omnivore 0.0.1 → 0.0.2
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/omnivore/document.rb +33 -0
- data/lib/omnivore/html_helper.rb +52 -0
- data/lib/omnivore/http_client.rb +1 -1
- data/lib/omnivore/version.rb +1 -1
- data/lib/omnivore.rb +3 -2
- data/omnivore.gemspec +2 -2
- data/spec/document_spec.rb +30 -0
- data/spec/html_helper_spec.rb +42 -0
- data/spec/http_client_spec.rb +1 -1
- metadata +18 -5
- data/lib/omnivore/xpath_extractor.rb +0 -12
- data/spec/xpath_extractor_spec.rb +0 -30
@@ -0,0 +1,33 @@
|
|
1
|
+
module Omnivore
|
2
|
+
require "omnivore/http_client"
|
3
|
+
require "omnivore/html_helper"
|
4
|
+
|
5
|
+
class Document
|
6
|
+
attr_reader :html
|
7
|
+
|
8
|
+
def self.from_url(url)
|
9
|
+
Document.new(HttpClient.get(url))
|
10
|
+
end
|
11
|
+
|
12
|
+
def self.from_html(html)
|
13
|
+
Document.new(html)
|
14
|
+
end
|
15
|
+
|
16
|
+
|
17
|
+
def initialize(html)
|
18
|
+
@html = html
|
19
|
+
end
|
20
|
+
|
21
|
+
|
22
|
+
def title
|
23
|
+
unless @title
|
24
|
+
matches = HtmlHelper.xpath(self.html, "/html/head/title")
|
25
|
+
@title = HtmlHelper.to_text(matches.first) || ""
|
26
|
+
end
|
27
|
+
@title
|
28
|
+
end
|
29
|
+
|
30
|
+
|
31
|
+
end
|
32
|
+
|
33
|
+
end
|
@@ -0,0 +1,52 @@
|
|
1
|
+
require "nokogiri"
|
2
|
+
|
3
|
+
module Omnivore
|
4
|
+
module HtmlHelper
|
5
|
+
|
6
|
+
class HtmlTransformer
|
7
|
+
|
8
|
+
def initialize(html)
|
9
|
+
@html = html
|
10
|
+
end
|
11
|
+
|
12
|
+
def to_text
|
13
|
+
document = Nokogiri::HTML.parse(@html)
|
14
|
+
partition(document, 'style', 'script').values.join(' ').strip.gsub(/\s+/, ' ')
|
15
|
+
end
|
16
|
+
|
17
|
+
def partition(node, *ignore_tags)
|
18
|
+
elements = { }
|
19
|
+
return elements if node.nil?
|
20
|
+
return elements if node.respond_to?('cdata?') and node.cdata?
|
21
|
+
return elements if node.respond_to?('comment?') and node.comment?
