horsefield 0.2.4 → 0.2.5
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/horsefield/node.rb +5 -1
- data/lib/horsefield/node_set.rb +5 -5
- data/lib/horsefield/version.rb +1 -1
- data/spec/scraper_spec.rb +12 -0
- metadata +3 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 8b8f8255739340596e630908fdf232ad5cf3ac97
|
4
|
+
data.tar.gz: 7f5e63af192760467df38b2788efadee28926da4
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: b493efb36209a2b52527ffb5291314f4b3eeb1a2e80588f5f20a5bd627aa91456acf51d7d4c088a1ef67806467ff4c86099e6ec8f489c9571df605bea60f47e9
|
7
|
+
data.tar.gz: bed0f9129ef6e737577644709d6d8b2a8e33db76a1b5ccb6e3f0adbbd69d5be3f76f0a4cd78675c8d6d5ab195d72afbe98b91bd6ba86b5b6275db723d35c0197
|
data/lib/horsefield/node.rb
CHANGED
@@ -8,7 +8,11 @@ module Horsefield
|
|
8
8
|
def process
|
9
9
|
case @html
|
10
10
|
when Nokogiri::XML::Element then
|
11
|
-
@
|
11
|
+
if @type == :text
|
12
|
+
@html.search('text()').to_s.split.join ' '
|
13
|
+
elsif @type == :html
|
14
|
+
@html.to_s
|
15
|
+
end
|
12
16
|
when Nokogiri::XML::Attr then
|
13
17
|
@html.value
|
14
18
|
end
|
data/lib/horsefield/node_set.rb
CHANGED
@@ -16,15 +16,15 @@ module Horsefield
|
|
16
16
|
def browse(*)
|
17
17
|
end
|
18
18
|
|
19
|
-
def one(name, selector, &block)
|
20
|
-
@nodes[name] = dig_deeper selector, &block
|
19
|
+
def one(name, selector, type = :text, &block)
|
20
|
+
@nodes[name] = dig_deeper selector, false, type, &block
|
21
21
|
end
|
22
22
|
|
23
23
|
def many(name, selector, &block)
|
24
24
|
@nodes[name] = dig_deeper selector, true, &block
|
25
25
|
end
|
26
26
|
|
27
|
-
def dig_deeper(selector, many = false, &block)
|
27
|
+
def dig_deeper(selector, many = false, type = :text, &block)
|
28
28
|
return nil if base_elements(selector).empty?
|
29
29
|
|
30
30
|
if block
|
@@ -38,10 +38,10 @@ module Horsefield
|
|
38
38
|
else
|
39
39
|
if many
|
40
40
|
base_elements(selector).map do |e|
|
41
|
-
Horsefield::Node.new(e).process(&block)
|
41
|
+
Horsefield::Node.new(e, type).process(&block)
|
42
42
|
end
|
43
43
|
else
|
44
|
-
Horsefield::Node.new(base_elements(selector).first).process(&block)
|
44
|
+
Horsefield::Node.new(base_elements(selector).first, type).process(&block)
|
45
45
|
end
|
46
46
|
end
|
47
47
|
end
|
data/lib/horsefield/version.rb
CHANGED
data/spec/scraper_spec.rb
CHANGED
@@ -31,6 +31,18 @@ describe Horsefield::Scraper do
|
|
31
31
|
result[:job][:missing].should be_nil
|
32
32
|
end
|
33
33
|
|
34
|
+
it 'can return HTML instead of text' do
|
35
|
+
result = Horsefield::Scraper.new.scrape html: @html do
|
36
|
+
one :job, '.listingsTable .odd, .listingsTable .even' do
|
37
|
+
one :title, '.jobTitleContainer', :html
|
38
|
+
one :company, '.companyContainer'
|
39
|
+
one :missing, '.doesNotExist'
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
result[:job][:title].should match(/<div class=\"jobTitleContainer\">/)
|
44
|
+
end
|
45
|
+
|
34
46
|
it 'works with Watir' do
|
35
47
|
browser = Watir::Browser.new :phantomjs
|
36
48
|
|
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: 0.2.
|
4
|
+
version: 0.2.5
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Erik Strömberg
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2013-
|
11
|
+
date: 2013-10-30 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: mechanize
|
@@ -166,7 +166,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
166
166
|
version: '0'
|
167
167
|
requirements: []
|
168
168
|
rubyforge_project:
|
169
|
-
rubygems_version: 2.
|
169
|
+
rubygems_version: 2.1.9
|
170
170
|
signing_key:
|
171
171
|
specification_version: 4
|
172
172
|
summary: It's a scraper
|