doctor_scrape 0.0.2

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.
Files changed (54) hide show
  1. data/.gitignore +18 -0
  2. data/.rbenv-version +1 -0
  3. data/.rspec +2 -0
  4. data/Gemfile +4 -0
  5. data/Guardfile +10 -0
  6. data/LICENSE +22 -0
  7. data/README.md +78 -0
  8. data/Rakefile +14 -0
  9. data/doctor_scrape.gemspec +35 -0
  10. data/lib/doctor_scrape/data.rb +12 -0
  11. data/lib/doctor_scrape/redirect_follower.rb +29 -0
  12. data/lib/doctor_scrape/scraper/base.rb +50 -0
  13. data/lib/doctor_scrape/scraper/bora.rb +25 -0
  14. data/lib/doctor_scrape/scraper/diva.rb +16 -0
  15. data/lib/doctor_scrape/scraper/duo.rb +32 -0
  16. data/lib/doctor_scrape/scraper/meta.rb +39 -0
  17. data/lib/doctor_scrape/scraper/unknown.rb +20 -0
  18. data/lib/doctor_scrape/search.rb +42 -0
  19. data/lib/doctor_scrape/version.rb +3 -0
  20. data/lib/doctor_scrape.rb +37 -0
  21. data/spec/cassettes/brage_bibsys_no_hibo_handle_URN_NBN_no-bibsys_brage_17854.yml +624 -0
  22. data/spec/cassettes/brage_bibsys_no_nhh_handle_URN_NBN_no-bibsys_brage_22813.yml +535 -0
  23. data/spec/cassettes/brage_bibsys_no_nhh_handle_URN_NBN_no-bibsys_brage_24121.yml +388 -0
  24. data/spec/cassettes/https___bora_hib_no_handle_10049_234.yml +429 -0
  25. data/spec/cassettes/https___bora_hib_no_handle_10049_330.yml +347 -0
  26. data/spec/cassettes/https___bora_uib_no_handle_1956_3282.yml +682 -0
  27. data/spec/cassettes/nora_search.yml +795 -0
  28. data/spec/cassettes/ntnu.diva-portal.org_smash_record.jsf?searchId=1&pid=diva2:122798.yml +398 -0
  29. data/spec/cassettes/ntnu_diva-portal_org_smash_record_jsf_searchId_1_pid_diva2_122794.yml +398 -0
  30. data/spec/cassettes/ntnu_diva-portal_org_smash_record_jsf_searchId_1_pid_diva2_122798.yml +487 -0
  31. data/spec/cassettes/www_duo_uio_no_sok_work_html_WORKID_112975.yml +248 -0
  32. data/spec/cassettes/www_duo_uio_no_sok_work_html_WORKID_149776.yml +240 -0
  33. data/spec/cassettes/www_ub_uit_no_munin_handle_10037_3822.yml +602 -0
  34. data/spec/cassettes/www_ub_uit_no_munin_handle_10037_3826.yml +534 -0
  35. data/spec/data_spec.rb +22 -0
  36. data/spec/parse/bibsys_spec.rb +40 -0
  37. data/spec/parse/bora_hib_spec.rb +29 -0
  38. data/spec/parse/bora_uib_spec.rb +18 -0
  39. data/spec/parse/diva_spec.rb +29 -0
  40. data/spec/parse/duo_spec.rb +29 -0
  41. data/spec/parse/munin_spec.rb +30 -0
  42. data/spec/redirect_follower_spec.rb +37 -0
  43. data/spec/scraper_spec.rb +43 -0
  44. data/spec/scrapers/base_spec.rb +6 -0
  45. data/spec/scrapers/bora_spec.rb +6 -0
  46. data/spec/scrapers/diva_spec.rb +6 -0
  47. data/spec/scrapers/duo_spec.rb +6 -0
  48. data/spec/scrapers/meta_spec.rb +6 -0
  49. data/spec/scrapers/unknown_spec.rb +18 -0
  50. data/spec/search_spec.rb +111 -0
  51. data/spec/shared/scraper.rb +62 -0
  52. data/spec/spec_helper.rb +29 -0
  53. data/spec/support/setup_scraper.rb +8 -0
  54. metadata +292 -0
metadata ADDED
@@ -0,0 +1,292 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: doctor_scrape
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.0.2
5
+ prerelease:
6
+ platform: ruby
7
+ authors:
8
+ - Gudleik Rasch
9
+ autorequire:
