human_power 0.0.2 → 0.0.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/README.md +8 -1
- data/lib/human_power/version.rb +1 -1
- data/lib/human_power.rb +10 -2
- data/user_agents.yml +170 -0
- metadata +4 -4
- data/lib/human_power/user_agents.rb +0 -7
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 85d862a0641b75ed9ca834a320e636899b0a707e
|
|
4
|
+
data.tar.gz: 8526d1ddd6b2a51439f7efb4339f397c5f575b07
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: ff9ebfe171ddc808a642e6bda45e3475d0da4ea07d1f063694ae7d92807ff4cfd9042dbd643d11dcf30c6449377f5437c4c84139cd2153149c8dff7adbb347fb
|
|
7
|
+
data.tar.gz: becb2c0552d849252a8ee195cb5cb0e0dd9274ad093a3dc4ddf31dc6c64b92b6630b598d45ce8d605d54a74de7003801b03814c1b1d4ccbc61ef54b474e12b72
|
data/README.md
CHANGED
|
@@ -24,7 +24,7 @@ If you are using Rails, you can add a sample *config/robots.rb* configuration fi
|
|
|
24
24
|
|
|
25
25
|
$ rails g human_power:install
|
|
26
26
|
|
|
27
|
-
It will allow crawlers
|
|
27
|
+
It will allow crawlers access to the whole site by default.
|
|
28
28
|
|
|
29
29
|
Now you can restart your server and visit `/robots.txt` to see what's generated from the new configuration file.
|
|
30
30
|
|
|
@@ -70,6 +70,13 @@ sitemap sitemap_url
|
|
|
70
70
|
sitemap one_url, two_url
|
|
71
71
|
```
|
|
72
72
|
|
|
73
|
+
Then visit `/robots.txt` in your browser.
|
|
74
|
+
|
|
75
|
+
## Crawlers
|
|
76
|
+
|
|
77
|
+
Please see [user_agents.yml](https://github.com/lassebunk/human_power/blob/master/user_agents.yml) for a list of 170+ built-in user agents/crawlers you can use like shown above.
|
|
78
|
+
The list is from [UserAgentString.com](http://www.useragentstring.com/pages/Crawlerlist/).
|
|
79
|
+
|
|
73
80
|
## Caveats
|
|
74
81
|
|
|
75
82
|
Human Power is great for adding rules to your robots.txt.
|
data/lib/human_power/version.rb
CHANGED
data/lib/human_power.rb
CHANGED
|
@@ -1,7 +1,6 @@
|
|
|
1
1
|
require "human_power/version"
|
|
2
2
|
require "human_power/generator"
|
|
3
3
|
require "human_power/rule"
|
|
4
|
-
require "human_power/user_agents"
|
|
5
4
|
require "human_power/rails" if defined?(Rails)
|
|
6
5
|
|
|
7
6
|
module HumanPower
|
|
@@ -20,8 +19,17 @@ module HumanPower
|
|
|
20
19
|
user_agents[key] = user_agent_string
|
|
21
20
|
end
|
|
22
21
|
|
|
22
|
+
# Hash of registered user agents.
|
|
23
23
|
def user_agents
|
|
24
|
-
@user_agents ||=
|
|
24
|
+
@user_agents ||= load_user_agents
|
|
25
25
|
end
|
|
26
|
+
|
|
27
|
+
private
|
|
28
|
+
|
|
29
|
+
# Loads the built-in user agents from crawlers.yml.
|
|
30
|
+
def load_user_agents
|
|
31
|
+
path = File.expand_path("../../user_agents.yml", __FILE__)
|
|
32
|
+
Hash[YAML.load(open(path).read).map { |k, v| [k.to_sym, v] }]
|
|
33
|
+
end
|
|
26
34
|
end
|
|
27
35
|
end
|
data/user_agents.yml
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
1
|
+
008: 008
|
|
2
|
+
abacho_bot: ABACHOBot
|
|
3
|
+
accoona_ai_agent: Accoona-AI-Agent
|
|
4
|
+
add_sugar_spider_bot: AddSugarSpiderBot
|
|
5
|
+
any_apex_bot: AnyApexBot
|
|
6
|
+
arachmo: Arachmo
|
|
7
|
+
blitzbot: B-l-i-t-z-B-O-T
|
|
8
|
+
baiduspider: Baiduspider
|
|
9
|
+
become_bot: BecomeBot
|
|
10
|
+
beslist_bot: BeslistBot
|
|
11
|
+
billy_bob_bot: BillyBobBot
|
|
12
|
+
bimbot: Bimbot
|
|
13
|
+
bingbot: Bingbot
|
|
14
|
+
blitz_bot: BlitzBOT
|
|
15
|
+