|
22
|
+
|
23
|
+
if node.kind_of?(Nokogiri::XML::Element) and ignore_tags and ignore_tags.size > 0
|
24
|
+
return elements if node.name =~ %r[#{ignore_tags.join('|')}]i
|
25
|
+
end
|
26
|
+
|
27
|
+
elements = { }
|
28
|
+
if node.kind_of?(Nokogiri::XML::Text)
|
29
|
+
elements[node.path.to_s] = node.text
|
30
|
+
return elements
|
31
|
+
end
|
32
|
+
node.children.each do |child|
|
33
|
+
elements.merge!(partition(child, *ignore_tags))
|
34
|
+
end
|
35
|
+
elements
|
36
|
+
end
|
37
|
+
|
38
|
+
end
|
39
|
+
|
40
|
+
def HtmlHelper.to_text(html)
|
41
|
+
transformer = HtmlTransformer.new(html)
|
42
|
+
transformer.to_text
|
43
|
+
end
|
44
|
+
|
45
|
+
|
46
|
+
def HtmlHelper.xpath(html, xpath)
|
47
|
+
document = Nokogiri::HTML.parse(html)
|
48
|
+
document.xpath(xpath).map { |m| m.to_html }
|
49
|
+
end
|
50
|
+
|
51
|
+
end
|
52
|
+
end
|
data/lib/omnivore/http_client.rb
CHANGED
data/lib/omnivore/version.rb
CHANGED
data/lib/omnivore.rb
CHANGED
data/omnivore.gemspec
CHANGED
@@ -19,6 +19,6 @@ Gem::Specification.new do |s|
|
|
19
19
|
s.require_paths = ["lib"]
|
20
20
|
|
21
21
|
# specify any dependencies here; for example:
|
22
|
-
s.add_development_dependency "rspec"
|
23
|
-
|
22
|
+
s.add_development_dependency "rspec", "~> 2.8.0"
|
23
|
+
s.add_runtime_dependency "nokogiri", "~> 1.5.0"
|
24
24
|
end
|
@@ -0,0 +1,30 @@
|
|
1
|
+
require 'omnivore/document'
|
2
|
+
include Omnivore
|
3
|
+
|
4
|
+
describe Document do
|
5
|
+
|
6
|
+
STATIC_HTML = %{
|
7
|
+
<html>
|
8
|
+
<head>
|
9
|
+
<title>Nothing To See</title>
|
10
|
+
</head>
|
11
|
+
<body>
|
12
|
+
<p>Nothing to see here, move along.</p>
|
13
|
+
</body>
|
14
|
+
</html>
|
15
|
+
}
|
16
|
+
|
17
|
+
it "should fetch the content of the provided url" do
|
18
|
+
document = Document.from_url("http://www.google.com")
|
19
|
+
document.html.should_not be_nil
|
20
|
+
document.html.should_not be_empty
|
21
|
+
end
|
22
|
+
|
23
|
+
it "should provide the document title" do
|
24
|
+
document = Document.from_html(STATIC_HTML)
|
25
|
+
document.title.should_not be_nil
|
26
|
+
document.title.should_not be_empty
|
27
|
+
document.title.should == "Nothing To See"
|
28
|
+
end
|
29
|
+
|
30
|
+
end
|
@@ -0,0 +1,42 @@
|
|
1
|
+
require "omnivore/html_helper"
|
2
|
+
include Omnivore
|
3
|
+
|
4
|
+
|
5
|
+
|
6
|
+
describe HtmlHelper do
|
7
|
+
|
8
|
+
it "should match the correct xpath" do
|
9
|
+
content = %{
|
10
|
+
<html>
|
11
|
+
<head></head>
|
12
|
+
<body>
|
13
|
+
<div class="banner">
|
14
|
+
I don't want to see this.
|
15
|
+
</div>
|
16
|
+
<div class="content">
|
17
|
+
This is what I want to see.
|
18
|
+
</div>
|
19
|
+
</body>
|
20
|
+
</html>
|
21
|
+
}
|
22
|
+
matches = HtmlHelper.xpath(content, "//div[@class=\"content\"]")
|
23
|
+
matches.size.should == 1
|
24
|
+
end
|
25
|
+
|
26
|
+
|
27
|
+
it "should be able to extract text from markup" do
|
28
|
+
html = %{
|
29
|
+
<p>
|
30
|
+
Content may contain some additional markup, such as:
|
31
|
+
<ul>
|
32
|
+
<li>Ordered or unordered lists,</li>
|
33
|
+
<li><a href="#">Hyperlinks,</a></li>
|
34
|
+
<li>and Images
|
35
|
+
</ul>
|
36
|
+
</p>
|
37
|
+
}
|
38
|
+
text = HtmlHelper.to_text(html)
|
39
|
+
text.should == "Content may contain some additional markup, such as: Ordered or unordered lists, Hyperlinks, and Images"
|
40
|
+
end
|
41
|
+
|
42
|
+
end
|
data/spec/http_client_spec.rb
CHANGED
@@ -3,7 +3,7 @@ require 'omnivore/http_client'
|
|
3
3
|
describe Omnivore::HttpClient do
|
4
4
|
|
5
5
|
it "should fetch the content of a url" do
|
6
|
-
html = Omnivore::HttpClient.get("http://
|
6
|
+
html = Omnivore::HttpClient.get("http://linksmart.com")
|
7
7
|
html.should_not be_nil
|
8
8
|
html.should_not be_empty
|
9
9
|
end
|
metadata
CHANGED
@@ -2,7 +2,7 @@
|
|
2
2
|
name: omnivore
|
3
3
|
version: !ruby/object:Gem::Version
|
4
4
|
prerelease:
|
5
|
-
version: 0.0.