10
+ bindir: bin
11
+ cert_chain: []
12
+ date: 2012-02-27 00:00:00.000000000 Z
13
+ dependencies:
14
+ - !ruby/object:Gem::Dependency
15
+ name: mechanize
16
+ requirement: &70265938257900 !ruby/object:Gem::Requirement
17
+ none: false
18
+ requirements:
19
+ - - ~>
20
+ - !ruby/object:Gem::Version
21
+ version: '2.3'
22
+ type: :runtime
23
+ prerelease: false
24
+ version_requirements: *70265938257900
25
+ - !ruby/object:Gem::Dependency
26
+ name: rspec
27
+ requirement: &70265938257380 !ruby/object:Gem::Requirement
28
+ none: false
29
+ requirements:
30
+ - - ~>
31
+ - !ruby/object:Gem::Version
32
+ version: 2.8.0
33
+ type: :development
34
+ prerelease: false
35
+ version_requirements: *70265938257380
36
+ - !ruby/object:Gem::Dependency
37
+ name: vcr
38
+ requirement: &70265938256900 !ruby/object:Gem::Requirement
39
+ none: false
40
+ requirements:
41
+ - - ~>
42
+ - !ruby/object:Gem::Version
43
+ version: 2.0.0.rc1
44
+ type: :development
45
+ prerelease: false
46
+ version_requirements: *70265938256900
47
+ - !ruby/object:Gem::Dependency
48
+ name: webmock
49
+ requirement: &70265938256420 !ruby/object:Gem::Requirement
50
+ none: false
51
+ requirements:
52
+ - - <
53
+ - !ruby/object:Gem::Version
54
+ version: '1.8'
55
+ type: :development
56
+ prerelease: false
57
+ version_requirements: *70265938256420
58
+ - !ruby/object:Gem::Dependency
59
+ name: guard
60
+ requirement: &70265938255940 !ruby/object:Gem::Requirement
61
+ none: false
62
+ requirements:
63
+ - - ~>
64
+ - !ruby/object:Gem::Version
65
+ version: 1.0.0
66
+ type: :development
67
+ prerelease: false
68
+ version_requirements: *70265938255940
69
+ - !ruby/object:Gem::Dependency
70
+ name: guard-rspec
71
+ requirement: &70265938255460 !ruby/object:Gem::Requirement
72
+ none: false
73
+ requirements:
74
+ - - ~>
75
+ - !ruby/object:Gem::Version
76
+ version: 0.6.0
77
+ type: :development
78
+ prerelease: false
79
+ version_requirements: *70265938255460
80
+ - !ruby/object:Gem::Dependency
81
+ name: ruby_gntp
82
+ requirement: &70265938254980 !ruby/object:Gem::Requirement
83
+ none: false
84
+ requirements:
85
+ - - ~>
86
+ - !ruby/object:Gem::Version
87
+ version: 0.3.4
88
+ type: :development
89
+ prerelease: false
90
+ version_requirements: *70265938254980
91
+ - !ruby/object:Gem::Dependency
92
+ name: rb-fsevent
93
+ requirement: &70265938254500 !ruby/object:Gem::Requirement
94
+ none: false
95
+ requirements:
96
+ - - ~>
97
+ - !ruby/object:Gem::Version
98
+ version: 0.9.0
99
+ type: :development
100
+ prerelease: false
101
+ version_requirements: *70265938254500
102
+ - !ruby/object:Gem::Dependency
103
+ name: pry
104
+ requirement: &70265938254020 !ruby/object:Gem::Requirement
105
+ none: false
106
+ requirements:
107
+ - - ~>
108
+ - !ruby/object:Gem::Version
109
+ version: 0.9.8.2
110
+ type: :development
111
+ prerelease: false
112
+ version_requirements: *70265938254020
113
+ - !ruby/object:Gem::Dependency
114
+ name: pry-doc
115
+ requirement: &70265938253540 !ruby/object:Gem::Requirement
116
+ none: false
117
+ requirements:
118
+ - - ~>
119
+ - !ruby/object:Gem::Version
120
+ version: 0.4.0
121
+ type: :development
122