boitho_com_dc: boitho.com-dc
|
|
16
|
+
boitho_com_robot: boitho.com-robot
|
|
17
|
+
btbot: btbot
|
|
18
|
+
catch_bot: CatchBot
|
|
19
|
+
cerberian_drtrs: Cerberian Drtrs
|
|
20
|
+
charlotte: Charlotte
|
|
21
|
+
convera_crawler: ConveraCrawler
|
|
22
|
+
cosmos: cosmos
|
|
23
|
+
covario_ids: Covario IDS
|
|
24
|
+
datapark_search: DataparkSearch
|
|
25
|
+
diamond_bot: DiamondBot
|
|
26
|
+
discobot: Discobot
|
|
27
|
+
dotbot: Dotbot
|
|
28
|
+
emerald_shield_com_web_bot: EmeraldShield.com WebBot
|
|
29
|
+
envolk_its_spider: envolk[ITS]spider
|
|
30
|
+
esperanza_bot: EsperanzaBot
|
|
31
|
+
exabot: Exabot
|
|
32
|
+
fast_enterprise_crawler: FAST Enterprise Crawler
|
|
33
|
+
fast_web_crawler: FAST-WebCrawler
|
|
34
|
+
fdse_robot: FDSE robot
|
|
35
|
+
find_links: FindLinks
|
|
36
|
+
furl_bot: FurlBot
|
|
37
|
+
fyber_spider: FyberSpider
|
|
38
|
+
g2crawler: g2crawler
|
|
39
|
+
gaisbot: Gaisbot
|
|
40
|
+
galaxy_bot: GalaxyBot
|
|
41
|
+
genie_bot: genieBot
|
|
42
|
+
gigabot: Gigabot
|
|
43
|
+
girafabot: Girafabot
|
|
44
|
+
googlebot: Googlebot
|
|
45
|
+
googlebot_image: Googlebot-Image
|
|
46
|
+
guruji_bot: GurujiBot
|
|
47
|
+
happy_fun_bot: HappyFunBot
|
|
48
|
+
hl_ftien_spider: hl_ftien_spider
|
|
49
|
+
holmes: Holmes
|
|
50
|
+
htdig: htdig
|
|
51
|
+
iaskspider: iaskspider
|
|
52
|
+
ia_archiver: ia_archiver
|
|
53
|
+
ic_crawler: iCCrawler
|
|
54
|
+
ichiro: ichiro
|
|
55
|
+
igde_spyder: igdeSpyder
|
|
56
|
+
irl_bot: IRLbot
|
|
57
|
+
issue_crawler: IssueCrawler
|
|
58
|
+
jaxified_bot: Jaxified Bot
|
|
59
|
+
jyxobot: Jyxobot
|
|
60
|
+
koepa_bot: KoepaBot
|
|
61
|
+
l_webis: L.webis
|
|
62
|
+
lapozz_bot: LapozzBot
|
|
63
|
+
larbin: Larbin
|
|
64
|
+
ld_spider: LDSpider
|
|
65
|
+
lexxe_bot: LexxeBot
|
|
66
|
+
linguee_bot: Linguee Bot
|
|
67
|
+
link_walker: LinkWalker
|
|
68
|
+
lmspider: lmspider
|
|
69
|
+
lwp_trivial: lwp-trivial
|
|
70
|
+
mabontland: mabontland
|
|
71
|
+
magpie_crawler: magpie-crawler
|
|
72
|
+
mediapartners_google: Mediapartners-Google
|
|
73
|
+
mj12bot: MJ12bot
|
|
74
|
+
mnogosearch: Mnogosearch
|
|
75
|
+
mogimogi: mogimogi
|
|
76
|
+
mojeek_bot: MojeekBot
|
|
77
|
+
moreoverbot: Moreoverbot
|
|
78
|
+
morning_paper: Morning Paper
|
|
79
|
+
msnbot: msnbot
|
|
80
|
+
msr_bot: MSRBot
|
|
81
|
+
mva_client: MVAClient
|
|
82
|
+
mxbot: mxbot
|
|
83
|
+
net_research_server: NetResearchServer
|
|
84
|
+
net_seer_crawler: NetSeer Crawler
|
|
85
|
+
news_gator: NewsGator
|
|
86
|
+
ng_search: NG-Search
|
|
87
|
+
nicebot: nicebot
|
|
88
|
+
noxtrumbot: noxtrumbot
|
|
89
|
+
nusearch_spider: Nusearch Spider
|
|
90
|
+
nutch_cvs: NutchCVS
|
|
91
|
+
nymesis: Nymesis
|
|
92
|
+
obot: obot
|
|
93
|
+
oegp: oegp
|
|
94
|
+
omgilibot: omgilibot
|
|
95
|
+
omni_explorer_bot: OmniExplorer_Bot
|
|
96
|
+
oozbot: OOZBOT
|
|
97
|
+
orbiter: Orbiter
|
|
98
|
+
page_bites_hyper_bot: PageBitesHyperBot
|
|
99
|
+
peew: Peew
|
|
100
|
+
polybot: polybot
|
|
101
|
+
pompos: Pompos
|
|
102
|
+
post_post: PostPost
|
|
103
|
+
psbot: Psbot
|
|
104
|
+
pyc_url: PycURL
|
|
105
|
+
qseero: Qseero
|
|
106
|
+
radian6: Radian6
|
|
107
|
+
rampy_bot: RAMPyBot
|
|
108
|
+
rufus_bot: RufusBot
|
|
109
|
+
sand_crawler: SandCrawler
|
|
110
|
+
sb_ider: SBIder
|
|
111
|
+
scout_jet: ScoutJet
|
|
112
|
+
scrubby: Scrubby
|
|
113
|
+
search_sight: SearchSight
|
