brilliant_web_scraper 0.1
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 +7 -0
- data/Gemfile +4 -0
- data/README.md +31 -0
- data/brilliant_web_scraper-1.0.0.gem +0 -0
- data/brilliant_web_scraper-1.0.gem +0 -0
- data/brilliant_web_scraper.gemspec +30 -0
- data/lib/brilliant_web_scraper.rb +55 -0
- data/lib/parsers/description_helper.rb +28 -0
- data/lib/parsers/emails.rb +30 -0
- data/lib/parsers/facebook_profile.rb +11 -0
- data/lib/parsers/instagram_profile.rb +11 -0
- data/lib/parsers/linkedin_profile.rb +11 -0
- data/lib/parsers/meta_description.rb +13 -0
- data/lib/parsers/org_description.rb +13 -0
- data/lib/parsers/phone_numbers.rb +34 -0
- data/lib/parsers/pinterest_profile.rb +11 -0
- data/lib/parsers/redirected_to.rb +29 -0
- data/lib/parsers/title.rb +13 -0
- data/lib/parsers/twitter_description.rb +13 -0
- data/lib/parsers/twitter_profile.rb +11 -0
- data/lib/parsers/unescape_html_helper.rb +17 -0
- data/lib/parsers/vimeo_profile.rb +11 -0
- data/lib/parsers/youtube_channel.rb +29 -0
- data/lib/scraper/errors.rb +19 -0
- data/lib/scraper/scrape_exceptions.rb +49 -0
- data/lib/scraper/scrape_helper.rb +59 -0
- data/lib/scraper/scrape_request.rb +29 -0
- data/lib/version.rb +6 -0
- data/spec/lib/parsers/description_helper_spec.rb +24 -0
- data/spec/lib/parsers/emails_spec.rb +60 -0
- data/spec/lib/parsers/facebook_profile_spec.rb +77 -0
- data/spec/lib/parsers/instagram_profile_spec.rb +45 -0
- data/spec/lib/parsers/linkedin_profile_spec.rb +43 -0
- data/spec/lib/parsers/meta_description_spec.rb +321 -0
- data/spec/lib/parsers/org_description_spec.rb +316 -0
- data/spec/lib/parsers/phone_numbers_spec.rb +69 -0
- data/spec/lib/parsers/pinterest_profile_spec.rb +44 -0
- data/spec/lib/parsers/redirected_to_spec.rb +207 -0
- data/spec/lib/parsers/title_spec.rb +87 -0
- data/spec/lib/parsers/twitter_description_spec.rb +314 -0
- data/spec/lib/parsers/twitter_profile_spec.rb +59 -0
- data/spec/lib/parsers/unescape_html_helper_spec.rb +0 -0
- data/spec/lib/parsers/vimeo_profile_spec.rb +43 -0
- data/spec/lib/parsers/youtube_profile_spec.rb +82 -0
- data/spec/lib/scraper/brilliant_web_scrape_test.rb +66 -0
- data/spec/lib/scraper/scrape_request_test.rb +34 -0
- data/spec/spec_helper.rb +111 -0
- data/spec/vcr/encoding_compatibility_error.yml +316 -0
- data/spec/vcr/invalid_byte_sequence_utf_8.yml +2383 -0
- data/spec/vcr/no_valid_data_to_scrape.yml +109 -0
- data/spec/vcr/non_html_scrape.yml +163 -0
- data/spec/vcr/valid_scrape_response.yml +696 -0
- metadata +250 -0
metadata
ADDED
|
@@ -0,0 +1,250 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: brilliant_web_scraper
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: '0.1'
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Kotu Bhaskara Rao
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
date: 2019-08-11 00:00:00.000000000 Z
