horsefield 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/.rspec +2 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +47 -0
- data/Rakefile +6 -0
- data/horsefield.gemspec +29 -0
- data/lib/horsefield.rb +5 -0
- data/lib/horsefield/node.rb +12 -0
- data/lib/horsefield/node_set.rb +48 -0
- data/lib/horsefield/scraper.rb +32 -0
- data/lib/horsefield/version.rb +3 -0
- data/spec/fixtures/monster.html +2311 -0
- data/spec/fixtures/vcr_cassettes/facebook/frontpage.yml +948 -0
- data/spec/fixtures/vcr_cassettes/facebook/johnny_qiu1.yml +7105 -0
- data/spec/fixtures/vcr_cassettes/facebook/login.yml +11872 -0
- data/spec/horsefield_spec.rb +4 -0
- data/spec/scraper_spec.rb +49 -0
- data/spec/spec_helper.rb +21 -0
- metadata +168 -0
@@ -0,0 +1,49 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
require 'horsefield/scraper'
|
3
|
+
|
4
|
+
VCR.configure do |c|
|
5
|
+
c.cassette_library_dir = 'spec/fixtures/vcr_cassettes'
|
6
|
+
c.hook_into :webmock
|
7
|
+
end
|
8
|
+
|
9
|
+
describe Horsefield::Scraper do
|
10
|
+
describe 'with HTML' do
|
11
|
+
before do
|
12
|
+
html = IO.read File.join(__dir__, 'fixtures/monster.html')
|
13
|
+
@scraper = Horsefield::Scraper.new(html: html)
|
14
|
+
end
|
15
|
+
|
16
|
+
it 'should scrape' do
|
17
|
+
result = @scraper.scrape do
|
18
|
+
many :jobs, '.listingsTable .odd, .listingsTable .even' do
|
19
|
+
one :title, '.jobTitleContainer'
|
20
|
+
one :company, '.companyContainer'
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
result[:jobs].should have(9).items
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
describe 'with URL' do
|
29
|
+
before do
|
30
|
+
@scraper = Horsefield::Scraper.new('https://www.facebook.com/johnny.qiu1/info?_fb_noscript=1')
|
31
|
+
end
|
32
|
+
|
33
|
+
it 'should scrape' do
|
34
|
+
VCR.use_cassette 'facebook/johnny_qiu1' do
|
35
|
+
result = @scraper.scrape do
|
36
|
+
one :name, '._8_2'
|
37
|
+
|
38
|
+
many :employers, '//table[@class="mal _5e7- profileInfoTable _3stn"]//*[text() = "Employers"]' do
|
39
|
+
end
|
40
|
+
|
41
|
+
many :educations, '//table[@class="mal _5e7- profileInfoTable _3stn"]//*[text() = "University" or text() = "Secondary school"]' do
|
42
|
+
end
|
43
|
+
end
|
44
|
+
|
45
|
+
result[:name].should == 'Johnny Qiu (邱博瀚)'
|
46
|
+
end
|
47
|
+
end
|
48
|
+
end
|
49
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
require 'pry'
|
2
|
+
require 'vcr'
|
3
|
+
require 'webmock'
|
4
|
+
|
5
|
+
# This file was generated by the `rspec --init` command. Conventionally, all
|
6
|
+
# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
|
7
|
+
# Require this file using `require "spec_helper"` to ensure that it is only
|
8
|
+
# loaded once.
|
9
|
+
#
|
10
|
+
# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
|
11
|
+
RSpec.configure do |config|
|
12
|
+
config.treat_symbols_as_metadata_keys_with_true_values = true
|
13
|
+
config.run_all_when_everything_filtered = true
|
14
|
+
config.filter_run :focus
|
15
|
+
|
16
|
+
# Run specs in random order to surface order dependencies. If you find an
|
17
|
+
# order dependency and want to debug it, you can fix the order by providing
|
18
|
+
# the seed, which is printed after each run.
|
19
|
+
# --seed 1234
|
20
|
+
config.order = 'random'
|
21
|
+
end
|
metadata
ADDED
@@ -0,0 +1,168 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: horsefield
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Erik Strömberg
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-08-25 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: mechanize
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - '>='
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - '>='
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: bundler
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ~>
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.3'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ~>
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.3'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rake
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :development
|
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: rspec
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - '>='
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: pry
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - '>='
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - '>='
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: vcr
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - '>='
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - '>='
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: webmock
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - '='
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: 1.12.0
|
104
|
+
type: :development
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - '='
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: 1.12.0
|
111
|
+
description: It's a scraper
|
112
|
+
email:
|
113
|
+
- erik.stromberg@gmail.com
|
114
|
+
executables: []
|
115
|
+
extensions: []
|
116
|
+
extra_rdoc_files: []
|
117
|
+
files:
|
118
|
+
- .gitignore
|
119
|
+
- .rspec
|
120
|
+
- Gemfile
|
121
|
+
- LICENSE.txt
|
122
|
+
- README.md
|
123
|
+
- Rakefile
|
124
|
+
- horsefield.gemspec
|
125
|
+
- lib/horsefield.rb
|
126
|
+
- lib/horsefield/node.rb
|
127
|
+
- lib/horsefield/node_set.rb
|
128
|
+
- lib/horsefield/scraper.rb
|
129
|
+
- lib/horsefield/version.rb
|
130
|
+
- spec/fixtures/monster.html
|
131
|
+
- spec/fixtures/vcr_cassettes/facebook/frontpage.yml
|
132
|
+
- spec/fixtures/vcr_cassettes/facebook/johnny_qiu1.yml
|
133
|
+
- spec/fixtures/vcr_cassettes/facebook/login.yml
|
134
|
+
- spec/horsefield_spec.rb
|
135
|
+
- spec/scraper_spec.rb
|
136
|
+
- spec/spec_helper.rb
|
137
|
+
homepage: ''
|
138
|
+
licenses:
|
139
|
+
- MIT
|
140
|
+
metadata: {}
|
141
|
+
post_install_message:
|
142
|
+
rdoc_options: []
|
143
|
+
require_paths:
|
144
|
+
- lib
|
145
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
146
|
+
requirements:
|
147
|
+
- - '>='
|
148
|
+
- !ruby/object:Gem::Version
|
149
|
+
version: '0'
|
150
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
151
|
+
requirements:
|
152
|
+
- - '>='
|
153
|
+
- !ruby/object:Gem::Version
|
154
|
+
version: '0'
|
155
|
+
requirements: []
|
156
|
+
rubyforge_project:
|
157
|
+
rubygems_version: 2.1.0.rc.1
|
158
|
+
signing_key:
|
159
|
+
specification_version: 4
|
160
|
+
summary: It's a scraper
|
161
|
+
test_files:
|
162
|
+
- spec/fixtures/monster.html
|
163
|
+
- spec/fixtures/vcr_cassettes/facebook/frontpage.yml
|
164
|
+
- spec/fixtures/vcr_cassettes/facebook/johnny_qiu1.yml
|
165
|
+
- spec/fixtures/vcr_cassettes/facebook/login.yml
|
166
|
+
- spec/horsefield_spec.rb
|
167
|
+
- spec/scraper_spec.rb
|
168
|
+
- spec/spec_helper.rb
|