news_scraper 0.1.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +10 -0
- data/.rubocop.yml +96 -0
- data/CODE_OF_CONDUCT.md +49 -0
- data/Gemfile +3 -0
- data/LICENSE.txt +21 -0
- data/README.md +105 -0
- data/Rakefile +24 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/circle.yml +3 -0
- data/config/article_scrape_patterns.yml +116 -0
- data/config/temp_dirs.yml +4 -0
- data/dev.yml +13 -0
- data/lib/news_scraper/active_support_lite/string.rb +11 -0
- data/lib/news_scraper/cli.rb +106 -0
- data/lib/news_scraper/constants.rb +6 -0
- data/lib/news_scraper/errors.rb +16 -0
- data/lib/news_scraper/extractors/article.rb +17 -0
- data/lib/news_scraper/extractors/google_news_rss.rb +41 -0
- data/lib/news_scraper/extractors_helpers.rb +27 -0
- data/lib/news_scraper/scraper.rb +42 -0
- data/lib/news_scraper/trainer/preset_selector.rb +77 -0
- data/lib/news_scraper/trainer/url_trainer.rb +74 -0
- data/lib/news_scraper/trainer.rb +25 -0
- data/lib/news_scraper/transformers/article.rb +77 -0
- data/lib/news_scraper/transformers/trainer_article.rb +17 -0
- data/lib/news_scraper/uri_parser.rb +41 -0
- data/lib/news_scraper/version.rb +3 -0
- data/lib/news_scraper.rb +42 -0
- data/news_scraper.gemspec +41 -0
- metadata +337 -0
metadata
ADDED
@@ -0,0 +1,337 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: news_scraper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Richard Wu
|
8
|
+
- Julian Nadeau
|
9
|
+
autorequire:
|
10
|
+
bindir: exe
|
11
|
+
cert_chain: []
|
12
|
+
date: 2016-09-18 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: nokogiri
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
requirements:
|
18
|
+
- - "~>"
|
19
|
+
- !ruby/object:Gem::Version
|
20
|
+
version: '1.6'
|
21
|
+
- - ">="
|
22
|
+
- !ruby/object:Gem::Version
|
23
|
+
version: 1.6.8
|
24
|
+
type: :runtime
|
25
|
+
prerelease: false
|
26
|
+
version_requirements: !ruby/object:Gem::Requirement
|
27
|
+
requirements:
|
28
|
+
- - "~>"
|
29
|
+
- !ruby/object:Gem::Version
|
30
|
+
version: '1.6'
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 1.6.8
|
34
|
+
- !ruby/object:Gem::Dependency
|
35
|
+
name: httparty
|
36
|
+
requirement: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0.14'
|
41
|
+
- - ">="
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
version: 0.14.0
|
44
|
+
type: :runtime
|
45
|
+
prerelease: false
|
46
|
+
version_requirements: !ruby/object:Gem::Requirement
|
47
|
+
requirements:
|
48
|
+
- - "~>"
|
49
|
+
- !ruby/object:Gem::Version
|
50
|
+
version: '0.14'
|
51
|
+
- - ">="
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: 0.14.0
|
54
|
+
- !ruby/object:Gem::Dependency
|
55
|
+
name: sanitize
|
56
|
+
requirement: !ruby/object:Gem::Requirement
|
57
|
+
requirements:
|
58
|
+
- - "~>"
|
59
|
+
- !ruby/object:Gem::Version
|
60
|
+
version: '4.2'
|
61
|
+
- - ">="
|
62
|
+
- !ruby/object:Gem::Version
|
63
|
+
version: 4.2.0
|
64
|
+
type: :runtime
|
65
|
+
prerelease: false
|
66
|
+
version_requirements: !ruby/object:Gem::Requirement
|
67
|
+
requirements:
|
68
|
+
- - "~>"
|
69
|
+
- !ruby/object:Gem::Version
|
70
|
+
version: '4.2'
