libcraigscrape 0.8.2 → 0.8.3

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.
Files changed (10) hide show
  1. data/CHANGELOG +4 -0
  2. data/Rakefile +1 -1
  3. data/bin/craigwatch +1 -1
  4. data/lib/listings.rb +1 -1
  5. data/lib/posting.rb +18 -7
  6. data/lib/scraper.rb +13 -5
  7. data/test/post_samples/posting1796890756-061710.html +2318 -0
  8. data/test/post_samples/posting1808219423.html +2473 -0
  9. data/test/test_craigslist_posting.rb +56 -1
  10. metadata +43 -17
data/test/test_craigslist_posting.rb CHANGED
@@ -300,7 +300,62 @@ EOD
300
300
  assert_equal [], sfbay_art_1223614914.images
301
301
  assert_equal ["http://images.craigslist.org/3kf3o93laZZZZZZZZZ96fbc594a6ceb1f1025.jpg"], sfbay_art_1223614914.pics
302
302
  assert_equal [:pic], sfbay_art_1223614914.img_types
303
-
303
+ end
304
+
305
+ # This is actually a 'bug' with hpricot itself when the ulimit is set too low.
306
+ # the Easy fix is running "ulimit -s 16384" before the tests. But the better fix was
307
+ # to remove the userbody sending these pages to be parsed by Hpricot
308
+ def test_bugs_found061710
309
+ posting_061710 = CraigScrape::Posting.new relative_uri_for('post_samples/posting1796890756-061710.html')
310
+
311
+ assert_equal false, posting_061710.deleted_by_author?
312
+ assert_equal true, posting_061710.downloaded?
313
+ assert_equal false, posting_061710.flagged_for_removal?
314
+ assert_equal ["south florida craigslist", "miami / dade", "for sale / wanted", "general for sale"], posting_061710.full_section
315
+ assert_equal false, posting_061710.has_img?
316
+ assert_equal false, posting_061710.has_pic?
317
+ assert_equal false, posting_061710.has_pic_or_img?
318
+ assert_equal "*****SOFTWARE**** (Dade/Broward)", posting_061710.header
319
+ assert_equal "*****SOFTWARE**** (Dade/Broward)", posting_061710.header_as_plain
320
+ assert_equal nil, posting_061710.href
321
+ assert_equal [], posting_061710.images
322
+ assert_equal [], posting_061710.img_types
323
+ assert_equal "*****SOFTWARE****", posting_061710.label
324
+ assert_equal "Dade/Broward", posting_061710.location
325
+ assert_equal [], posting_061710.pics
326
+ assert_equal [0, 0, 0, 17, 6, 2010, 4, 168, true, "EDT"], posting_061710.post_date.to_a
327
+ assert_equal [0, 22, 13, 17, 6, 2010, 4, 168, true, "EDT"], posting_061710.post_time.to_a
328
+ assert_equal 1796890756, posting_061710.posting_id
329
+ assert_equal nil, posting_061710.price
330
+ assert_equal nil, posting_061710.reply_to
331
+ assert_equal "general for sale", posting_061710.section
332
+ assert_equal false, posting_061710.system_post?
333
+ assert_equal "*****SOFTWARE****", posting_061710.title
334
+
335
+ posting1808219423 = CraigScrape::Posting.new relative_uri_for('post_samples/posting1808219423.html')
336
+ assert_equal false, posting1808219423.deleted_by_author?
337
+ assert_equal true, posting1808219423.downloaded?
338
+ assert_equal false, posting1808219423.flagged_for_removal?
339
+ assert_equal ["south florida craigslist", "miami / dade", "for sale / wanted", "general for sale"], posting1808219423.full_section
340
+ assert_equal true, posting1808219423.has_img?
341
+ assert_equal false, posting1808219423.has_pic?
342
+ assert_equal true, posting1808219423.has_pic_or_img?
343
+ assert_equal "*Software*AdobeCS5*RosettaStone*AutoCAD*Windows7*Office2010*&* More (Dade/Broward)", posting1808219423.header
344
+ assert_equal "*Software*AdobeCS5*RosettaStone*AutoCAD*Windows7*Office2010*&* More (Dade/Broward)", posting1808219423.header_as_plain
345
+ assert_equal nil, posting1808219423.href
346
+ assert_equal ["http://i800.photobucket.com/albums/yy287/todofull69/Programas/office-2010.jpg", "http://i844.photobucket.com/albums/ab10/fziqe/adobeblogcopy.jpg", "http://i31.photobucket.com/albums/c383/drapizan/RosettaStone.jpg", "http://i1002.photobucket.com/albums/af142/tagurtoast/Windows_7.jpg", "http://i800.photobucket.com/albums/yy287/todofull69/Programas/office-2010.jpg", "http://i844.photobucket.com/albums/ab10/fziqe/adobeblogcopy.jpg", "http://i31.photobucket.com/albums/c383/drapizan/RosettaStone.jpg", "http://i1002.photobucket.com/albums/af142/tagurtoast/Windows_7.jpg", "http://i800.photobucket.com/albums/yy287/todofull69/Programas/office-2010.jpg", "http://i844.photobucket.com/albums/ab10/fziqe/adobeblogcopy.jpg", "http://i31.photobucket.com/albums/c383/drapizan/RosettaStone.jpg", "http://i1002.photobucket.com/albums/af142/tagurtoast/Windows_7.jpg", "http://i800.photobucket.com/albums/yy287/todofull69/Programas/office-2010.jpg", "http://i844.photobucket.com/albums/ab10/fziqe/adobeblogcopy.jpg", "http://i31.photobucket.com/albums/c383/drapizan/RosettaStone.jpg", "http://i1002.photobucket.com/albums/af142/tagurtoast/Windows_7.jpg", "http://i800.photobucket.com/albums/yy287/todofull69/Programas/office-2010.jpg", "http://i844.photobucket.com/albums/ab10/fziqe/adobeblogcopy.jpg", "http://i31.photobucket.com/albums/c383/drapizan/RosettaStone.jpg", "http://i1002.photobucket.com/albums/af142/tagurtoast/Windows_7.jpg"], posting1808219423.images
347
+ assert_equal [:img], posting1808219423.img_types
348
+ assert_equal "*Software*AdobeCS5*RosettaStone*AutoCAD*Windows7*Office2010*&* More", posting1808219423.label
349
+ assert_equal "Dade/Broward", posting1808219423.location
350
+ assert_equal [], posting1808219423.pics
351
+ assert_equal [0, 0, 0, 24, 6, 2010, 4, 175, true, "EDT"], posting1808219423.post_date.to_a
352
+ assert_equal [0, 35, 7, 24, 6, 2010, 4, 175, true, "EDT"], posting1808219423.post_time.to_a
353
+ assert_equal 1808219423, posting1808219423.posting_id
354
+ assert_equal nil, posting1808219423.price
355
+ assert_equal nil, posting1808219423.reply_to
356
+ assert_equal "general for sale", posting1808219423.section
357
+ assert_equal false, posting1808219423.system_post?
358
+ assert_equal "*Software*AdobeCS5*RosettaStone*AutoCAD*Windows7*Office2010*&* More", posting1808219423.title
304
359
  end
305
360
 
