webpage 0.0.9 → 0.0.10

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/lib/webpage.rb CHANGED
@@ -14,6 +14,9 @@ class Webpage
14
14
  end
15
15
  @domain = options[:domain]
16
16
  end
17
+ def h1
18
+ @nokogiri.xpath("//h1").text
19
+ end
17
20
  def title
18
21
  @nokogiri.xpath("//title").text
19
22
  end
data/spec/webpage_spec.rb CHANGED
@@ -1,8 +1,10 @@
1
+ # encoding: utf-8
2
+
1
3
  #coding:UTF-8
2
4
  require 'webpage'
3
5
  sample = File.read(File.join(File.dirname(__FILE__),'sample'))
4
6
  sample_uri = 'http://www.hudong.com/wiki/甜菜根'
5
- sample_to_uri = 'http://123.hudong.com/'
7
+ sample_to_uri = 'http://www.hudong.com/'
6
8
  sample_not_to_uri = 'http://1234.hudong.com/'
7
9
  sample_to_host = 'hudong.com'
8
10
  sample_title = '甜菜根_互动百科'
@@ -28,8 +30,8 @@ describe Webpage do
28
30
  it "links should be an array" do
29
31
  page.links.class.should == Array
30
32
  end
31
- it "['h1'].to_a should return Array" do
32
- page['h1'].to_a.class.should == Array
33
+ it "h1 should return String" do
34
+ page.h1.class.should == String
33
35
  end
34
36
 
35
37
  it "[] should return class Nokogiri::XML::NodeSet" do
@@ -41,8 +43,8 @@ describe Webpage do
41
43
  it "nodes_with should return an array with elements Nokogiri::XML::NodeSet" do
42
44
  page.nodes_with('id').class.should == Nokogiri::XML::NodeSet
43
45
  end
44
- it "xpath should return an array with elements Nokogiri::XML::NodeSet" do
45
- page.xpath('//id').class.should == Nokogiri::XML::NodeSet
46
+ it "nokogiri.xpath should return an array with elements Nokogiri::XML::NodeSet" do
47
+ page.nokogiri.xpath('//id').class.should == Nokogiri::XML::NodeSet
46
48
  end
47
49
  it "links' elements should be Webpage::Link" do
48
50
  page.links.each do |link|
@@ -53,7 +55,7 @@ describe Webpage do
53
55
  it "description should be text" do
54
56
  page.description.class.should == String
55
57
  end
56
-
58
+
57
59
  it "keywords should be array" do
58
60
  page.keywords.class.should == Array
59
61
  end
@@ -63,7 +65,7 @@ describe Webpage do
63
65
  keyword.class.should == String
64
66
  end
65
67
  end
66
-
68
+
67
69
  it "link_to? should return bool" do
68
70
  [TrueClass,FalseClass].should include page.link_to?(sample_to_uri).class
69
71
  end
@@ -98,7 +100,7 @@ describe "the instance webpage of #{sample_uri}" do
98
100
  page.nodes_with('id').size.should == 92
99
101
  end
100
102
  it "should has <h1>#{sample_h1}"do
101
- page['h1'].text.should == sample_h1
103
+ page.h1.should == sample_h1
102
104
  end
103
105
  it "should has canonical to #{sample_uri}" do
104
106
  page.canonical.should == sample_uri
@@ -111,7 +113,7 @@ describe "the instance webpage of #{sample_uri}" do
111
113
  it "should not link_to #{sample_not_to_uri}" do
112
114
  page.link_to?(sample_not_to_uri).should be_false
113
115
  end
114
-
116
+
115
117
  it "should has link to " do
116
118
  page.links_to_different_host.any?{|link|link['href']}
117
119
  end
data/webpage.gemspec CHANGED
@@ -1,12 +1,12 @@
1
1
  Gem::Specification.new do |s|
2
2
  s.name = %q{webpage}
3
- s.version = '0.0.9'
3
+ s.version = '0.0.10'
4
4
  s.authors = ["seoaqua"]
5
- s.date = %q{2012-07-29}
5
+ s.date = %q{2013-02-28}
6
6
  s.description = %q{a tool to extract some basic data from a webpage}
7
7
  s.email = %q{seoaqua@qq.com}
8
8
  s.files = `git ls-files`.split("\n")
9
9
  s.homepage = %q{https://github.com/seoaqua/webpage}
10
10
  s.summary = s.description
11
- s.add_development_dependency 'mechanize'
11
+ s.add_development_dependency 'nokogiri'
12
12
  end
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: webpage
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.0.9
4
+ version: 0.0.10
5
5
  prerelease:
6
6
  platform: ruby
7
7
  authors:
@@ -9,10 +9,10 @@ authors:
9
9
  autorequire:
10
10
  bindir: bin
11
11
  cert_chain: []
12
- date: 2012-07-29 00:00:00.000000000 Z
12
+ date: 2013-02-28 00:00:00.000000000 Z
13
13
  dependencies:
14
14
  - !ruby/object:Gem::Dependency
15
- name: mechanize
15
+ name: nokogiri
16
16
  requirement: !ruby/object:Gem::Requirement
17
17
  none: false
18
18
  requirements:
@@ -60,7 +60,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
60
60
  version: '0'
61
61
  requirements: []
62
62
  rubyforge_project:
63
- rubygems_version: 1.8.24
63
+ rubygems_version: 1.8.25
64
64
  signing_key:
65
65
  specification_version: 3
66
66
  summary: a tool to extract some basic data from a webpage