480 'webcollage',
1481 'WebCookies',
1482 'WebCopier',
1483 'WebCorp',
1484 'WebDataStats',
1485 'WebDoc',
1486 'WebEnhancer',
1487 'WebFetch',
1488 'WebFuck',
1489 'WebGazer',
1490 'WebGo IS',
1491 'WebImageCollector',
1492 'WebImages',
1493 'WebIndex',
1494 'webkit2png',
1495 'WebLeacher',
1496 'webmastercoffee',
1497 'webmon ',
1498 'WebPix',
1499 'WebReaper',
1500 'WebSauger',
1501 'webscreenie',
1502 'Webshag',
1503 'Webshot',
1504 'Website Quester',
1505 'websitepulse agent',
1506 'WebsiteQuester',
1507 'Websnapr',
1508 'WebSniffer',
1509 'Webster',
1510 'WebStripper',
1511 'WebSucker',
1512 'webtech\/',
1513 'WebThumbnail',
1514 'Webthumb\/',
1515 'WebWhacker',
1516 'WebZIP',
1517 'WeLikeLinks',
1518 'WEPA',
1519 'WeSEE',
1520 'wf84',
1521 'Wfuzz\/',
1522 'wget',
1523 'WhatCMS',
1524 'WhatsApp',
1525 'WhatsMyIP',
1526 'WhatWeb',
1527 'WhereGoes\?',
1528 'Whibse',
1529 'WhoAPI\/',
1530 'WhoRunsCoinHive',
1531 'Whynder Magnet',
1532 'Windows-RSS-Platform',
1533 'WinHttp-Autoproxy-Service',
1534 'WinHTTP\/',
1535 'WinPodder',
1536 'wkhtmlto',
1537 'wmtips',
1538 'Woko',
1539 'Wolfram HTTPClient',
1540 'woorankreview',
1541 'WordPress\/',
1542 'WordupinfoSearch',
1543 'Word\/',
1544 'worldping-api',
1545 'wotbox',
1546 'WP Engine Install Performance API',
1547 'wpif',
1548 'wprecon\.com survey',
1549 'WPScan',
1550 'wscheck',
1551 'Wtrace',
1552 'WWW-Collector-E',
1553 'WWW-Mechanize',
1554 'WWW::Document',
1555 'WWW::Mechanize',
1556 'WWWOFFLE',
1557 'www\.monitor\.us',
1558 'x09Mozilla',
1559 'x22Mozilla',
1560 'XaxisSemanticsClassifier',
1561 'XenForo\/',
1562 'Xenu Link Sleuth',
1563 'XING-contenttabreceiver',
1564 'xpymep([0-9]?)\.exe',
1565 'Y!J-[A-Z][A-Z][A-Z]',
1566 'Yaanb',
1567 'yacy',
1568 'Yahoo Link Preview',
1569 'YahooCacheSystem',
1570 'YahooMailProxy',
1571 'YahooYSMcm',
1572 'YandeG',
1573 'Yandex(?!Search)',
1574 'yanga',
1575 'yeti',
1576 'Yo-yo',
1577 'Yoleo Consumer',
1578 'yomins\.com',
1579 'yoogliFetchAgent',
1580 'YottaaMonitor',
1581 'Your-Website-Sucks',
1582 'yourls\.org',
1583 'YoYs\.net',
1584 'YP\.PL',
1585 'Zabbix',
1586 'Zade',
1587 'Zao',
1588 'Zauba',
1589 'Zemanta Aggregator',
1590 'Zend\\\\Http\\\\Client',
1591 'Zend_Http_Client',
1592 'Zermelo',
1593 'Zeus ',
1594 'zgrab',
1595 'ZnajdzFoto',
1596 'ZnHTTP',
1597 'Zombie\.js',
1598 'Zoom\.Mac',
1599 'ZoteroTranslationServer',
1600 'ZyBorg',
1601 '[a-z0-9\-_]*(bot|crawl|archiver|transcoder|spider|uptime|validator|fetcher|cron|checker|reader|extractor|monitoring|analyzer|scraper)'
1602 ];
1603 }
1604
1605 /**
1606 * Return the list of strings to remove from the user agent before running the crawler regex.
1607 *
1608 * @return array
1609 */
1610 public function get_exclusions_list() {
1611 return [
1612 'Safari.[\d\.]*',
1613 'Firefox.[\d\.]*',
1614 ' Chrome.[\d\.]*',
1615 'Chromium.[\d\.]*',
1616 'MSIE.[\d\.]',
1617 'Opera\/[\d\.]*',
1618 'Mozilla.[\d\.]*',
1619 'AppleWebKit.[\d\.]*',
1620 'Trident.[\d\.]*',
1621 'Windows NT.[\d\.]*',
1622 'Android [\d\.]*',
1623 'Macintosh.',
1624 'Ubuntu',
1625 'Linux',
1626 '[ ]Intel',
1627 'Mac OS X [\d_]*',
1628 '(like )?Gecko(.[\d\.]*)?',
1629 'KHTML,',
1630 'CriOS.[\d\.]*',
1631 'CPU iPhone OS ([0-9_])* like Mac OS X',
1632 'CPU OS ([0-9_])* like Mac OS X',
1633 'iPod',
1634 'compatible',
1635 'x86_..',
1636 'i686',
1637 'x64',
1638 'X11',
1639 'rv:[\d\.]*',
1640 'Version.[\d\.]*',
1641 'WOW64',
1642 'Win64',
1643 'Dalvik.[\d\.]*',
1644 ' \.NET CLR [\d\.]*',
1645 'Presto.[\d\.]*',
1646 'Media Center PC',
1647 'BlackBerry',
1648 'Build',
1649 'Opera Mini\/\d{1,2}\.\d{1,2}\.[\d\.]*\/\d{1,2}\.',
1650 'Opera',
1651 ' \.NET[\d\.]*',
1652 'cubot',
1653 '; M bot',
1654 '; CRONO',
1655 '; B bot',
1656 '; IDbot',
1657 '; ID bot',
1658 '; POWER BOT',
1659 'OCTOPUS-CORE'
1660 ];
1661 }
1662
1663 /**
1664 * Return all possible HTTP headers that represent the User-Agent string.
1665 *
1666 * @return array
1667 */
1668 public function get_headers_list() {
1669 return [
1670 // The default User-Agent string.
1671 'HTTP_USER_AGENT',
1672 // Header can occur on devices using Opera Mini.
1673 'HTTP_X_OPERAMINI_PHONE_UA',
1674 // Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/
1675 'HTTP_X_DEVICE_USER_AGENT',
1676 'HTTP_X_ORIGINAL_USER_AGENT',
1677 'HTTP_X_SKYFIRE_PHONE',
1678 'HTTP_X_BOLT_PHONE_UA',
1679 'HTTP_DEVICE_STOCK_UA',
1680 'HTTP_X_UCBROWSER_DEVICE_UA',
1681 // Sometimes, bots (especially Google) use a genuine user agent, but fill this header in with their email address
1682 'HTTP_FROM',
1683 'HTTP_X_SCANNER' // Seen in use by Netsparker
1684 ];
1685 }
1686 }
1687