|
|
12
|
+
dependencies:
|
|
13
|
+
- !ruby/object:Gem::Dependency
|
|
14
|
+
name: nesty
|
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
|
16
|
+
requirements:
|
|
17
|
+
- - "~>"
|
|
18
|
+
- !ruby/object:Gem::Version
|
|
19
|
+
version: '1.0'
|
|
20
|
+
- - ">="
|
|
21
|
+
- !ruby/object:Gem::Version
|
|
22
|
+
version: 1.0.1
|
|
23
|
+
type: :runtime
|
|
24
|
+
prerelease: false
|
|
25
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
26
|
+
requirements:
|
|
27
|
+
- - "~>"
|
|
28
|
+
- !ruby/object:Gem::Version
|
|
29
|
+
version: '1.0'
|
|
30
|
+
- - ">="
|
|
31
|
+
- !ruby/object:Gem::Version
|
|
32
|
+
version: 1.0.1
|
|
33
|
+
- !ruby/object:Gem::Dependency
|
|
34
|
+
name: rest-client
|
|
35
|
+
requirement: !ruby/object:Gem::Requirement
|
|
36
|
+
requirements:
|
|
37
|
+
- - "~>"
|
|
38
|
+
- !ruby/object:Gem::Version
|
|
39
|
+
version: '2.0'
|
|
40
|
+
- - ">="
|
|
41
|
+
- !ruby/object:Gem::Version
|
|
42
|
+
version: 2.0.2
|
|
43
|
+
type: :runtime
|
|
44
|
+
prerelease: false
|
|
45
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
46
|
+
requirements:
|
|
47
|
+
- - "~>"
|
|
48
|
+
- !ruby/object:Gem::Version
|
|
49
|
+
version: '2.0'
|
|
50
|
+
- - ">="
|
|
51
|
+
- !ruby/object:Gem::Version
|
|
52
|
+
version: 2.0.2
|
|
53
|
+
- !ruby/object:Gem::Dependency
|
|
54
|
+
name: nesty
|
|
55
|
+
requirement: !ruby/object:Gem::Requirement
|
|
56
|
+
requirements:
|
|
57
|
+
- - "~>"
|
|
58
|
+
- !ruby/object:Gem::Version
|
|
59
|
+
version: '1.0'
|
|
60
|
+
- - ">="
|
|
61
|
+
- !ruby/object:Gem::Version
|
|
62
|
+
version: 1.0.1
|
|
63
|
+
type: :development
|
|
64
|
+
prerelease: false
|
|
65
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
66
|
+
requirements:
|
|
67
|
+
- - "~>"
|
|
68
|
+
- !ruby/object:Gem::Version
|
|
69
|
+
version: '1.0'
|
|
70
|
+
- - ">="
|
|
71
|
+
- !ruby/object:Gem::Version
|
|
72
|
+
version: 1.0.1
|
|
73
|
+
- !ruby/object:Gem::Dependency
|
|
74
|
+
name: pry
|
|
75
|
+
requirement: !ruby/object:Gem::Requirement
|
|
76
|
+
requirements:
|
|
77
|
+
- - "~>"
|
|
78
|
+
- !ruby/object:Gem::Version
|
|
79
|
+
version: 0.12.2
|
|
80
|
+
type: :development
|
|
81
|
+
prerelease: false
|
|
82
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
83
|
+
requirements:
|
|
84
|
+
- - "~>"
|
|
85
|
+
- !ruby/object:Gem::Version
|
|
86
|
+
version: 0.12.2
|
|
87
|
+
- !ruby/object:Gem::Dependency
|
|
88
|
+
name: rest-client
|
|
89
|
+
requirement: !ruby/object:Gem::Requirement
|
|
90
|
+
requirements:
|
|
91
|
+
- - "~>"
|
|
92
|
+
- !ruby/object:Gem::Version
|
|
93
|
+
version: '2.0'
|
|
94
|
+
- - ">="
|
|
95
|
+
- !ruby/object:Gem::Version
|
|
96
|
+
version: 2.0.2
|
|
97
|
+
type: :development
|
|
98
|
+
prerelease: false
|
|
99
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
100
|
+
requirements:
|
|
101
|
+
- - "~>"
|
|
