libcraigscrape 1.0 → 1.1.0
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.
- data/CHANGELOG +12 -1
- data/Gemfile +12 -0
- data/Rakefile +1 -54
- data/bin/craig_report_schema.yml +4 -1
- data/bin/craigwatch +148 -146
- data/bin/report_mailer/report.html.erb +20 -0
- data/bin/report_mailer/{craigslist_report.plain.erb → report.text.erb} +7 -6
- data/lib/geo_listings.rb +1 -1
- data/lib/libcraigscrape.rb +52 -59
- data/lib/listings.rb +75 -39
- data/lib/posting.rb +120 -63
- data/lib/scraper.rb +43 -63
- data/spec/assets/geolisting_iso_us_120412.html +441 -0
- data/spec/assets/listing_cta_ftl_112612.html +1470 -0
- data/spec/assets/listing_rea_miami_123012.html +1397 -0
- data/spec/assets/listing_search_ppa_nyc_121212.html +1584 -0
- data/spec/assets/posting_daytona_art_120512-2.html +160 -0
- data/spec/assets/posting_daytona_art_120512.html +153 -0
- data/spec/assets/posting_mdc_cto_ftl_112612.html +170 -0
- data/spec/assets/posting_mdc_reb_120612.html +183 -0
- data/spec/assets/posting_sfbay_1226.html +157 -0
- data/spec/assets/posting_sya_121012-2.html +122 -0
- data/spec/assets/posting_sya_121012.html +165 -0
- data/spec/assets/this_post_has_expired_old.html +48 -0
- data/spec/geolisting_spec.rb +9 -0
- data/spec/listings_spec.rb +77 -0
- data/spec/postings_spec.rb +157 -0
- data/spec/spec_helper.rb +8 -0
- data/test/test_craigslist_geolisting.rb +5 -5
- data/test/test_craigslist_listing.rb +30 -30
- data/test/test_craigslist_posting.rb +25 -145
- metadata +200 -114
- data/bin/report_mailer/craigslist_report.html.erb +0 -17
metadata
CHANGED
@@ -1,220 +1,306 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: libcraigscrape
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
hash: 15
|
5
4
|
prerelease: false
|
6
5
|
segments:
|
7
6
|
- 1
|
7
|
+
- 1
|
8
8
|
- 0
|
9
|
-
version:
|
9
|
+
version: 1.1.0
|
10
10
|
platform: ruby
|
11
11
|
authors:
|
12
|
-
- Chris DeRose
|
12
|
+
- Chris DeRose
|
13
13
|
autorequire:
|
14
14
|
bindir: bin
|
15
15
|
cert_chain: []
|
16
16
|
|
17
|
-
date:
|
17
|
+
date: 2012-12-15 00:00:00 -05:00
|
18
18
|
default_executable:
|
19
19
|
dependencies:
|
20
20
|
- !ruby/object:Gem::Dependency
|
21
|
-
name:
|
21
|
+
name: htmlentities
|
22
22
|
prerelease: false
|
23
23
|
requirement: &id001 !ruby/object:Gem::Requirement
|
24
|
-
none: false
|
25
24
|
requirements:
|
26
|
-
- -
|
25
|
+
- - ~>
|
27
26
|
- !ruby/object:Gem::Version
|
28
|
-
hash: 15
|
29
27
|
segments:
|
30
|
-
- 1
|
31
|
-
- 4
|
32
28
|
- 4
|
33
|
-
|
29
|
+
- 3
|
30
|
+
version: "4.3"
|
34
31
|
type: :runtime
|
35
32
|
version_requirements: *id001
|
36
33
|
- !ruby/object:Gem::Dependency
|
37
|
-
name:
|
34
|
+
name: nokogiri
|
38
35
|
prerelease: false
|
39
36
|
requirement: &id002 !ruby/object:Gem::Requirement
|
40
|
-
none: false
|
41
37
|
requirements:
|
42
38
|
- - ">="
|
43
39
|
- !ruby/object:Gem::Version
|
44
|
-
hash: 63
|
45
40
|
segments:
|
41
|
+
- 1
|
46
42
|
- 4
|
47
|
-
-
|
48
|
-
|
49
|
-
version: 4.0.0
|
43
|
+
- 4
|
44
|
+
version: 1.4.4
|
50
45
|
type: :runtime
|
51
46
|
version_requirements: *id002
|
52
47
|
- !ruby/object:Gem::Dependency
|
53
|
-
name:
|
48
|
+
name: activerecord
|
54
49
|
prerelease: false
|
55
50
|
requirement: &id003 !ruby/object:Gem::Requirement
|
56
|
-
none: false
|
57
51
|
requirements:
|
58
|
-
- -
|
52
|
+
- - ~>
|
59
53
|
- !ruby/object:Gem::Version
|
60
|
-
hash: 3
|
61
54
|
segments:
|
62
|
-
- 2
|
63
55
|
- 3
|
64
|
-
-
|
65
|
-
|
66
|
-
|
56
|
+
- 2
|
57
|
+
- 9
|
58
|
+
version: 3.2.9
|
59
|
+
type: :runtime
|
60
|
+
version_requirements: *id003
|
61
|
+
- !ruby/object:Gem::Dependency
|
62
|
+
name: activesupport
|
63
|
+
prerelease: false
|
64
|
+
requirement: &id004 !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ~>
|
67
67
|
- !ruby/object:Gem::Version
|
68
|
-
hash: 5
|
69
68
|
segments:
|
70
69
|
- 3
|
71
|
-
|
70
|
+
- 2
|
71
|
+
- 9
|
72
|
+
version: 3.2.9
|
72
73
|
type: :runtime
|
73
|
-
version_requirements: *
|
74
|
+
version_requirements: *id004
|
74
75
|
- !ruby/object:Gem::Dependency
|
75
|
-
name:
|
76
|
+
name: rspec
|
76
77
|
prerelease: false
|
77
|
-
requirement: &
|
78
|
-
none: false
|
78
|
+
requirement: &id005 !ruby/object:Gem::Requirement
|
79
79
|
requirements:
|
80
80
|
- - ">="
|
81
81
|
- !ruby/object:Gem::Version
|
82
|
-
hash: 3
|
83
82
|
segments:
|
83
|
+
- 0
|
84
|
+
version: "0"
|
85
|
+
type: :runtime
|
86
|
+
version_requirements: *id005
|
87
|
+
- !ruby/object:Gem::Dependency
|
88
|
+
name: money
|
89
|
+
prerelease: false
|
90
|
+
requirement: &id006 !ruby/object:Gem::Requirement
|
91
|
+
requirements:
|
92
|
+
- - ~>
|
93
|
+
- !ruby/object:Gem::Version
|
94
|
+
segments:
|
95
|
+
- 5
|
96
|
+
- 0
|
97
|
+
- 0
|
98
|
+
version: 5.0.0
|
99
|
+
type: :runtime
|
100
|
+
version_requirements: *id006
|
101
|
+
- !ruby/object:Gem::Dependency
|
102
|
+
name: kwalify
|
103
|
+
prerelease: false
|
104
|
+
requirement: &id007 !ruby/object:Gem::Requirement
|
105
|
+
requirements:
|
106
|
+
- - ~>
|
107
|
+
- !ruby/object:Gem::Version
|
108
|
+
segments:
|
109
|
+
- 0
|
110
|
+
- 7
|
111
|
+
version: "0.7"
|
112
|
+
type: :runtime
|
113
|
+
version_requirements: *id007
|
114
|
+
- !ruby/object:Gem::Dependency
|
115
|
+
name: actionmailer
|
116
|
+
prerelease: false
|
117
|
+
requirement: &id008 !ruby/object:Gem::Requirement
|
118
|
+
requirements:
|
119
|
+
- - ~>
|
120
|
+
- !ruby/object:Gem::Version
|
121
|
+
segments:
|
122
|
+
- 3
|
84
123
|
- 2
|
124
|
+
- 9
|
125
|
+
version: 3.2.9
|
126
|
+
type: :runtime
|
127
|
+
version_requirements: *id008
|
128
|
+
- !ruby/object:Gem::Dependency
|
129
|
+
name: sqlite3
|
130
|
+
prerelease: false
|
131
|
+
requirement: &id009 !ruby/object:Gem::Requirement
|
132
|
+
requirements:
|
133
|
+
- - ~>
|
134
|
+
- !ruby/object:Gem::Version
|
135
|
+
segments:
|
136
|
+
- 1
|
85
137
|
- 3
|
138
|
+
version: "1.3"
|
139
|
+
type: :runtime
|
140
|
+
version_requirements: *id009
|
141
|
+
- !ruby/object:Gem::Dependency
|
142
|
+
name: typhoeus
|
143
|
+
prerelease: false
|
144
|
+
requirement: &id010 !ruby/object:Gem::Requirement
|
145
|
+
requirements:
|
146
|
+
- - ~>
|
147
|
+
- !ruby/object:Gem::Version
|
148
|
+
segments:
|
86
149
|
- 0
|
87
|
-
|
88
|
-
|
150
|
+
- 5
|
151
|
+
version: "0.5"
|
152
|
+
type: :runtime
|
153
|
+
version_requirements: *id010
|
154
|
+
- !ruby/object:Gem::Dependency
|
155
|
+
name: rake
|
156
|
+
prerelease: false
|
157
|
+
requirement: &id011 !ruby/object:Gem::Requirement
|
158
|
+
requirements:
|
159
|
+
- - ">="
|
89
160
|
- !ruby/object:Gem::Version
|
90
|
-
hash: 5
|
91
161
|
segments:
|
92
|
-
-
|
93
|
-
version: "
|
162
|
+
- 0
|
163
|
+
version: "0"
|
94
164
|
type: :runtime
|
95
|
-
version_requirements: *
|
96
|
-
|
97
|
-
|
98
|
-
|
99
|
-
|
165
|
+
version_requirements: *id011
|
166
|
+
- !ruby/object:Gem::Dependency
|
167
|
+
name: rspec
|
168
|
+
prerelease: false
|
169
|
+
requirement: &id012 !ruby/object:Gem::Requirement
|
170
|
+
requirements:
|
171
|
+
- - ">="
|
172
|
+
- !ruby/object:Gem::Version
|
173
|
+
segments:
|
174
|
+
- 2
|
175
|
+
- 12
|
176
|
+
- 0
|
177
|
+
version: 2.12.0
|
178
|
+
type: :development
|
179
|
+
version_requirements: *id012
|
180
|
+
description: "An easy library to do the heavy lifting between you and Craigslist\xE2\x80\x98s posting database. Given a URL, libcraigscrape will follow links, scrape fields, and make ruby-sense out of the raw html from craigslist\xE2\x80\x98s servers. libcraigscrape was primarily developed to support the included craigwatch script. See the included craigwatch script for examples of libcraigscape in action, and (hopefully) to serve an immediate craigscraping need."
|
181
|
+
email: info@derosetechnologies.com
|
182
|
+
executables: []
|
183
|
+
|
100
184
|
extensions: []
|
101
185
|
|
102
|
-
extra_rdoc_files:
|
103
|
-
|
104
|
-
- CHANGELOG
|
105
|
-
- COPYING
|
106
|
-
- COPYING.LESSER
|
107
|
-
- bin/craigwatch
|
186
|
+
extra_rdoc_files: []
|
187
|
+
|
108
188
|
files:
|
189
|
+
- Rakefile
|
190
|
+
- bin/craig_report_schema.yml
|
191
|
+
- bin/craigwatch
|
192
|
+
- bin/report_mailer/report.html.erb
|
193
|
+
- bin/report_mailer/report.text.erb
|
194
|
+
- lib/geo_listings.rb
|
109
195
|
- lib/libcraigscrape.rb
|
196
|
+
- lib/listings.rb
|
197
|
+
- lib/posting.rb
|
198
|
+
- lib/scraper.rb
|
199
|
+
- test/geolisting_samples/geo_listing_ca070209.html
|
200
|
+
- test/geolisting_samples/geo_listing_ca_sk070209.html
|
201
|
+
- test/geolisting_samples/geo_listing_cn070209.html
|
202
|
+
- test/geolisting_samples/geo_listing_us070209.html
|
203
|
+
- test/geolisting_samples/hierarchy_test071009/index.html
|
204
|
+
- test/geolisting_samples/hierarchy_test071009/us/fl/ft%20myers%20%5C/%20SW%20florida/index.html
|
205
|
+
- test/geolisting_samples/hierarchy_test071009/us/fl/ft%20myers%20%5C/index.html
|
206
|
+
- test/geolisting_samples/hierarchy_test071009/us/fl/index.html
|
207
|
+
- test/geolisting_samples/hierarchy_test071009/us/fl/miami/index.html
|
208
|
+
- test/geolisting_samples/hierarchy_test071009/us/fl/miami/nonsense/index.html
|
110
209
|
- test/geolisting_samples/hierarchy_test071009/us/fl/miami/nonsense/more-nonsense/index.html
|
111
|
-
-
|
112
|
-
-
|
113
|
-
-
|
114
|
-
-
|
115
|
-
-
|
116
|
-
- bin/report_mailer/craigslist_report.html.erb
|
117
|
-
- bin/report_mailer/craigslist_report.plain.erb
|
210
|
+
- test/geolisting_samples/hierarchy_test071009/us/fl/nonexist/index.html
|
211
|
+
- test/geolisting_samples/hierarchy_test071009/us/fl/nonsense/index.html
|
212
|
+
- test/geolisting_samples/hierarchy_test071009/us/fl/south%20florida/index.html
|
213
|
+
- test/geolisting_samples/hierarchy_test071009/us/index.html
|
214
|
+
- test/google.html
|
118
215
|
- test/libcraigscrape_test_helpers.rb
|
119
|
-
- test/test_craigslist_posting.rb
|
120
216
|
- test/listing_samples/category_output.html
|
121
|
-
- test/listing_samples/
|
217
|
+
- test/listing_samples/category_output_2.html
|
122
218
|
- test/listing_samples/empty_listings.html
|
123
|
-
- test/listing_samples/
|
124
|
-
- test/listing_samples/mia_search_kitten.3.15.10.html
|
125
|
-
- test/listing_samples/fortmyers_art_index.060909/891513957.html
|
219
|
+
- test/listing_samples/fortmyers_art_index.060909/1046596324.html
|
126
220
|
- test/listing_samples/fortmyers_art_index.060909/1053085283.html
|
127
|
-
- test/listing_samples/fortmyers_art_index.060909/
|
221
|
+
- test/listing_samples/fortmyers_art_index.060909/1112522674.html
|
222
|
+
- test/listing_samples/fortmyers_art_index.060909/823516079.html
|
128
223
|
- test/listing_samples/fortmyers_art_index.060909/825684735.html
|
129
|
-
- test/listing_samples/fortmyers_art_index.060909/
|
130
|
-
- test/listing_samples/fortmyers_art_index.060909/
|
224
|
+
- test/listing_samples/fortmyers_art_index.060909/891513957.html
|
225
|
+
- test/listing_samples/fortmyers_art_index.060909/897549505.html
|
131
226
|