306
361
  end
metadata CHANGED
@@ -1,7 +1,13 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: libcraigscrape
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.8.2
4
+ hash: 57
5
+ prerelease: false
6
+ segments:
7
+ - 0
8
+ - 8
9
+ - 3
10
+ version: 0.8.3
5
11
  platform: ruby
6
12
  authors:
7
13
  - Chris DeRose, DeRose Technologies, Inc.
@@ -9,39 +15,51 @@ autorequire:
9
15
  bindir: bin
10
16
  cert_chain: []
11
17
 
12
- date: 2010-04-17 00:00:00 -04:00
18
+ date: 2010-08-02 00:00:00 -04:00
13
19
  default_executable:
14
20
  dependencies:
15
21
  - !ruby/object:Gem::Dependency
16
22
  name: hpricot
17
- type: :runtime
18
- version_requirement:
19
- version_requirements: !ruby/object:Gem::Requirement
23
+ prerelease: false
24
+ requirement: &id001 !ruby/object:Gem::Requirement
25
+ none: false
20
26
  requirements:
21
27
  - - ">="
22
28
  - !ruby/object:Gem::Version
29
+ hash: 3
30
+ segments:
31
+ - 0
23
32
  version: "0"
24
- version:
33
+ type: :runtime
34
+ version_requirements: *id001
25
35
  - !ruby/object:Gem::Dependency
26
36
  name: htmlentities
27
- type: :runtime
28
- version_requirement:
29
- version_requirements: !ruby/object:Gem::Requirement
37
+ prerelease: false
38
+ requirement: &id002 !ruby/object:Gem::Requirement
39
+ none: false
30
40
  requirements:
31
41
  - - ">="
32
42
  - !ruby/object:Gem::Version
43
+ hash: 3
44
+ segments:
45
+ - 0
33
46
  version: "0"
34
- version:
47
+ type: :runtime
48
+ version_requirements: *id002
35
49
  - !ruby/object:Gem::Dependency
36
50
  name: activesupport
37
- type: :runtime
38
- version_requirement:
39
- version_requirements: !ruby/object:Gem::Requirement
51
+ prerelease: false
52
+ requirement: &id003 !ruby/object:Gem::Requirement
53
+ none: false
40
54
  requirements:
41
55
  - - ">="
42
56
  - !ruby/object:Gem::Version
57
+ hash: 3
58
+ segments:
59
+ - 0
43
60
  version: "0"
44
- version:
61
+ type: :runtime
62
+ version_requirements: *id003
45
63
  description: quick, easy, craigslist parsing library that takes the monotony out of working with craigslist posts and listings
46
64
  email: cderose@derosetechnologies.com
47
65
  executables:
@@ -93,7 +111,9 @@ files:
93
111
  - test/post_samples/posting1.html
94
112
  - test/post_samples/posting0.html
95
113
  - test/post_samples/posting5.html
114
+ - test/post_samples/posting1796890756-061710.html
96
115
  - test/post_samples/posting3.html
116
+ - test/post_samples/posting1808219423.html
97
117
  - test/post_samples/sfbay_art_1223614914.html
98
118
  - test/post_samples/this_post_has_been_deleted_by_its_author.html
99
119
  - test/post_samples/1207457727.html
@@ -135,21 +155,27 @@ rdoc_options:
135
155
  require_paths:
136
156
  - lib
137
157
  required_ruby_version: !ruby/object:Gem::Requirement
158
+ none: false
138
159
  requirements:
139
160
  - - ">="
140
161
  - !ruby/object:Gem::Version
162
+ hash: 3
163
+ segments:
164
+ - 0
141
165
  version: "0"
142
- version:
143
166
  required_rubygems_version: !ruby/object:Gem::Requirement
167
+ none: false
144
168
  requirements:
145
169
  - - ">="
146
170
  - !ruby/object:Gem::Version
171
+ hash: 3
172
+ segments:
173
+ - 0
147
174
  version: "0"
148
- version:
149
175
  requirements: []
150
176
 
151
177
  rubyforge_project: libcraigwatch
152
- rubygems_version: 1.3.5
178
+ rubygems_version: 1.3.7
153
179
  signing_key:
154
180
  specification_version: 3
155
181
  summary: quick, easy, craigslist parsing library that takes the monotony out of working with craigslist posts and listings