Codebase list libhttp-browserdetect-perl / 58cef7f
* Fix detection of SCO Unix to trigger fewer false positives * Correct detection of (most) robots based on "+http://blah" Andrew Moise 9 years ago
2 changed file(s) with 57 addition(s) and 37 deletion(s). Raw diff Collapse all Expand all
957957 $self->{robot_fragment} = "search";
958958 $robot_tests->{robot} = 'unknown';
959959 }
960 elsif ( 0 && $self->{user_agent} =~ /([\w \/\.]+)\s*[\;\(]\s*\+http\:/i )
960 elsif ( $self->{user_agent} =~ /([\w \/\.\-]+)[ \;\(\)]*\+http\:/i )
961961 {
962962 # Something followed by +http
963963 $self->{robot_string} = $1;
964 $self->{robot_string} =~ s/^(.*?)\s*/$1/;
964 $self->{robot_string} =~ s/^ *(.+?)[ \;\(\)]*$/$1/;
965965 $robot_tests->{robot} = 'unknown';
966966 }
967967 else {
12021202 $os_tests->{aix3} = 1 if ( index( $ua, "aix 3" ) != -1 );
12031203 $os_tests->{aix4} = 1 if ( index( $ua, "aix 4" ) != -1 );
12041204 }
1205 elsif ( index( $ua, "sco" ) != -1 || index( $ua, "unix_sv" ) != -1 ) {
1205 elsif ( $ua =~ m{\bsco\b} || index( $ua, "unix_sv" ) != -1 ) {
12061206 $os = 'unix';
12071207 $os_string = 'SCO Unix';
12081208 $os_tests->{sco} = $os_tests->{unix} = 1;
28522852 "BUbiNG (+http://law.di.unimi.it/BUbiNG.html)" : {
28532853 "browser_major" : 0,
28542854 "browser_minor" : ".0",
2855 "match" : [],
2856 "robot" : 0
2855 "match" : [
2856 "robot"
2857 ],
2858 "robot" : "unknown",
2859 "robot_name" : "BUbiNG"
28572860 },
28582861 "Baiduspider-image+(+http://www.baidu.com/search/spider.htm)\\\\nReferer: http://image.baidu.com/i?ct=503316480&z=0&tn=baiduimagedetail" : {
28592862 "browser_major" : 0,
29322935 "Crowsnest/0.5 (+http://www.crowsnest.tv/)" : {
29332936 "browser_major" : 0,
29342937 "browser_minor" : ".5",
2935 "match" : [],
2936 "robot" : 0
2938 "match" : [
2939 "robot"
2940 ],
2941 "robot" : "unknown",
2942 "robot_name" : "Crowsnest/0.5"
29372943 },
29382944 "Dalvik/1.6.0 (Linux; U; Android 4.4.2; LGMS395 Build/KOT49I.MS39510d)" : {
29392945 "browser" : "dalvik",
1134811354 "mac",
1134911355 "macosx",
1135011356 "firefox",
11351 "gecko"
11357 "gecko",
11358 "robot"
1135211359 ],
1135311360 "os" : "macosx",
1135411361 "os_beta" : "",
1135511362 "os_major" : "10",
1135611363 "os_minor" : ".9",
1135711364 "os_string" : "Mac OS X",
11358 "robot" : 0
11365 "robot" : "unknown",
11366 "robot_string": "FlipboardProxy/1.1"
1135911367 },
1136011368 "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10) AppleWebKit/600.2.5 (KHTML, like Gecko) Version/8.0.2 Safari/600.2.5" : {
1136111369 "browser" : "safari",
1663716645 "browser_major" : "5",
1663816646 "browser_minor" : ".0",
1663916647 "match" : [
16640 "unix",
16641 "sco",
1664216648 "robot"
1664316649 ],
16644 "os" : "unix",
16645 "os_string" : "SCO Unix",
1664616650 "robot" : "unknown",
16647 "robot_name" : "Blekkobot"
16651 "robot_name" : "ScoutJet"
1664816652 },
1664916653 "Mozilla/5.0 (compatible; DomainAppender /1.0; +http://www.profound.net/domainappender)" : {
1665016654 "browser_major" : "5",
1666216666 "robot"
1666316667 ],
1666416668 "robot" : "unknown",
16665 "robot_name" : "http://domainsigma.com/robot"
16669 "robot_name" : "DomainSigmaCrawler/0.1"
1666616670 },
1666716671 "Mozilla/5.0 (compatible; DotBot/1.1; http://www.opensiteexplorer.org/dotbot, help@moz.com)" : {
1666816672 "browser_major" : "1",
1672416728 "Mozilla/5.0 (compatible; GoogleDocs; documents; +http://docs.google.com)" : {
1672516729 "browser_major" : "5",
1672616730 "browser_minor" : ".0",
16727 "match" : [],
16728 "robot" : 0
16731 "match" : [
16732 "robot"
16733 ],
16734 "robot" : "unknown",
16735 "robot_string" : "documents"
1672916736 },
