bot_detection 1.0.6 → 1.0.7
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.gitignore +1 -0
- data/.travis.yml +11 -0
- data/CHANGELOG.md +5 -0
- data/Rakefile +3 -1
- data/bot_detection.gemspec +4 -2
- data/lib/bot_detection/bot_user_agents.rb +41 -0
- data/lib/bot_detection/search_engine_user_agents.rb +3 -0
- data/lib/bot_detection/version.rb +1 -1
- metadata +31 -16
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 3f9cf46bdce8f49486f6a1bc88f966f2068920aa
|
4
|
+
data.tar.gz: 7ec14e78a5cf23c8534642f945186b95ccb8f042
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: e455e84029af1e41be86f87b381f028ee36443dcb7cb202cceaff4be8516bcdcd50029676d10af21513e4e151f6fdd60f8d19263742567f773cc39f224b72b17
|
7
|
+
data.tar.gz: 964f6ef6ce7fe47fe5b97cdc474462557056c394e79041f6983056ab9589a8be3160242694b0d602313b33c8ed18cf1dbf3e520c1d4d5e4d8bb6f3117823433c
|
data/.gitignore
CHANGED
data/.travis.yml
ADDED
data/CHANGELOG.md
CHANGED
@@ -1,5 +1,10 @@
|
|
1
1
|
# Changelog
|
2
2
|
|
3
|
+
#### Release 1.0.7
|
4
|
+
|
5
|
+
- added several new user agents, which have been spotted around, to the list
|
6
|
+
- added rspec to validate builds on travis
|
7
|
+
|
3
8
|
#### Release 1.0.6
|
4
9
|
|
5
10
|
- added several new user agents, which have been spotted around, to the list
|
data/Rakefile
CHANGED
data/bot_detection.gemspec
CHANGED
@@ -5,6 +5,7 @@ require 'bot_detection/version'
|
|
5
5
|
|
6
6
|
Gem::Specification.new do |spec|
|
7
7
|
spec.name = "bot_detection"
|
8
|
+
spec.description = "Checks a user agent for a web crawler"
|
8
9
|
spec.version = BotDetection::VERSION
|
9
10
|
spec.authors = ["Nils Berenbold"]
|
10
11
|
spec.email = ["nils.berenbold@gmail.com"]
|
@@ -16,8 +17,9 @@ Gem::Specification.new do |spec|
|
|
16
17
|
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
17
18
|
spec.require_paths = ["lib"]
|
18
19
|
|
19
|
-
spec.add_runtime_dependency "public_suffix", "~> 1.4
|
20
|
+
spec.add_runtime_dependency "public_suffix", "~> 1.4"
|
20
21
|
|
22
|
+
spec.add_development_dependency "rspec", "~> 3.1"
|
21
23
|
spec.add_development_dependency "bundler", "~> 1.6"
|
22
|
-
spec.add_development_dependency "rake"
|
24
|
+
spec.add_development_dependency "rake", "~> 10.4"
|
23
25
|
end
|
@@ -12,6 +12,7 @@ BotDetection::BotUserAgents = [
|
|
12
12
|
"Mozilla/5.0 (Windows; U; Windows NT 6.0; en-GB; rv:1.0; trendictionbot0.5.0; trendiction search; http://www.trendiction.de/bot; please let us know of any problems; web at trendiction.com) Gecko/20071127 Firefox/3.0.0.11",
|
13
13
|
"ia_archiver (+http://www.alexa.com/site/help/webmasters; crawler@alexa.com)",
|
14
14
|
"Mozilla/5.0 (compatible; Exabot/3.0 (BiggerBetter); +http://www.exabot.com/go/robot)",
|
15
|
+
"Mozilla/5.0 (compatible; Exabot/3.0; +http://www.exabot.com/go/robot)",
|
15
16
|