|
114
|
+
seekbot: Seekbot
|
|
115
|
+
semanticdiscovery: semanticdiscovery
|
|
116
|
+
sensis_web_crawler: Sensis Web Crawler
|
|
117
|
+
seo_chat_bot: SEOChat::Bot
|
|
118
|
+
seznam_bot: SeznamBot
|
|
119
|
+
shim_crawler: Shim-Crawler
|
|
120
|
+
shop_wiki: ShopWiki
|
|
121
|
+
shoula_robot: Shoula robot
|
|
122
|
+
silk: silk
|
|
123
|
+
sitebot: Sitebot
|
|
124
|
+
snappy: Snappy
|
|
125
|
+
sogou_spider: sogou spider
|
|
126
|
+
sosospider: Sosospider
|
|
127
|
+
speedy_spider: Speedy Spider
|
|
128
|
+
sqworm: Sqworm
|
|
129
|
+
stack_rambler: StackRambler
|
|
130
|
+
suggybot: suggybot
|
|
131
|
+
survey_bot: SurveyBot
|
|
132
|
+
synoo_bot: SynooBot
|
|
133
|
+
teoma: Teoma
|
|
134
|
+
terrawiz_bot: TerrawizBot
|
|
135
|
+
the_su_bot: TheSuBot
|
|
136
|
+
thumbnail_cz_robot: Thumbnail.CZ robot
|
|
137
|
+
tin_eye: TinEye
|
|
138
|
+
truwo_gps: truwoGPS
|
|
139
|
+
turnitin_bot: TurnitinBot
|
|
140
|
+
tweeted_times_bot: TweetedTimes Bot
|
|
141
|
+
twenga_bot: TwengaBot
|
|
142
|
+
updated: updated
|
|
143
|
+
urlfilebot: Urlfilebot
|
|
144
|
+
vagabondo: Vagabondo
|
|
145
|
+
voila_bot: VoilaBot
|
|
146
|
+
vortex: Vortex
|
|
147
|
+
voyager: voyager
|
|
148
|
+
vyu2: VYU2
|
|
149
|
+
webcollage: webcollage
|
|
150
|
+
websquash_com: Websquash.com
|
|
151
|
+
wf84: wf84
|
|
152
|
+
wo_finde_ich_robot: WoFindeIch Robot
|
|
153
|
+
womlpe_factory: WomlpeFactory
|
|
154
|
+
xaldon_web_spider: Xaldon_WebSpider
|
|
155
|
+
yacy: yacy
|
|
156
|
+
yahoo_slurp: Yahoo! Slurp
|
|
157
|
+
yahoo_slurp_china: Yahoo! Slurp China
|
|
158
|
+
yahoo_seeker: YahooSeeker
|
|
159
|
+
yahoo_seeker_testing: YahooSeeker-Testing
|
|
160
|
+
yandex_bot: YandexBot
|
|
161
|
+
yandex_images: YandexImages
|
|
162
|
+
yasaklibot: Yasaklibot
|
|
163
|
+
yeti: Yeti
|
|
164
|
+
yodao_bot: YodaoBot
|
|
165
|
+
yoogli_fetch_agent: yoogliFetchAgent
|
|
166
|
+
youdao_bot: YoudaoBot
|
|
167
|
+
zao: Zao
|
|
168
|
+
zealbot: Zealbot
|
|
169
|
+
zspider: zspider
|
|
170
|
+
zy_borg: ZyBorg
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: human_power
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.3
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Lasse Bunk
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2013-12-
|
|
11
|
+
date: 2013-12-09 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: bundler
|
|
@@ -90,7 +90,6 @@ files:
|
|
|
90
90
|
- lib/human_power/rails/controller.rb
|
|
91
91
|
- lib/human_power/rails/engine.rb
|
|
92
92
|
- lib/human_power/rule.rb
|
|
93
|
-
- lib/human_power/user_agents.rb
|
|
94
93
|
- lib/human_power/version.rb
|
|
95
94
|
- test/dummy/README.rdoc
|
|
96
95
|
- test/dummy/Rakefile
|
|
@@ -134,6 +133,7 @@ files:
|
|
|
134
133
|
- test/generator_test.rb
|
|
135
134
|
- test/rails/integration_test.rb
|
|
136
135
|
- test/test_helper.rb
|
|
136
|
+
- user_agents.yml
|
|
137
137
|
homepage: https://github.com/lassebunk/human_power
|
|
138
138
|
licenses:
|
|
139
139
|
- MIT
|
|
@@ -154,7 +154,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
154
154
|
version: '0'
|
|
155
155
|
requirements: []
|
|
156
156
|
rubyforge_project:
|
|
157
|
-
rubygems_version: 2.
|
|
157
|
+
rubygems_version: 2.0.3
|
|
158
158
|
signing_key:
|
|
159
159
|
specification_version: 4
|
|
160
160
|
summary: Easy generation of robots.txt. Force the robots into submission!
|