+ prerelease: false
123
+ version_requirements: *70265938253540
124
+ - !ruby/object:Gem::Dependency
125
+ name: pry-editline
126
+ requirement: &70265938253060 !ruby/object:Gem::Requirement
127
+ none: false
128
+ requirements:
129
+ - - ~>
130
+ - !ruby/object:Gem::Version
131
+ version: 1.1.1
132
+ type: :development
133
+ prerelease: false
134
+ version_requirements: *70265938253060
135
+ - !ruby/object:Gem::Dependency
136
+ name: hirb
137
+ requirement: &70265938252580 !ruby/object:Gem::Requirement
138
+ none: false
139
+ requirements:
140
+ - - ~>
141
+ - !ruby/object:Gem::Version
142
+ version: 0.6.0
143
+ type: :development
144
+ prerelease: false
145
+ version_requirements: *70265938252580
146
+ - !ruby/object:Gem::Dependency
147
+ name: awesome_print
148
+ requirement: &70265938252100 !ruby/object:Gem::Requirement
149
+ none: false
150
+ requirements:
151
+ - - ~>
152
+ - !ruby/object:Gem::Version
153
+ version: 1.0.2
154
+ type: :development
155
+ prerelease: false
156
+ version_requirements: *70265938252100
157
+ - !ruby/object:Gem::Dependency
158
+ name: simplecov
159
+ requirement: &70265938251620 !ruby/object:Gem::Requirement
160
+ none: false
161
+ requirements:
162
+ - - ~>
163
+ - !ruby/object:Gem::Version
164
+ version: 0.6.0
165
+ type: :development
166
+ prerelease: false
167
+ version_requirements: *70265938251620
168
+ description: Library for scraping norwegian doctoral dissertations
169
+ email:
170
+ - gudleik@gmail.com
171
+ executables: []
172
+ extensions: []
173
+ extra_rdoc_files: []
174
+ files:
175
+ - .gitignore
176
+ - .rbenv-version
177
+ - .rspec
178
+ - Gemfile
179
+ - Guardfile
180
+ - LICENSE
181
+ - README.md
182
+ - Rakefile
183
+ - doctor_scrape.gemspec
184
+ - lib/doctor_scrape.rb
185
+ - lib/doctor_scrape/data.rb
186
+ - lib/doctor_scrape/redirect_follower.rb
187
+ - lib/doctor_scrape/scraper/base.rb
188
+ - lib/doctor_scrape/scraper/bora.rb
189
+ - lib/doctor_scrape/scraper/diva.rb
190
+ - lib/doctor_scrape/scraper/duo.rb
191
+ - lib/doctor_scrape/scraper/meta.rb
192
+ - lib/doctor_scrape/scraper/unknown.rb
193
+ - lib/doctor_scrape/search.rb
194
+ - lib/doctor_scrape/version.rb
195
+ - spec/cassettes/brage_bibsys_no_hibo_handle_URN_NBN_no-bibsys_brage_17854.yml
196
+ - spec/cassettes/brage_bibsys_no_nhh_handle_URN_NBN_no-bibsys_brage_22813.yml
197
+ - spec/cassettes/brage_bibsys_no_nhh_handle_URN_NBN_no-bibsys_brage_24121.yml
198
+ - spec/cassettes/https___bora_hib_no_handle_10049_234.yml
199
+ - spec/cassettes/https___bora_hib_no_handle_10049_330.yml
200
+ - spec/cassettes/https___bora_uib_no_handle_1956_3282.yml
201
+ - spec/cassettes/nora_search.yml
202
+ - spec/cassettes/ntnu.diva-portal.org_smash_record.jsf?searchId=1&pid=diva2:122798.yml
203
+ - spec/cassettes/ntnu_diva-portal_org_smash_record_jsf_searchId_1_pid_diva2_122794.yml
204
+ - spec/cassettes/ntnu_diva-portal_org_smash_record_jsf_searchId_1_pid_diva2_122798.yml
205
+ - spec/cassettes/www_duo_uio_no_sok_work_html_WORKID_112975.yml
206
+ - spec/cassettes/www_duo_uio_no_sok_work_html_WORKID_149776.yml
207
+ - spec/cassettes/www_ub_uit_no_munin_handle_10037_3822.yml
208
+ - spec/cassettes/www_ub_uit_no_munin_handle_10037_3826.yml