"Mozilla/5.0 (compatible; Linux x86_64; Mail.RU_Bot/2.0; +http://go.mail.ru/help/robots)",
|
16
17
|
"Mozilla/5.0 (compatible; SMTBot/1.0; +http://www.similartech.com/smtbot)",
|
17
18
|
"Twitterbot/1.0",
|
@@ -41,8 +42,48 @@ BotDetection::BotUserAgents = [
|
|
41
42
|
"bitlybot",
|
42
43
|
"Mozilla/5.0 (TweetmemeBot/4.0; +http://datasift.com/bot.html) Gecko/20100101 Firefox/31.0",
|
43
44
|
"Mozilla/5.0 (Linux; U; Android 4.2.2; bg-bg; CUBOT X6 Build/JDQ39) AppleWebKit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30",
|
45
|
+
"Mozilla/5.0 (Linux; U; Android 4.2.2; de-de; CUBOT S108 Build/CUBOT_S108) AppleWebKit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30",
|
44
46
|
"DoCoMo/2.0 N905i(c100;TB;W24H16) (compatible; Googlebot-Mobile/2.1; +http://www.google.com/bot.html)",
|
45
47
|
"AppEngine-Google; (+http://code.google.com/appengine; appid: asburyisgay)",
|
46
48
|
"Mozilla/5.0 (compatible; SemrushBot/0.98~bl; +http://www.semrush.com/bot.html)",
|
47
49
|
"Mozilla/5.0 (compatible; DotBot/1.1; http://www.opensiteexplorer.org/dotbot, help@moz.com)",
|
50
|
+
"Sogou web spider/4.0(+http://www.sogou.com/docs/help/webmasters.htm#07)",
|
51
|
+
"MaxPointCrawler/Nutch-1.1 (maxpoint.crawler at maxpointinteractive dot com)",
|
52
|
+
"woobot/2.0",
|
53
|
+
"techmixx Spider v1 (http://techmixx.com/)",
|
54
|
+
"WordPress/4.0.1; http://novarabota.org",
|
55
|
+
"yacybot (/global; amd64 Windows 7 6.1; java 1.8.0_25; Europe/en) http://yacy.net/bot.html",
|
56
|
+
"Mozilla/5.0 (compatible; Linux x86_64; Mail.RU_Bot/Fast/2.0; +http://go.mail.ru/help/robots)",
|
57
|
+
"QuerySeekerSpider ( http://queryseeker.com/bot.html )",
|
58
|
+
"Mozilla/5.0 (compatible; LinkpadBot/1.06; +http://www.linkpad.ru)",
|
59
|
+
"Mozilla/5.0 (compatible; MixrankBot; crawler@mixrank.com)",
|
60
|
+
"rogerbot/1.0 (http://moz.com/help/pro/what-is-rogerbot-, rogerbot-wherecat@moz.com)",
|
61
|
+
"Mozilla/5.0 (compatible; OpenHoseBot/2.1; +http://www.openhose.org/bot.html)",
|
62
|
+
"Superarama.com - BOT/v.0.1",
|
63
|
+
"Mozilla/5.0 (compatible; memoryBot/1.21.14 +http://mignify.com/bot.html)",
|
64
|
+
"Elmer, the Thinglink ImageBot (http://www.thinglink.com/help/ThinglinkImageBot)",
|
65
|
+
"Mozilla/5.0 (compatible; SEOkicks-Robot; +http://www.seokicks.de/robot.html)",
|
66
|
+
"Mozilla/5.0 (compatible; MJ12bot/v1.4.4; http://www.majestic12.co.uk/bot.php?+)",
|
67
|
+
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; CrystalSemanticsBot http://www.crystalsemantics.com/service-navigation/imprint/useragent/)",
|
68
|
+
"Mozilla/5.0 (compatible;acapbot/0.1;treat like Googlebot)",
|
69
|
+
"Mozilla/5.0 (compatible; archive.org_bot +http://archive.org/details/archive.org_bot)",
|
70
|
+
"Slackbot-LinkExpanding 1.0 (+https://api.slack.com/robots)",
|
71
|
+
"Wotbox/2.01 (+http://www.wotbox.com/bot/)",
|
72
|
+
"Wotbox/2.0 (bot@wotbox.com; http://www.wotbox.com)",
|
73
|
+
"Mozilla/5.0 (compatible; EveryoneSocialBot/1.0; support@everyonesocial.com http://everyonesocial.com/)",
|
74
|
+
"Jabse.com/2.0 (+http://www.jabse.com/bot.php)",
|
75
|
+
"Cliqzbot/0.1 (+http://cliqz.com/company/cliqzbot)",
|
76
|
+
"Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.1.2) Gecko/20090729 Firefox/3.5.2 (.NET CLR 3.5.30729; Diffbot/0.1; +http://www.diffbot.com)",
|
77
|
+
"CCBot/2.0 (http://commoncrawl.org/faq/)",
|
78
|
+
"Mozilla/5.0 (compatible; Kraken/0.1; http://linkfluence.net/; bot@linkfluence.net)",
|
79
|
+
"Mozilla/5.0 (compatible; uMBot-FC/1.0; mailto: crawling@ubermetrics-technologies.com)",
|
80
|
+
"Mozilla/5.0 (compatible; memoryBot/1.20.311 +http://internetmemory.org/en/)",
|
81
|
+
"Mozilla/5.0 (compatible; uMBot-LN/1.0; mailto: crawling@ubermetrics-technologies.com)",
|
82
|
+
"Mozilla/5.0 (compatible; linkdexbot/2.0; +http://www.linkdex.com/bots/)",
|
83
|
+
"German Wikipedia Broken Weblinks Bot; contact: gifti@tools.wmflabs.org",
|
84
|
+
"Mozilla/5.0 (compatible; SeznamBot/3.2; +http://fulltext.sblog.cz/)",
|
85
|
+
"Mozilla/5.0 (compatible; TwitterCrawler)",
|
86
|
+
"rogerbot/1.0 (http://moz.com/help/pro/what-is-rogerbot-, rogerbot-crawler+shiny@moz.com)",
|
87
|
+
"crawler4j (http://code.google.com/p/crawler4j/)",
|
88
|
+
"Mozilla/5.0 (compatible; PaperLiBot/2.1; http://support.paper.li/entries/20023257-what-is-paper-li)",
|
48
89
|
]
|
@@ -3,6 +3,7 @@ BotDetection::SearchEngineUserAgents = [
|
|
3
3
|
"Baiduspider+(+http://www.baidu.com/search/spider.htm)",
|
4
4
|
"Baiduspider+(+http://www.baidu.com/search/spider_jp.html)",
|
5
5
|
"BaiDuSpider",
|
6
|
+
"Mozilla/5.0+(compatible;+Baiduspider-cpro;++http://www.baidu.com/search/spider.html)",
|
6
7
|
"DuckDuckBot/1.0; (+http://duckduckgo.com/duckduckbot.html)",
|
7
8
|
"Mozilla/5.0 (compatible; YandexBot/3.0; +http://yandex.com/bots)",
|
8
9
|
"Mozilla/5.0 (compatible; YandexImages/3.0; +http://yandex.com/bots)",
|
@@ -28,10 +29,12 @@ BotDetection::SearchEngineUserAgents = [
|
|
28
29
|
"Mozilla/5.0 (compatible; bingbot/2.0 +http://www.bing.com/bingbot.htm)",
|
29
30
|
"msnbot/2.1",
|
30
31
|
"msnbot/2.0b",
|
32
|
+
"msnbot/2.0b (+http://search.msn.com/msnbot.htm)",
|
31
33
|
"msnbot/1.1 (+http://search.msn.com/msnbot.htm)",
|
32
34
|
"msnbot/1.1",
|
33
35
|
"msnbot/1.0 (+http://search.msn.com/msnbot.htm)",
|
34
36
|
"msnbot/0.9 (+http://search.msn.com/msnbot.htm)",
|
35
37
|
"msnbot/0.11 ( http://search.msn.com/msnbot.htm)",
|
36
38
|
"MSNBOT/0.1 (http://search.msn.com/msnbot.htm)",
|
39
|
+
"Mozilla/5.0 (compatible; Yeti/1.1; +http://help.naver.com/robots/)",
|
37
40
|
]
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: bot_detection
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.0.