102
|
+
- !ruby/object:Gem::Version
|
|
103
|
+
version: '2.0'
|
|
104
|
+
- - ">="
|
|
105
|
+
- !ruby/object:Gem::Version
|
|
106
|
+
version: 2.0.2
|
|
107
|
+
- !ruby/object:Gem::Dependency
|
|
108
|
+
name: rspec
|
|
109
|
+
requirement: !ruby/object:Gem::Requirement
|
|
110
|
+
requirements:
|
|
111
|
+
- - "~>"
|
|
112
|
+
- !ruby/object:Gem::Version
|
|
113
|
+
version: '3.5'
|
|
114
|
+
type: :development
|
|
115
|
+
prerelease: false
|
|
116
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
117
|
+
requirements:
|
|
118
|
+
- - "~>"
|
|
119
|
+
- !ruby/object:Gem::Version
|
|
120
|
+
version: '3.5'
|
|
121
|
+
- !ruby/object:Gem::Dependency
|
|
122
|
+
name: rubocop
|
|
123
|
+
requirement: !ruby/object:Gem::Requirement
|
|
124
|
+
requirements:
|
|
125
|
+
- - "~>"
|
|
126
|
+
- !ruby/object:Gem::Version
|
|
127
|
+
version: 0.73.0
|
|
128
|
+
type: :development
|
|
129
|
+
prerelease: false
|
|
130
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
131
|
+
requirements:
|
|
132
|
+
- - "~>"
|
|
133
|
+
- !ruby/object:Gem::Version
|
|
134
|
+
version: 0.73.0
|
|
135
|
+
- !ruby/object:Gem::Dependency
|
|
136
|
+
name: vcr
|
|
137
|
+
requirement: !ruby/object:Gem::Requirement
|
|
138
|
+
requirements:
|
|
139
|
+
- - "~>"
|
|
140
|
+
- !ruby/object:Gem::Version
|
|
141
|
+
version: '3.0'
|
|
142
|
+
- - ">="
|
|
143
|
+
- !ruby/object:Gem::Version
|
|
144
|
+
version: 3.0.1
|
|
145
|
+
type: :development
|
|
146
|
+
prerelease: false
|
|
147
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
148
|
+
requirements:
|
|
149
|
+
- - "~>"
|
|
150
|
+
- !ruby/object:Gem::Version
|
|
151
|
+
version: '3.0'
|
|
152
|
+
- - ">="
|
|
153
|
+
- !ruby/object:Gem::Version
|
|
154
|
+
version: 3.0.1
|
|
155
|
+
- !ruby/object:Gem::Dependency
|
|
156
|
+
name: webmock
|
|
157
|
+
requirement: !ruby/object:Gem::Requirement
|
|
158
|
+
requirements:
|
|
159
|
+
- - "~>"
|
|
160
|
+
- !ruby/object:Gem::Version
|
|
161
|
+
version: '2.1'
|
|
162
|
+
type: :development
|
|
163
|
+
prerelease: false
|
|
164
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
165
|
+
requirements:
|
|
166
|
+
- - "~>"
|
|
167
|
+
- !ruby/object:Gem::Version
|
|
168
|
+
version: '2.1'
|
|
169
|
+
description: Scrapes data such as description, social profiles, contact details
|
|
170
|
+
email: bkotu6717@gmail.com
|
|
171
|
+
executables: []
|
|
172
|
+
extensions: []
|
|
173
|
+
extra_rdoc_files: []
|
|
174
|
+
files:
|
|
175
|
+
- Gemfile
|
|
176
|
+
- README.md
|
|
177
|
+
- brilliant_web_scraper-1.0.0.gem
|
|
178
|
+
- brilliant_web_scraper-1.0.gem
|
|
179
|
+
- brilliant_web_scraper.gemspec
|
|
180
|
+
- lib/brilliant_web_scraper.rb
|
|
181
|
+
- lib/parsers/description_helper.rb
|
|
182
|
+
- lib/parsers/emails.rb
|
|
183
|
+
- lib/parsers/facebook_profile.rb
|
|
184
|
+
- lib/parsers/instagram_profile.rb
|
|
185
|
+
- lib/parsers/linkedin_profile.rb
|
|
186
|
+
- lib/parsers/meta_description.rb
|
|
187
|
+
- lib/parsers/org_description.rb
|
|
188
|
+
- lib/parsers/phone_numbers.rb
|
|
189
|
+
- lib/parsers/pinterest_profile.rb
|
|
190
|
+
- lib/parsers/redirected_to.rb
|
|
191
|
+
- lib/parsers/title.rb
|
|
192
|
+
- lib/parsers/twitter_description.rb
|
|
193
|
+
- lib/parsers/twitter_profile.rb
|
|
194
|
+
- lib/parsers/unescape_html_helper.rb
|
|
195
|
+
- lib/parsers/vimeo_profile.rb
|
|
196
|
+
- lib/parsers/youtube_channel.rb
|
|
197
|
+
- lib/scraper/errors.rb
|
|
198
|
+
- lib/scraper/scrape_exceptions.rb
|
|
199
|
+
- lib/scraper/scrape_helper.rb
|
|
200
|
+
- lib/scraper/scrape_request.rb
|
|
201
|
+
- lib/version.rb
|
|
202
|
+
- spec/lib/parsers/description_helper_spec.rb
|
|
203
|
+
- spec/lib/parsers/emails_spec.rb
|
|
204
|
+
- spec/lib/parsers/facebook_profile_spec.rb
|
|
205
|
+
- spec/lib/parsers/instagram_profile_spec.rb
|
|
206
|
+
- spec/lib/parsers/linkedin_profile_spec.rb
|
|
207
|
+
- spec/lib/parsers/meta_description_spec.rb
|
|
208
|
+
- spec/lib/parsers/org_description_spec.rb
|
|
209
|
+
- spec/lib/parsers/phone_numbers_spec.rb
|
|
210
|
+
- spec/lib/parsers/pinterest_profile_spec.rb
|
|
211
|
+
- spec/lib/parsers/redirected_to_spec.rb
|
|
212
|
+
- spec/lib/parsers/title_spec.rb
|
|
213
|
+
- spec/lib/parsers/twitter_description_spec.rb
|
|
214
|
+
- spec/lib/parsers/twitter_profile_spec.rb
|
|
215
|
+
- spec/lib/parsers/unescape_html_helper_spec.rb
|
|
216
|
+
- spec/lib/parsers/vimeo_profile_spec.rb
|
|
217
|
+
- spec/lib/parsers/youtube_profile_spec.rb
|
|
218
|
+
- spec/lib/scraper/brilliant_web_scrape_test.rb
|
|
219
|
+
- spec/lib/scraper/scrape_request_test.rb
|
|
220
|
+
- spec/spec_helper.rb
|
|
221
|
+
- spec/vcr/encoding_compatibility_error.yml
|
|
222
|
+
- spec/vcr/invalid_byte_sequence_utf_8.yml
|
|
223
|
+
- spec/vcr/no_valid_data_to_scrape.yml
|
|
224
|
+
- spec/vcr/non_html_scrape.yml
|
|
225
|
+
- spec/vcr/valid_scrape_response.yml
|
|
226
|
+
homepage: https://github.com/bkotu6717/brilliant_web_scraper
|
|
227
|
+
licenses:
|
|
228
|
+
- Nonstandard
|
|
229
|
+
metadata: {}
|
|
230
|
+
post_install_message:
|
|
231
|
+
rdoc_options: []
|
|
232
|
+
require_paths:
|
|
233
|
+
- lib
|
|
234
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
235
|
+
requirements:
|
|
236
|
+
- - ">="
|
|
237
|
+
- !ruby/object:Gem::Version
|
|
238
|
+
version: 2.3.0
|
|
239
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
240
|
+
requirements:
|
|
241
|
+
- - ">="
|
|
242
|
+
- !ruby/object:Gem::Version
|
|
243
|
+
version: '0'
|
|
244
|
+
requirements: []
|
|
245
|
+
rubyforge_project:
|
|
246
|
+
rubygems_version: 2.5.1
|
|
247
|
+
signing_key:
|
|
248
|
+
specification_version: 4
|
|
249
|
+
summary: A decent web scraping ruby library!
|
|
250
|
+
test_files: []
|