|
5
|
+
version: 0.0.2
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
8
8
|
- Matthias Eder
|
@@ -19,11 +19,22 @@ dependencies:
|
|
19
19
|
requirement: &id001 !ruby/object:Gem::Requirement
|
20
20
|
none: false
|
21
21
|
requirements:
|
22
|
-
- -
|
22
|
+
- - ~>
|
23
23
|
- !ruby/object:Gem::Version
|
24
|
-
version:
|
24
|
+
version: 2.8.0
|
25
25
|
type: :development
|
26
26
|
version_requirements: *id001
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: nokogiri
|
29
|
+
prerelease: false
|
30
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
31
|
+
none: false
|
32
|
+
requirements:
|
33
|
+
- - ~>
|
34
|
+
- !ruby/object:Gem::Version
|
35
|
+
version: 1.5.0
|
36
|
+
type: :runtime
|
37
|
+
version_requirements: *id002
|
27
38
|
description: A library for extracting content from HTML documents.
|
28
39
|
email:
|
29
40
|
- matthias@izume.com
|
@@ -40,12 +51,14 @@ files:
|
|
40
51
|
- README.md
|
41
52
|
- Rakefile
|
42
53
|
- lib/omnivore.rb
|
54
|
+
- lib/omnivore/document.rb
|
55
|
+
- lib/omnivore/html_helper.rb
|
43
56
|
- lib/omnivore/http_client.rb
|
44
57
|
- lib/omnivore/version.rb
|
45
|
-
- lib/omnivore/xpath_extractor.rb
|
46
58
|
- omnivore.gemspec
|
59
|
+
- spec/document_spec.rb
|
60
|
+
- spec/html_helper_spec.rb
|
47
61
|
- spec/http_client_spec.rb
|
48
|
-
- spec/xpath_extractor_spec.rb
|
49
62
|
has_rdoc: true
|
50
63
|
homepage: ""
|
51
64
|
licenses: []
|
@@ -1,30 +0,0 @@
|
|
1
|
-
require "omnivore/xpath_extractor"
|
2
|
-
|
3
|
-
CONTENT = %{
|
4
|
-
<html>
|
5
|
-
<head></head>
|
6
|
-
<body>
|
7
|
-
<div class="banner">
|
8
|
-
This is a banner
|
9
|
-
</div>
|
10
|
-
<div class="topnav">
|
11
|
-
<ul>
|
12
|
-
<li>Home</li>
|
13
|
-
<li>About</li>
|
14
|
-
</ul>
|
15
|
-
</div>
|
16
|
-
<div class="content">
|
17
|
-
This is where the real stuff is.
|
18
|
-
</div>
|
19
|
-
</body>
|
20
|
-
</html>
|
21
|
-
}
|
22
|
-
|
23
|
-
describe Omnivore::XPathExtractor do
|
24
|
-
|
25
|
-
it "should match the correct xpath" do
|
26
|
-
matches = Omnivore::XPathExtractor.match(CONTENT, "//div[@class=\"content\"]")
|
27
|
-
matches.size.should be > 0
|
28
|
-
end
|
29
|
-
|
30
|
-
end
|