|
4
|
+
version: 1.0.7
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Nils Berenbold
|
@@ -14,52 +14,67 @@ dependencies:
|
|
14
14
|
name: public_suffix
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
-
- - ~>
|
17
|
+
- - "~>"
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: 1.4
|
19
|
+
version: '1.4'
|
20
20
|
type: :runtime
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
|
-
- - ~>
|
24
|
+
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version: 1.4
|
26
|
+
version: '1.4'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rspec
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '3.1'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '3.1'
|
27
41
|
- !ruby/object:Gem::Dependency
|
28
42
|
name: bundler
|
29
43
|
requirement: !ruby/object:Gem::Requirement
|
30
44
|
requirements:
|
31
|
-
- - ~>
|
45
|
+
- - "~>"
|
32
46
|
- !ruby/object:Gem::Version
|
33
47
|
version: '1.6'
|
34
48
|
type: :development
|
35
49
|
prerelease: false
|
36
50
|
version_requirements: !ruby/object:Gem::Requirement
|
37
51
|
requirements:
|
38
|
-
- - ~>
|
52
|
+
- - "~>"
|
39
53
|
- !ruby/object:Gem::Version
|
40
54
|
version: '1.6'
|
41
55
|
- !ruby/object:Gem::Dependency
|
42
56
|
name: rake
|
43
57
|
requirement: !ruby/object:Gem::Requirement
|
44
58
|
requirements:
|
45
|
-
- -
|
59
|
+
- - "~>"
|
46
60
|
- !ruby/object:Gem::Version
|
47
|
-
version: '
|
61
|
+
version: '10.4'
|
48
62
|
type: :development
|
49
63
|
prerelease: false
|
50
64
|
version_requirements: !ruby/object:Gem::Requirement
|
51
65
|
requirements:
|
52
|
-
- -
|
66
|
+
- - "~>"
|
53
67
|
- !ruby/object:Gem::Version
|
54
|
-
version: '
|
55
|
-
description:
|
68
|
+
version: '10.4'
|
69
|
+
description: Checks a user agent for a web crawler
|
56
70
|
email:
|
57
71
|
- nils.berenbold@gmail.com
|
58
72
|
executables: []
|
59
73
|
extensions: []
|
60
74
|
extra_rdoc_files: []
|
61
75
|
files:
|
62
|
-
- .gitignore
|
76
|
+
- ".gitignore"
|
77
|
+
- ".travis.yml"
|
63
78
|
- CHANGELOG.md
|
64
79
|
- Gemfile
|
65
80
|
- LICENSE.txt
|
@@ -82,17 +97,17 @@ require_paths:
|
|
82
97
|
- lib
|
83
98
|
required_ruby_version: !ruby/object:Gem::Requirement
|
84
99
|
requirements:
|
85
|
-
- -
|
100
|
+
- - ">="
|
86
101
|
- !ruby/object:Gem::Version
|
87
102
|
version: '0'
|
88
103
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
89
104
|
requirements:
|
90
|
-
- -
|
105
|
+
- - ">="
|
91
106
|
- !ruby/object:Gem::Version
|
92
107
|
version: '0'
|
93
108
|
requirements: []
|
94
109
|
rubyforge_project:
|
95
|
-
rubygems_version: 2.
|
110
|
+
rubygems_version: 2.4.5
|
96
111
|
signing_key:
|
97
112
|
specification_version: 4
|
98
113
|
summary: Detects Search Engine crawlers by reverse DNS lookups.
|