|
71
|
+
- - ">="
|
72
|
+
- !ruby/object:Gem::Version
|
73
|
+
version: 4.2.0
|
74
|
+
- !ruby/object:Gem::Dependency
|
75
|
+
name: ruby-readability
|
76
|
+
requirement: !ruby/object:Gem::Requirement
|
77
|
+
requirements:
|
78
|
+
- - "~>"
|
79
|
+
- !ruby/object:Gem::Version
|
80
|
+
version: '0.7'
|
81
|
+
- - ">="
|
82
|
+
- !ruby/object:Gem::Version
|
83
|
+
version: 0.7.0
|
84
|
+
type: :runtime
|
85
|
+
prerelease: false
|
86
|
+
version_requirements: !ruby/object:Gem::Requirement
|
87
|
+
requirements:
|
88
|
+
- - "~>"
|
89
|
+
- !ruby/object:Gem::Version
|
90
|
+
version: '0.7'
|
91
|
+
- - ">="
|
92
|
+
- !ruby/object:Gem::Version
|
93
|
+
version: 0.7.0
|
94
|
+
- !ruby/object:Gem::Dependency
|
95
|
+
name: htmlbeautifier
|
96
|
+
requirement: !ruby/object:Gem::Requirement
|
97
|
+
requirements:
|
98
|
+
- - "~>"
|
99
|
+
- !ruby/object:Gem::Version
|
100
|
+
version: '1.1'
|
101
|
+
- - ">="
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: 1.1.1
|
104
|
+
type: :runtime
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - "~>"
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '1.1'
|
111
|
+
- - ">="
|
112
|
+
- !ruby/object:Gem::Version
|
113
|
+
version: 1.1.1
|
114
|
+
- !ruby/object:Gem::Dependency
|
115
|
+
name: bundler
|
116
|
+
requirement: !ruby/object:Gem::Requirement
|
117
|
+
requirements:
|
118
|
+
- - "~>"
|
119
|
+
- !ruby/object:Gem::Version
|
120
|
+
version: '1.12'
|
121
|
+
- - ">="
|
122
|
+
- !ruby/object:Gem::Version
|
123
|
+
version: 1.12.0
|
124
|
+
type: :development
|
125
|
+
prerelease: false
|
126
|
+
version_requirements: !ruby/object:Gem::Requirement
|
127
|
+
requirements:
|
128
|
+
- - "~>"
|
129
|
+
- !ruby/object:Gem::Version
|
130
|
+
version: '1.12'
|
131
|
+
- - ">="
|
132
|
+
- !ruby/object:Gem::Version
|
133
|
+
version: 1.12.0
|
134
|
+
- !ruby/object:Gem::Dependency
|
135
|
+
name: rake
|
136
|
+
requirement: !ruby/object:Gem::Requirement
|
137
|
+
requirements:
|
138
|
+
- - "~>"
|
139
|
+
- !ruby/object:Gem::Version
|
140
|
+
version: '10.0'
|
141
|
+
- - ">="
|
142
|
+
- !ruby/object:Gem::Version
|
143
|
+
version: 10.0.0
|
144
|
+
type: :development
|
145
|
+
prerelease: false
|
146
|
+
version_requirements: !ruby/object:Gem::Requirement
|
147
|
+
requirements:
|
148
|
+
- - "~>"
|
149
|
+
- !ruby/object:Gem::Version
|
150
|
+
version: '10.0'
|
151
|
+
- - ">="
|
152
|
+
- !ruby/object:Gem::Version
|
153
|
+
version: 10.0.0
|
154
|
+
- !ruby/object:Gem::Dependency
|
155
|
+
name: minitest
|
156
|
+
requirement: !ruby/object:Gem::Requirement
|
157
|
+
requirements:
|
158
|
+
- - "~>"
|
159
|
+
- !ruby/object:Gem::Version
|
160
|
+
version: '5.9'
|
161
|
+
- - ">="
|
162
|
+
- !ruby/object:Gem::Version
|
163
|
+
version: 5.9.0
|
164
|
+
type: :development
|
165
|
+
prerelease: false
|
166
|
+
version_requirements: !ruby/object:Gem::Requirement
|
167
|
+
requirements:
|
168
|
+
- - "~>"
|
169
|
+
- !ruby/object:Gem::Version
|
170
|
+
version: '5.9'
|
171
|
+
- - ">="
|
172
|
+
- !ruby/object:Gem::Version
|
173
|
+
version: 5.9.0
|
174
|
+
- !ruby/object:Gem::Dependency
|
175
|
+
name: pry
|
176
|