209
+ - spec/data_spec.rb
210
+ - spec/parse/bibsys_spec.rb
211
+ - spec/parse/bora_hib_spec.rb
212
+ - spec/parse/bora_uib_spec.rb
213
+ - spec/parse/diva_spec.rb
214
+ - spec/parse/duo_spec.rb
215
+ - spec/parse/munin_spec.rb
216
+ - spec/redirect_follower_spec.rb
217
+ - spec/scraper_spec.rb
218
+ - spec/scrapers/base_spec.rb
219
+ - spec/scrapers/bora_spec.rb
220
+ - spec/scrapers/diva_spec.rb
221
+ - spec/scrapers/duo_spec.rb
222
+ - spec/scrapers/meta_spec.rb
223
+ - spec/scrapers/unknown_spec.rb
224
+ - spec/search_spec.rb
225
+ - spec/shared/scraper.rb
226
+ - spec/spec_helper.rb
227
+ - spec/support/setup_scraper.rb
228
+ homepage: https://github.com/Skalar/doctor_scrape
229
+ licenses: []
230
+ post_install_message:
231
+ rdoc_options: []
232
+ require_paths:
233
+ - lib
234
+ required_ruby_version: !ruby/object:Gem::Requirement
235
+ none: false
236
+ requirements:
237
+ - - ! '>='
238
+ - !ruby/object:Gem::Version
239
+ version: '0'
240
+ segments:
241
+ - 0
242
+ hash: 3232288903732204116
243
+ required_rubygems_version: !ruby/object:Gem::Requirement
244
+ none: false
245
+ requirements:
246
+ - - ! '>='
247
+ - !ruby/object:Gem::Version
248
+ version: '0'
249
+ segments:
250
+ - 0
251
+ hash: 3232288903732204116
252
+ requirements: []
253
+ rubyforge_project:
254
+ rubygems_version: 1.8.11
255
+ signing_key:
256
+ specification_version: 3
257
+ summary: Library for scraping norwegian doctoral dissertations
258
+ test_files:
259
+ - spec/cassettes/brage_bibsys_no_hibo_handle_URN_NBN_no-bibsys_brage_17854.yml
260
+ - spec/cassettes/brage_bibsys_no_nhh_handle_URN_NBN_no-bibsys_brage_22813.yml
261
+ - spec/cassettes/brage_bibsys_no_nhh_handle_URN_NBN_no-bibsys_brage_24121.yml
262
+ - spec/cassettes/https___bora_hib_no_handle_10049_234.yml
263
+ - spec/cassettes/https___bora_hib_no_handle_10049_330.yml
264
+ - spec/cassettes/https___bora_uib_no_handle_1956_3282.yml
265
+ - spec/cassettes/nora_search.yml
266
+ - spec/cassettes/ntnu.diva-portal.org_smash_record.jsf?searchId=1&pid=diva2:122798.yml
267
+ - spec/cassettes/ntnu_diva-portal_org_smash_record_jsf_searchId_1_pid_diva2_122794.yml
268
+ - spec/cassettes/ntnu_diva-portal_org_smash_record_jsf_searchId_1_pid_diva2_122798.yml
269
+ - spec/cassettes/www_duo_uio_no_sok_work_html_WORKID_112975.yml
270
+ - spec/cassettes/www_duo_uio_no_sok_work_html_WORKID_149776.yml
271
+ - spec/cassettes/www_ub_uit_no_munin_handle_10037_3822.yml
272
+ - spec/cassettes/www_ub_uit_no_munin_handle_10037_3826.yml
273
+ - spec/data_spec.rb
274
+ - spec/parse/bibsys_spec.rb
275
+ - spec/parse/bora_hib_spec.rb
276
+ - spec/parse/bora_uib_spec.rb
277
+ - spec/parse/diva_spec.rb
278
+ - spec/parse/duo_spec.rb
279
+ - spec/parse/munin_spec.rb
280
+ - spec/redirect_follower_spec.rb
281
+ - spec/scraper_spec.rb
282
+ - spec/scrapers/base_spec.rb
283
+ - spec/scrapers/bora_spec.rb
284
+ - spec/scrapers/diva_spec.rb
285
+ - spec/scrapers/duo_spec.rb
286
+ - spec/scrapers/meta_spec.rb
287
+ - spec/scrapers/unknown_spec.rb
288
+ - spec/search_spec.rb
289
+ - spec/shared/scraper.rb
290
+ - spec/spec_helper.rb
291
+ - spec/support/setup_scraper.rb
292
+ has_rdoc: