rubyscraper 0.3.0 → 0.9.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Gemfile.lock +5 -6
- data/README.md +37 -7
- data/lib/rubyscraper.rb +14 -148
- data/lib/rubyscraper/api_dispatcher.rb +31 -0
- data/lib/rubyscraper/binary.rb +9 -6
- data/lib/rubyscraper/option_parser.rb +72 -0
- data/lib/rubyscraper/paginator.rb +59 -0
- data/lib/rubyscraper/processor.rb +47 -0
- data/lib/rubyscraper/sub_page_scraper.rb +53 -0
- data/lib/rubyscraper/summary_scraper.rb +65 -0
- data/lib/rubyscraper/version.rb +1 -1
- data/rubyscraper.gemspec +5 -6
- data/spec/paginator_spec.rb +83 -0
- data/spec/rubyscraper_spec.rb +2 -6
- data/spec/spec_helper.rb +3 -0
- data/spec/sub_page_scraper_spec.rb +51 -0
- data/spec/summary_scraper_spec.rb +125 -0
- metadata +27 -33
- data/lib/assets/scrapes.json +0 -287
metadata
CHANGED
@@ -1,71 +1,57 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: rubyscraper
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.9.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Nathan Owsiany
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2015-04-
|
11
|
+
date: 2015-04-28 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: capybara
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
-
- - "
|
17
|
+
- - "~>"
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: '
|
19
|
+
version: '2.4'
|
20
20
|
type: :runtime
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
|
-
- - "
|
24
|
+
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version: '
|
26
|
+
version: '2.4'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: poltergeist
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
|
-
- - "
|
31
|
+
- - "~>"
|
32
32
|
- !ruby/object:Gem::Version
|
33
|
-
version: '
|
33
|
+
version: '1.6'
|
34
34
|
type: :runtime
|
35
35
|
prerelease: false
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
|
-
- - "
|
38
|
+
- - "~>"
|
39
39
|
- !ruby/object:Gem::Version
|
40
|
-
version: '
|
40
|
+
version: '1.6'
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
42
|
name: rest-client
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
|
-
- - "
|
46
|
-
- !ruby/object:Gem::Version
|
47
|
-
version: '0'
|
48
|
-
type: :runtime
|
49
|
-
prerelease: false
|
50
|
-
version_requirements: !ruby/object:Gem::Requirement
|
51
|
-
requirements:
|
52
|
-
- - ">="
|
53
|
-
- !ruby/object:Gem::Version
|
54
|
-
version: '0'
|
55
|
-
- !ruby/object:Gem::Dependency
|
56
|
-
name: slop
|
57
|
-
requirement: !ruby/object:Gem::Requirement
|
58
|
-
requirements:
|
59
|
-
- - ">="
|
45
|
+
- - "~>"
|
60
46
|
- !ruby/object:Gem::Version
|
61
|
-
version: '
|
47
|
+
version: '1.8'
|
62
48
|
type: :runtime
|
63
49
|
prerelease: false
|
64
50
|
version_requirements: !ruby/object:Gem::Requirement
|
65
51
|
requirements:
|
66
|
-
- - "
|
52
|
+
- - "~>"
|
67
53
|
- !ruby/object:Gem::Version
|
68
|
-
version: '
|
54
|
+
version: '1.8'
|
69
55
|
- !ruby/object:Gem::Dependency
|
70
56
|
name: bundler
|
71
57
|
requirement: !ruby/object:Gem::Requirement
|
@@ -112,16 +98,16 @@ dependencies:
|
|
112
98
|
name: pry
|
113
99
|
requirement: !ruby/object:Gem::Requirement
|
114
100
|
requirements:
|
115
|
-
- - "
|
101
|
+
- - "~>"
|
116
102
|
- !ruby/object:Gem::Version
|
117
|
-
version: '0'
|
103
|
+
version: '0.10'
|
118
104
|
type: :development
|
119
105
|
prerelease: false
|
120
106
|
version_requirements: !ruby/object:Gem::Requirement
|
121
107
|
requirements:
|
122
|
-
- - "
|
108
|
+
- - "~>"
|
123
109
|
- !ruby/object:Gem::Version
|
124
|
-
version: '0'
|
110
|
+
version: '0.10'
|
125
111
|
description: Scrapes job sites for job details and sends post request to server.
|
126
112
|
email: nowsiany@gmail.com
|
127
113
|
executables:
|
@@ -136,13 +122,21 @@ files:
|
|
136
122
|
- bin/console
|
137
123
|
- bin/rubyscraper
|
138
124
|
- bin/setup
|
139
|
-
- lib/assets/scrapes.json
|
140
125
|
- lib/rubyscraper.rb
|
126
|
+
- lib/rubyscraper/api_dispatcher.rb
|
141
127
|
- lib/rubyscraper/binary.rb
|
128
|
+
- lib/rubyscraper/option_parser.rb
|
129
|
+
- lib/rubyscraper/paginator.rb
|
130
|
+
- lib/rubyscraper/processor.rb
|
131
|
+
- lib/rubyscraper/sub_page_scraper.rb
|
132
|
+
- lib/rubyscraper/summary_scraper.rb
|
142
133
|
- lib/rubyscraper/version.rb
|
143
134
|
- rubyscraper.gemspec
|
135
|
+
- spec/paginator_spec.rb
|
144
136
|
- spec/rubyscraper_spec.rb
|
145
137
|
- spec/spec_helper.rb
|
138
|
+
- spec/sub_page_scraper_spec.rb
|
139
|
+
- spec/summary_scraper_spec.rb
|
146
140
|
homepage: https://github.com/ndwhtlssthr/rubyscraper
|
147
141
|
licenses:
|
148
142
|
- MIT
|
data/lib/assets/scrapes.json
DELETED
@@ -1,287 +0,0 @@
|
|
1
|
-
[
|
2
|
-
{
|
3
|
-
"name":"stackoverflow",
|
4
|
-
"base_url":"http://www.careers.stackoverflow.com",
|
5
|
-
"summary":{
|
6
|
-
"url":"/jobs?searchTerm=SEARCHTERM&sort=p",
|
7
|
-
"pagination_fmt":"&pg=",
|
8
|
-
"pagination_start":"1",
|
9
|
-
"pagination_scale":"1",
|
10
|
-
"params":[
|
11
|
-
{
|
12
|
-
"SEARCHTERM":[
|
13
|
-
"ruby",
|
14
|
-
"ruby+on+rails",
|
15
|
-
"javascript"
|
16
|
-
]
|
17
|
-
}
|
18
|
-
],
|
19
|
-
"loop":".listResults .-item",
|
20
|
-
"fields":[
|
21
|
-
{
|
22
|
-
"field":"position",
|
23
|
-
"method":"find",
|
24
|
-
"path":"h3.-title a"
|
25
|
-
},
|
26
|
-
{
|
27
|
-
"field":"url",
|
28
|
-
"method":"find",
|
29
|
-
"path":"h3.-title a",
|
30
|
-
"attr":"href"
|
31
|
-
},
|
32
|
-
{
|
33
|
-
"field":"posting_date",
|
34
|
-
"method":"first",
|
35
|
-
"path":"p._muted"
|
36
|
-
}
|
37
|
-
]
|
38
|
-
},
|
39
|
-
"sub_page":{
|
40
|
-
"fields":[
|
41
|
-
{
|
42
|
-
"field":"company",
|
43
|
-
"method":"find",
|
44
|
-
"path":"a.employer"
|
45
|
-
},
|
46
|
-
{
|
47
|
-
"field":"location",
|
48
|
-
"method":"find",
|
49
|
-
"path":"span.location"
|
50
|
-
},
|
51
|
-
{
|
52
|
-
"field":"description",
|
53
|
-
"method":"all",
|
54
|
-
"path":"div.description p",
|
55
|
-
"loop_collect":"text",
|
56
|
-
"join":"\n"
|
57
|
-
},
|
58
|
-
{
|
59
|
-
"field":"tags",
|
60
|
-
"method":"all",
|
61
|
-
"path":"div.tags a.post-tag",
|
62
|
-
"loop_collect":"text",
|
63
|
-
"join":", "
|
64
|
-
}
|
65
|
-
]
|
66
|
-
}
|
67
|
-
},
|
68
|
-
{
|
69
|
-
"name":"rubynow",
|
70
|
-
"base_url":"http://jobs.rubynow.com/",
|
71
|
-
"summary":{
|
72
|
-
"url":"",
|
73
|
-
"no_pagination?":"true",
|
74
|
-
"pagination_fmt":"",
|
75
|
-
"pagination_start":"",
|
76
|
-
"pagination_scale":"",
|
77
|
-
"params":[
|
78
|
-
],
|
79
|
-
"loop":"ul.jobs li",
|
80
|
-
"fields":[
|
81
|
-
{
|
82
|
-
"field":"position",
|
83
|
-
"method":"find",
|
84
|
-
"path":"h3 a"
|
85
|
-
},
|
86
|
-
{
|
87
|
-
"field":"url",
|
88
|
-
"method":"find",
|
89
|
-
"path":"h3 a",
|
90
|
-
"attr":"href"
|
91
|
-
},
|
92
|
-
{
|
93
|
-
"field":"posting_date",
|
94
|
-
"method":"find",
|
95
|
-
"path":"span.date"
|
96
|
-
}
|
97
|
-
]
|
98
|
-
},
|
99
|
-
"sub_page":{
|
100
|
-
"fields":[
|
101
|
-
{
|
102
|
-
"field":"description",
|
103
|
-
"method":"all",
|
104
|
-
"path":"div#info p",
|
105
|
-
"loop_collect":"text",
|
106
|
-
"join":"\n"
|
107
|
-
},
|
108
|
-
{
|
109
|
-
"field":"company",
|
110
|
-
"method":"find",
|
111
|
-
"path":"h2#headline a"
|
112
|
-
},
|
113
|
-
{
|
114
|
-
"field":"location",
|
115
|
-
"method":"find",
|
116
|
-
"path":"h3#location"
|
117
|
-
}
|
118
|
-
]
|
119
|
-
}
|
120
|
-
},
|
121
|
-
{
|
122
|
-
"name":"weworkremotely",
|
123
|
-
"base_url":"https://weworkremotely.com",
|
124
|
-
"summary":{
|
125
|
-
"url":"/categories/2/jobs",
|
126
|
-
"no_pagination?":"true",
|
127
|
-
"pagination_fmt":"",
|
128
|
-
"pagination_start":"",
|
129
|
-
"pagination_scale":"",
|
130
|
-
"params":[
|
131
|
-
],
|
132
|
-
"loop":"section.jobs ul li",
|
133
|
-
"fields":[
|
134
|
-
{
|
135
|
-
"field":"position",
|
136
|
-
"method":"find",
|
137
|
-
"path":"span.title"
|
138
|
-
},
|
139
|
-
{
|
140
|
-
"field":"company",
|
141
|
-
"method":"find",
|
142
|
-
"path":"span.company"
|
143
|
-
},
|
144
|
-
{
|
145
|
-
"field":"url",
|
146
|
-
"method":"find",
|
147
|
-
"path":"a",
|
148
|
-
"attr":"href"
|
149
|
-
},
|
150
|
-
{
|
151
|
-
"field":"posting_date",
|
152
|
-
"method":"find",
|
153
|
-
"path":"span.date"
|
154
|
-
}
|
155
|
-
]
|
156
|
-
},
|
157
|
-
"sub_page":{
|
158
|
-
"fields":[
|
159
|
-
{
|
160
|
-
"field":"location",
|
161
|
-
"method":"find",
|
162
|
-
"path":"span.location"
|
163
|
-
},
|
164
|
-
{
|
165
|
-
"field":"description",
|
166
|
-
"method":"all",
|
167
|
-
"path":"div.listing-container div",
|
168
|
-
"loop_collect":"text",
|
169
|
-
"join":"\n"
|
170
|
-
}
|
171
|
-
]
|
172
|
-
}
|
173
|
-
},
|
174
|
-
{
|
175
|
-
"name":"indeed",
|
176
|
-
"skip":"true",
|
177
|
-
"base_url":"http://www.indeed.com",
|
178
|
-
"summary":{
|
179
|
-
"url":"/jobs?q=SEARCHTERM&sr=directhire",
|
180
|
-
"pagination_fmt":"&start=",
|
181
|
-
"pagination_start":"0",
|
182
|
-
"pagination_scale":"10",
|
183
|
-
"params":[
|
184
|
-
{
|
185
|
-
"SEARCHTERM":[
|
186
|
-
"ruby",
|
187
|
-
"ruby+on+rails",
|
188
|
-
"junior+web+developer",
|
189
|
-
"ember.js",
|
190
|
-
"full+stack"
|
191
|
-
]
|
192
|
-
}
|
193
|
-
],
|
194
|
-
"loop":"div.row.result",
|
195
|
-
"fields":[
|
196
|
-
{
|
197
|
-
"field":"position",
|
198
|
-
"method":"find",
|
199
|
-
"path":"h2.jobtitle a"
|
200
|
-
},
|
201
|
-
{
|
202
|
-
"field":"url",
|
203
|
-
"method":"find",
|
204
|
-
"path":"h2.jobtitle a",
|
205
|
-
"attr":"href"
|
206
|
-
},
|
207
|
-
{
|
208
|
-
"field":"company",
|
209
|
-
"method":"find",
|
210
|
-
"path":"span.company span"
|
211
|
-
},
|
212
|
-
{
|
213
|
-
"field":"location",
|
214
|
-
"method":"find",
|
215
|
-
"path":"span.location span"
|
216
|
-
},
|
217
|
-
{
|
218
|
-
"field":"description",
|
219
|
-
"method":"find",
|
220
|
-
"path":"span.summary span"
|
221
|
-
},
|
222
|
-
{
|
223
|
-
"field":"posting_date",
|
224
|
-
"method":"find",
|
225
|
-
"path":"span.date"
|
226
|
-
}
|
227
|
-
]
|
228
|
-
},
|
229
|
-
"sub_page":{
|
230
|
-
"fields":[
|
231
|
-
]
|
232
|
-
}
|
233
|
-
},
|
234
|
-
{
|
235
|
-
"name":"linkedin",
|
236
|
-
"skip":"true",
|
237
|
-
"base_url":"https://www.linkedin.com",
|
238
|
-
"summary":{
|
239
|
-
"url":"/vsearch/j?keywords=SEARCHTERM&openAdvancedForm=true&locationType=I&countryCode=us&rsid=754744171429892349899&orig=FCTD&openFacets=L,C,TP&f_TP=1&pt=jobs&pt=jobs",
|
240
|
-
"pagination_fmt":"&page_num=",
|
241
|
-
"pagination_start":"1",
|
242
|
-
"pagination_scale":"1",
|
243
|
-
"params":[
|
244
|
-
{
|
245
|
-
"SEARCHTERM":[
|
246
|
-
"Ruby",
|
247
|
-
"Ruby+On+Rails",
|
248
|
-
"javascript"
|
249
|
-
]
|
250
|
-
}
|
251
|
-
],
|
252
|
-
"loop":"ol.search-results li.result",
|
253
|
-
"fields":[
|
254
|
-
{
|
255
|
-
"field":"position",
|
256
|
-
"method":"find",
|
257
|
-
"path":"a.title"
|
258
|
-
},
|
259
|
-
{
|
260
|
-
"field":"url",
|
261
|
-
"method":"find",
|
262
|
-
"path":"a.title",
|
263
|
-
"attr":"href"
|
264
|
-
},
|
265
|
-
{
|
266
|
-
"field":"company",
|
267
|
-
"method":"find",
|
268
|
-
"path":"div.description a"
|
269
|
-
},
|
270
|
-
{
|
271
|
-
"field":"location",
|
272
|
-
"method":"find",
|
273
|
-
"path":"dl.demographic bdi"
|
274
|
-
}
|
275
|
-
]
|
276
|
-
},
|
277
|
-
"sub_page":{
|
278
|
-
"fields":[
|
279
|
-
{
|
280
|
-
"field":"description",
|
281
|
-
"method":"find",
|
282
|
-
"path":"div.description-section div.rich-text"
|
283
|
-
}
|
284
|
-
]
|
285
|
-
}
|
286
|
-
}
|
287
|
-
]
|