+
requirement: !ruby/object:Gem::Requirement
|
177
|
+
requirements:
|
178
|
+
- - "~>"
|
179
|
+
- !ruby/object:Gem::Version
|
180
|
+
version: '0.10'
|
181
|
+
- - ">="
|
182
|
+
- !ruby/object:Gem::Version
|
183
|
+
version: 0.10.4
|
184
|
+
type: :development
|
185
|
+
prerelease: false
|
186
|
+
version_requirements: !ruby/object:Gem::Requirement
|
187
|
+
requirements:
|
188
|
+
- - "~>"
|
189
|
+
- !ruby/object:Gem::Version
|
190
|
+
version: '0.10'
|
191
|
+
- - ">="
|
192
|
+
- !ruby/object:Gem::Version
|
193
|
+
version: 0.10.4
|
194
|
+
- !ruby/object:Gem::Dependency
|
195
|
+
name: mocha
|
196
|
+
requirement: !ruby/object:Gem::Requirement
|
197
|
+
requirements:
|
198
|
+
- - "~>"
|
199
|
+
- !ruby/object:Gem::Version
|
200
|
+
version: '1.1'
|
201
|
+
- - ">="
|
202
|
+
- !ruby/object:Gem::Version
|
203
|
+
version: 1.1.0
|
204
|
+
type: :development
|
205
|
+
prerelease: false
|
206
|
+
version_requirements: !ruby/object:Gem::Requirement
|
207
|
+
requirements:
|
208
|
+
- - "~>"
|
209
|
+
- !ruby/object:Gem::Version
|
210
|
+
version: '1.1'
|
211
|
+
- - ">="
|
212
|
+
- !ruby/object:Gem::Version
|
213
|
+
version: 1.1.0
|
214
|
+
- !ruby/object:Gem::Dependency
|
215
|
+
name: timecop
|
216
|
+
requirement: !ruby/object:Gem::Requirement
|
217
|
+
requirements:
|
218
|
+
- - "~>"
|
219
|
+
- !ruby/object:Gem::Version
|
220
|
+
version: '0.8'
|
221
|
+
- - ">="
|
222
|
+
- !ruby/object:Gem::Version
|
223
|
+
version: 0.8.0
|
224
|
+
type: :development
|
225
|
+
prerelease: false
|
226
|
+
version_requirements: !ruby/object:Gem::Requirement
|
227
|
+
requirements:
|
228
|
+
- - "~>"
|
229
|
+
- !ruby/object:Gem::Version
|
230
|
+
version: '0.8'
|
231
|
+
- - ">="
|
232
|
+
- !ruby/object:Gem::Version
|
233
|
+
version: 0.8.0
|
234
|
+
- !ruby/object:Gem::Dependency
|
235
|
+
name: rubocop
|
236
|
+
requirement: !ruby/object:Gem::Requirement
|
237
|
+
requirements:
|
238
|
+
- - "~>"
|
239
|
+
- !ruby/object:Gem::Version
|
240
|
+
version: '0.42'
|
241
|
+
- - ">="
|
242
|
+
- !ruby/object:Gem::Version
|
243
|
+
version: 0.42.0
|
244
|
+
type: :development
|
245
|
+
prerelease: false
|
246
|
+
version_requirements: !ruby/object:Gem::Requirement
|
247
|
+
requirements:
|
248
|
+
- - "~>"
|
249
|
+
- !ruby/object:Gem::Version
|
250
|
+
version: '0.42'
|
251
|
+
- - ">="
|
252
|
+
- !ruby/object:Gem::Version
|
253
|
+
version: 0.42.0
|
254
|
+
- !ruby/object:Gem::Dependency
|
255
|
+
name: rdoc
|
256
|
+
requirement: !ruby/object:Gem::Requirement
|
257
|
+
requirements:
|
258
|
+
- - "~>"
|
259
|
+
- !ruby/object:Gem::Version
|
260
|
+
version: '4.2'
|
261
|
+
- - ">="
|
262
|
+
- !ruby/object:Gem::Version
|
263
|
+
version: 4.2.2
|
264
|
+
type: :development
|
265
|
+
prerelease: false
|
266
|
+
version_requirements: !ruby/object:Gem::Requirement
|
267
|
+
requirements:
|
268
|
+
- - "~>"
|
269
|
+
- !ruby/object:Gem::Version
|
270
|
+
version: '4.2'
|
271
|
+
- - ">="
|
272
|
+
- !ruby/object:Gem::Version
|
273
|
+
version: 4.2.2
|
274
|
+
description: A collection of extractors, transformers and loaders for scraping news
|
275
|
+
websites and syndicates.