1673016737 "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)" : {
1673116738 "browser_major" : "2",
1674916756 "Mozilla/5.0 (compatible; GroupHigh/1.0; +http://www.grouphigh.com/)" : {
1675016757 "browser_major" : "1",
1675116758 "browser_minor" : ".0",
16752 "match" : [],
16753 "robot" : 0
16759 "match" : [
16760 "robot"
16761 ],
16762 "robot" : "unknown",
16763 "robot_string" : "GroupHigh/1.0"
1675416764 },
1675516765 "Mozilla/5.0 (compatible; HyperCrawl/0.2; +http://www.seograph.net/bot.html)" : {
1675616766 "browser_major" : 0,
1675916769 "robot"
1676016770 ],
1676116771 "robot" : "unknown",
16762 "robot_name" : "http://www.seograph.net/bot.html"
16772 "robot_name" : "HyperCrawl/0.2"
1676316773 },
1676416774 "Mozilla/5.0 (compatible; Linux x86_64; Mail.RU_Bot/2.0; +http://go.mail.ru/help/robots)" : {
1676516775 "browser_major" : "5",
1752717537 "Mozilla/5.0 (compatible; Seznam screenshot-generator 2.1; +http://fulltext.sblog.cz/screenshot/)" : {
1752817538 "browser_major" : "5",
1752917539 "browser_minor" : ".0",
17530 "match" : [],
17531 "robot" : 0
17540 "match" : [
17541 "robot"
17542 ],
17543 "robot" : "unknown",
17544 "robot_string" : "Seznam screenshot-generator 2.1"
1753217545 },
1753317546 "Mozilla/5.0 (compatible; SeznamBot/3.2; +http://fulltext.sblog.cz/)" : {
1753417547 "browser_major" : "3",
1759217605 "robot"
1759317606 ],
1759417607 "robot" : "unknown",
17595 "robot_name" : "archive.org_bot"
17608 "robot_name" : "Wayback Machine Live Record"
1759617609 },
1759717610 "Mozilla/5.0 (compatible; bingbot/2.0; +http://www.bing.com/bingbot.htm)" : {
1759817611 "browser_major" : "2",
1761817631 "Mozilla/5.0 (compatible; coccoc/1.0; +http://help.coccoc.com/)" : {
1761917632 "browser_major" : "1",
1762017633 "browser_minor" : ".0",
17621 "match" : [],
17622 "robot" : 0
17634 "match" : [
17635 "robot"
17636 ],
17637 "robot" : "unknown",
17638 "robot_string" : "coccoc/1.0"
1762317639 },
1762417640 "Mozilla/5.0 (compatible; heritrix/3.1.1 +http://www.baidu.com)" : {
1762517641 "browser_major" : "5",
1762617642 "browser_minor" : ".0",
17627 "match" : [],
17628 "robot" : 0
17643 "match" : [
17644 "robot"
17645 ],
17646 "robot" : "unknown",
17647 "robot_string" : "heritrix/3.1.1"
1762917648 },
1763017649 "Mozilla/5.0 (compatible; linkdexbot/2.2; +http://www.linkdex.com/bots/)" : {
1763117650 "browser_major" : "2",
1768817707 "engine_string" : "WebKit",
1768917708 "language" : "EN",
1769017709 "match" : [
17691 "unix",
17692 "sco",
1769317710 "chrome",
1769417711 "webkit"
1769517712 ],
17696 "os" : "unix",
17697 "os_string" : "SCO Unix",
1769817713 "robot" : 0
1769917714 },
1770017715 "Mozilla/5.0 (iPad; CPU OS 5_0_1 like Mac OS X) AppleWebKit/534.46 (KHTML, like Gecko) Version/5.1 Mobile/9A405 Safari/7534.48.3" : {
1878218797 "nav4up",
1878318798 "nav45up",
1878418799 "nav6",
18785 "nav6up"
18786 ],
18787 "robot" : 0
18800 "nav6up",
18801 "robot"
18802 ],
18803 "robot" : "unknown",
18804 "robot_string" : "Mozilla/5.0 Moreover/5.1"
1878818805 },
1878918806 "NING/1.0" : {
1879018807 "browser_major" : "1",
1907419091 "browser_beta" : ".4",
1907519092 "browser_major" : 0,
1907619093 "browser_minor" : ".9",
19077 "match" : [],
19078 "robot" : 0
19094 "match" : [
19095 "robot"
19096 ],
19097 "robot" : "unknown",
19098 "robot_string" : "OrgProbe/0.9.4"
1907919099 },
1908019100 "PHP/5.2.17p1" : {
1908119101 "browser_beta" : ".17p1",
1932019340 "robot"
1932119341 ],
1932219342 "robot" : "unknown",
19323 "robot_name" : "http://www.wotbox.com/bot/"
19343 "robot_name" : "Wotbox/2.01"
1932419344 },
1932519345 "Xenu Link Sleuth/1.3.8" : {
1932619346 "browser_beta" : ".8",