- test/listing_samples/fortmyers_art_index.060909/960826026.html
|
132
|
-
- test/listing_samples/fortmyers_art_index.060909/1046596324.html
|
133
227
|
- test/listing_samples/fortmyers_art_index.060909/993256300.html
|
134
|
-
- test/listing_samples/fortmyers_art_index.060909/
|
135
|
-
- test/listing_samples/fortmyers_art_index.060909/
|
136
|
-
- test/listing_samples/category_output_2.html
|
228
|
+
- test/listing_samples/fortmyers_art_index.060909/fortmyers_art_index500.060909.html
|
229
|
+
- test/listing_samples/fortmyers_art_index.060909/fortmyers_art_index600.060909.html
|
137
230
|
- test/listing_samples/long_search_output.html
|
138
|
-
- test/listing_samples/
|
231
|
+
- test/listing_samples/mia_fua_index8900.5.21.09.html
|
232
|
+
- test/listing_samples/mia_search_kitten.3.15.10.html
|
139
233
|
- test/listing_samples/miami_search_sss_rack.6.18.09/miami_search_sss_rack1000.6.18.09.html
|
234
|
+
- test/listing_samples/miami_search_sss_rack.6.18.09/miami_search_sss_rack900.6.18.09.html
|
140
235
|
- test/listing_samples/new_listing_span.4.17.10.html
|
141
|
-
- test/
|
142
|
-
- test/post_samples/
|
236
|
+
- test/listing_samples/short_search_output.html
|
237
|
+
- test/post_samples/1207457727.html
|
143
238
|
- test/post_samples/brw_reb_1224008903.html
|
144
|
-
- test/post_samples/posting1.html
|
145
239
|
- test/post_samples/posting0.html
|
146
|
-
- test/post_samples/
|
147
|
-
- test/post_samples/posting5.html
|
240
|
+
- test/post_samples/posting1.html
|
148
241
|
- test/post_samples/posting1796890756-061710.html
|
149
|
-
- test/post_samples/posting3.html
|
150
|
-
- test/post_samples/this_post_has_expired.html
|
151
242
|
- test/post_samples/posting1808219423.html
|
243
|
+
- test/post_samples/posting1938291834-090610.html
|
244
|
+
- test/post_samples/posting2.html
|
245
|
+
- test/post_samples/posting3.html
|
246
|
+
- test/post_samples/posting4.html
|
247
|
+
- test/post_samples/posting5.html
|
152
248
|
- test/post_samples/sfbay_art_1223614914.html
|
153
249
|
- test/post_samples/this_post_has_been_deleted_by_its_author.html
|
154
|
-
- test/post_samples/
|
155
|
-
- test/post_samples/posting2.html
|
156
|
-
- test/google.html
|
250
|
+
- test/post_samples/this_post_has_expired.html
|
157
251
|
- test/test_craigslist_geolisting.rb
|
158
|
-
- test/
|
159
|
-
- test/
|
160
|
-
-
|
252
|
+
- test/test_craigslist_listing.rb
|
253
|
+
- test/test_craigslist_posting.rb
|
254
|
+
- spec/assets/geolisting_iso_us_120412.html
|
255
|
+
- spec/assets/listing_cta_ftl_112612.html
|
256
|
+
- spec/assets/listing_rea_miami_123012.html
|
257
|
+
- spec/assets/listing_search_ppa_nyc_121212.html
|
258
|
+
- spec/assets/posting_daytona_art_120512-2.html
|
259
|
+
- spec/assets/posting_daytona_art_120512.html
|
260
|
+
- spec/assets/posting_mdc_cto_ftl_112612.html
|
261
|
+
- spec/assets/posting_mdc_reb_120612.html
|
262
|
+
- spec/assets/posting_sfbay_1226.html
|
263
|
+
- spec/assets/posting_sya_121012-2.html
|
264
|
+
- spec/assets/posting_sya_121012.html
|
265
|
+
- spec/assets/this_post_has_expired_old.html
|
266
|
+
- spec/geolisting_spec.rb
|
267
|
+
- spec/listings_spec.rb
|
268
|
+
- spec/postings_spec.rb
|
269
|
+
- spec/spec_helper.rb
|
270
|
+
- Gemfile
|
271
|
+
- CHANGELOG
|
272
|
+
- COPYING