|
276
|
+
email:
|
277
|
+
- richardwu1997@gmail.com
|
278
|
+
executables: []
|
279
|
+
extensions: []
|
280
|
+
extra_rdoc_files: []
|
281
|
+
files:
|
282
|
+
- ".gitignore"
|
283
|
+
- ".rubocop.yml"
|
284
|
+
- CODE_OF_CONDUCT.md
|
285
|
+
- Gemfile
|
286
|
+
- LICENSE.txt
|
287
|
+
- README.md
|
288
|
+
- Rakefile
|
289
|
+
- bin/console
|
290
|
+
- bin/setup
|
291
|
+
- circle.yml
|
292
|
+
- config/article_scrape_patterns.yml
|
293
|
+
- config/temp_dirs.yml
|
294
|
+
- dev.yml
|
295
|
+
- lib/news_scraper.rb
|
296
|
+
- lib/news_scraper/active_support_lite/string.rb
|
297
|
+
- lib/news_scraper/cli.rb
|
298
|
+
- lib/news_scraper/constants.rb
|
299
|
+
- lib/news_scraper/errors.rb
|
300
|
+
- lib/news_scraper/extractors/article.rb
|
301
|
+
- lib/news_scraper/extractors/google_news_rss.rb
|
302
|
+
- lib/news_scraper/extractors_helpers.rb
|
303
|
+
- lib/news_scraper/scraper.rb
|
304
|
+
- lib/news_scraper/trainer.rb
|
305
|
+
- lib/news_scraper/trainer/preset_selector.rb
|
306
|
+
- lib/news_scraper/trainer/url_trainer.rb
|
307
|
+
- lib/news_scraper/transformers/article.rb
|
308
|
+
- lib/news_scraper/transformers/trainer_article.rb
|
309
|
+
- lib/news_scraper/uri_parser.rb
|
310
|
+
- lib/news_scraper/version.rb
|
311
|
+
- news_scraper.gemspec
|
312
|
+
homepage: https://github.com/richardwu/news_scraper
|
313
|
+
licenses:
|
314
|
+
- MIT
|
315
|
+
metadata:
|
316
|
+
allowed_push_host: https://rubygems.org
|
317
|
+
post_install_message:
|
318
|
+
rdoc_options: []
|
319
|
+
require_paths:
|
320
|
+
- lib
|
321
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
322
|
+
requirements:
|
323
|
+
- - ">="
|
324
|
+
- !ruby/object:Gem::Version
|
325
|
+
version: '0'
|
326
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
327
|
+
requirements:
|
328
|
+
- - ">="
|
329
|
+
- !ruby/object:Gem::Version
|
330
|
+
version: '0'
|
331
|
+
requirements: []
|
332
|
+
rubyforge_project:
|
333
|
+
rubygems_version: 2.5.1
|
334
|
+
signing_key:
|
335
|
+
specification_version: 4
|
336
|
+
summary: Simple ETL news scraper in Ruby
|
337
|
+
test_files: []
|