horsefield 0.2.13 → 0.3.13
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.
- checksums.yaml +4 -4
- data/lib/horsefield/node_set.rb +4 -0
- data/lib/horsefield/scraper.rb +3 -0
- data/lib/horsefield/version.rb +1 -1
- data/spec/scraper_spec.rb +16 -3
- metadata +2 -4
- data/spec/horsefield_spec.rb +0 -11
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 600cdb34954a4e1cbe152d9885bffae6b84604f6
|
4
|
+
data.tar.gz: 3dabac2ccec96a351bb483fb7e6cc9918507072f
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 4fd0f85c2f966e4676ac083f67fb9064b13cde9f756d185c70a9fe66f646a8fd92f04715605511842d887a0459d8a240fb0a89a42965f649e9824aedb8460917
|
7
|
+
data.tar.gz: 77cf1c3d70e6e2ab26615ff58abb574c08641f4b51bce10f694e6996b3752c57454bef292b7276a2fe6f2b3cb43986f0e7fd044469b9ebd9dfbb7495d098762c
|
data/lib/horsefield/node_set.rb
CHANGED
@@ -18,6 +18,10 @@ module Horsefield
|
|
18
18
|
def browse(*)
|
19
19
|
end
|
20
20
|
|
21
|
+
def scope(selector, &block)
|
22
|
+
@nodes = @nodes.merge(dig_deeper(selector, false, &block))
|
23
|
+
end
|
24
|
+
|
21
25
|
def one(name, selector, type = :text, &block)
|
22
26
|
@nodes[name] = dig_deeper selector, false, type, &block
|
23
27
|
end
|
data/lib/horsefield/scraper.rb
CHANGED
data/lib/horsefield/version.rb
CHANGED
data/spec/scraper_spec.rb
CHANGED
@@ -16,7 +16,20 @@ describe Horsefield::Scraper do
|
|
16
16
|
end
|
17
17
|
end
|
18
18
|
|
19
|
-
result[:jobs].
|
19
|
+
expect(result[:jobs].length).to eq(9)
|
20
|
+
end
|
21
|
+
|
22
|
+
it 'should be able to scrape in scope' do
|
23
|
+
result = Horsefield::Scraper.new.scrape html: @html do
|
24
|
+
scope '#primaryResults' do
|
25
|
+
many :jobs, '.listingsTable .odd, .listingsTable .even' do
|
26
|
+
one :title, '.jobTitleContainer'
|
27
|
+
one :company, '.companyContainer'
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
expect(result[:jobs].length).to eq(9)
|
20
33
|
end
|
21
34
|
|
22
35
|
it 'should return nil for selectors that are not found' do
|
@@ -28,7 +41,7 @@ describe Horsefield::Scraper do
|
|
28
41
|
end
|
29
42
|
end
|
30
43
|
|
31
|
-
result[:job][:missing].
|
44
|
+
expect(result[:job][:missing]).to be_nil
|
32
45
|
end
|
33
46
|
|
34
47
|
it 'can return HTML instead of text' do
|
@@ -40,7 +53,7 @@ describe Horsefield::Scraper do
|
|
40
53
|
end
|
41
54
|
end
|
42
55
|
|
43
|
-
result[:job][:title].
|
56
|
+
expect(result[:job][:title]).to match(/<a id=\"ctl00_ctl00_ctl00_body_body_wacCenterStage_ctl02_rptResults_ctl00_linkJobTitle\"/)
|
44
57
|
end
|
45
58
|
|
46
59
|
it 'works with Watir' do
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: horsefield
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.3.13
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Erik Strömberg
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2014-01-
|
11
|
+
date: 2014-01-28 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: mechanize
|
@@ -143,7 +143,6 @@ files:
|
|
143
143
|
- lib/horsefield/version.rb
|
144
144
|
- spec/fixtures/monster.html
|
145
145
|
- spec/fixtures/vcr_cassettes/facebook/johnny_qiu1.yml
|
146
|
-
- spec/horsefield_spec.rb
|
147
146
|
- spec/scraper_spec.rb
|
148
147
|
- spec/spec_helper.rb
|
149
148
|
homepage: ''
|
@@ -173,6 +172,5 @@ summary: It's a scraper
|
|
173
172
|
test_files:
|
174
173
|
- spec/fixtures/monster.html
|
175
174
|
- spec/fixtures/vcr_cassettes/facebook/johnny_qiu1.yml
|
176
|
-
- spec/horsefield_spec.rb
|
177
175
|
- spec/scraper_spec.rb
|
178
176
|
- spec/spec_helper.rb
|
data/spec/horsefield_spec.rb
DELETED