|
273
|
+
- COPYING.LESSER
|
161
274
|
- README
|
162
|
-
- test/geolisting_samples/hierarchy_test071009/us/fl/miami/nonsense/index.html
|
163
|
-
- test/geolisting_samples/hierarchy_test071009/us/fl/miami/index.html
|
164
|
-
- test/geolisting_samples/hierarchy_test071009/us/fl/nonsense/index.html
|
165
|
-
- test/geolisting_samples/hierarchy_test071009/us/fl/south%20florida/index.html
|
166
|
-
- test/geolisting_samples/hierarchy_test071009/us/fl/nonexist/index.html
|
167
|
-
- test/geolisting_samples/hierarchy_test071009/us/fl/ft%20myers%20%5C/%20SW%20florida/index.html
|
168
|
-
- test/geolisting_samples/hierarchy_test071009/us/fl/ft%20myers%20%5C/index.html
|
169
|
-
- test/geolisting_samples/hierarchy_test071009/us/fl/index.html
|
170
|
-
- test/geolisting_samples/hierarchy_test071009/us/index.html
|
171
|
-
- test/geolisting_samples/hierarchy_test071009/index.html
|
172
|
-
- test/geolisting_samples/geo_listing_us070209.html
|
173
|
-
- lib/listings.rb
|
174
|
-
- lib/geo_listings.rb
|
175
|
-
- lib/posting.rb
|
176
|
-
- Rakefile
|
177
|
-
- lib/scraper.rb
|
178
275
|
has_rdoc: true
|
179
276
|
homepage: http://www.derosetechnologies.com/community/libcraigscrape
|
180
277
|
licenses: []
|
181
278
|
|
182
279
|
post_install_message:
|
183
|
-
rdoc_options:
|
184
|
-
|
185
|
-
- --title
|
186
|
-
- The libcraigscrape Reference
|
187
|
-
- --main
|
188
|
-
- README
|
189
|
-
- --inline-source
|
280
|
+
rdoc_options: []
|
281
|
+
|
190
282
|
require_paths:
|
191
283
|
- lib
|
192
284
|
required_ruby_version: !ruby/object:Gem::Requirement
|
193
|
-
none: false
|
194
285
|
requirements:
|
195
286
|
- - ">="
|
196
287
|
- !ruby/object:Gem::Version
|
197
|
-
hash: 3
|
198
288
|
segments:
|
199
289
|
- 0
|
200
290
|
version: "0"
|
201
291
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
202
|
-
none: false
|
203
292
|
requirements:
|
204
293
|
- - ">="
|
205
294
|
- !ruby/object:Gem::Version
|
206
|
-
hash: 3
|
207
295
|
segments:
|
208
296
|
- 0
|
209
297
|
version: "0"
|
210
298
|
requirements: []
|
211
299
|
|
212
|
-
rubyforge_project:
|
213
|
-
rubygems_version: 1.3.
|
300
|
+
rubyforge_project:
|
301
|
+
rubygems_version: 1.3.6
|
214
302
|
signing_key:
|
215
303
|
specification_version: 3
|
216
304
|
summary: quick, easy, craigslist parsing library that takes the monotony out of working with craigslist posts and listings
|
217
|
-
test_files:
|
218
|
-
|
219
|
-
- test/test_craigslist_listing.rb
|
220
|
-
- test/test_craigslist_geolisting.rb
|
305
|
+
test_files: []
|
306
|
+
|
@@ -1,17 +0,0 @@
|
|
1
|
-
<h2><%=h @subject %></h2>
|
2
|
-
<%@summaries.each do |summary| %>
|
3
|
-
<h3><%=h summary[:search].name%></h3>
|
4
|
-
<% if summary[:postings].length > 0 %>
|
5
|
-
<%summary[:postings].each do |post|%>
|
6
|
-
<%='<p>%s <a href="%s">%s -</a>%s%s</p>' % [
|
7
|
-
h(post.post_date.strftime('%b %d')),
|
8
|
-
post.url,
|
9
|
-
h(post.label),
|
10
|
-
(post.location) ? '<font size="-1"> (%s)</font>' % h(post.location) : '',
|
11
|
-
(post.has_pic_or_img?) ? ' <span style="color: orange"> img</span>': ''
|
12
|
-
] -%>
|
13
|
-
<% end %>
|
14
|
-
<% else %>
|
15
|
-
<p><i>No new postings were found, which matched the search criteria.</i></p>
|
16
|
-
<% end %>
|
17
|
-
<% end %>
|