omnivore 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +4 -0
- data/.rvmrc +7 -0
- data/Gemfile +4 -0
- data/README.md +1 -0
- data/Rakefile +1 -0
- data/lib/omnivore/http_client.rb +21 -0
- data/lib/omnivore/version.rb +3 -0
- data/lib/omnivore/xpath_extractor.rb +12 -0
- data/lib/omnivore.rb +7 -0
- data/omnivore.gemspec +24 -0
- data/spec/http_client_spec.rb +11 -0
- data/spec/xpath_extractor_spec.rb +30 -0
- metadata +78 -0
data/.gitignore
ADDED
data/.rvmrc
ADDED
data/Gemfile
ADDED
data/README.md
ADDED
|
@@ -0,0 +1 @@
|
|
|
1
|
+
Nothing to see here, move along.
|
data/Rakefile
ADDED
|
@@ -0,0 +1 @@
|
|
|
1
|
+
require "bundler/gem_tasks"
|
|
@@ -0,0 +1,21 @@
|
|
|
1
|
+
require 'net/http'
|
|
2
|
+
require 'uri'
|
|
3
|
+
|
|
4
|
+
module Omnivore
|
|
5
|
+
class HttpClient
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
def HttpClient.get(url, attempts=3)
|
|
9
|
+
raise ArgumentError, 'HTTP redirect too deep' if attempts == 0
|
|
10
|
+
|
|
11
|
+
response = Net::HTTP.get_response(URI.parse(url))
|
|
12
|
+
case response
|
|
13
|
+
when Net::HTTPSuccess then response.body
|
|
14
|
+
when Net::HTTPRedirection then HttpClient.get(response['location'], attempts - 1)
|
|
15
|
+
else
|
|
16
|
+
response.error!
|
|
17
|
+
end
|
|
18
|
+
end
|
|
19
|
+
|
|
20
|
+
end
|
|
21
|
+
end
|
data/lib/omnivore.rb
ADDED
data/omnivore.gemspec
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
|
2
|
+
$:.push File.expand_path("../lib", __FILE__)
|
|
3
|
+
require "omnivore/version"
|
|
4
|
+
|
|
5
|
+
Gem::Specification.new do |s|
|
|
6
|
+
s.name = "omnivore"
|
|
7
|
+
s.version = Omnivore::VERSION
|
|
8
|
+
s.authors = ["Matthias Eder"]
|
|
9
|
+
s.email = ["matthias@izume.com"]
|
|
10
|
+
s.homepage = ""
|
|
11
|
+
s.summary = %q{Content extraction and analysis}
|
|
12
|
+
s.description = %q{A library for extracting content from HTML documents.}
|
|
13
|
+
|
|
14
|
+
s.rubyforge_project = "omnivore"
|
|
15
|
+
|
|
16
|
+
s.files = `git ls-files`.split("\n")
|
|
17
|
+
s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
|
18
|
+
s.executables = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
|
|
19
|
+
s.require_paths = ["lib"]
|
|
20
|
+
|
|
21
|
+
# specify any dependencies here; for example:
|
|
22
|
+
s.add_development_dependency "rspec"
|
|
23
|
+
# s.add_runtime_dependency "rest-client"
|
|
24
|
+
end
|
|
@@ -0,0 +1,11 @@
|
|
|
1
|
+
require 'omnivore/http_client'
|
|
2
|
+
|
|
3
|
+
describe Omnivore::HttpClient do
|
|
4
|
+
|
|
5
|
+
it "should fetch the content of a url" do
|
|
6
|
+
html = Omnivore::HttpClient.get("http://blog.steveklabnik.com/posts/2011-09-28-real-modern-ruby-development")
|
|
7
|
+
html.should_not be_nil
|
|
8
|
+
html.should_not be_empty
|
|
9
|
+
end
|
|
10
|
+
|
|
11
|
+
end
|
|
@@ -0,0 +1,30 @@
|
|
|
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
|
metadata
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: omnivore
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
prerelease:
|
|
5
|
+
version: 0.0.1
|
|
6
|
+
platform: ruby
|
|
7
|
+
authors:
|
|
8
|
+
- Matthias Eder
|
|
9
|
+
autorequire:
|
|
10
|
+
bindir: bin
|
|
11
|
+
cert_chain: []
|
|
12
|
+
|
|
13
|
+
date: 2012-01-05 00:00:00 -07:00
|
|
14
|
+
default_executable:
|
|
15
|
+
dependencies:
|
|
16
|
+
- !ruby/object:Gem::Dependency
|
|
17
|
+
name: rspec
|
|
18
|
+
prerelease: false
|
|
19
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
|
20
|
+
none: false
|
|
21
|
+
requirements:
|
|
22
|
+
- - ">="
|
|
23
|
+
- !ruby/object:Gem::Version
|
|
24
|
+
version: "0"
|
|
25
|
+
type: :development
|
|
26
|
+
version_requirements: *id001
|
|
27
|
+
description: A library for extracting content from HTML documents.
|
|
28
|
+
email:
|
|
29
|
+
- matthias@izume.com
|
|
30
|
+
executables: []
|
|
31
|
+
|
|
32
|
+
extensions: []
|
|
33
|
+
|
|
34
|
+
extra_rdoc_files: []
|
|
35
|
+
|
|
36
|
+
files:
|
|
37
|
+
- .gitignore
|
|
38
|
+
- .rvmrc
|
|
39
|
+
- Gemfile
|
|
40
|
+
- README.md
|
|
41
|
+
- Rakefile
|
|
42
|
+
- lib/omnivore.rb
|
|
43
|
+
- lib/omnivore/http_client.rb
|
|
44
|
+
- lib/omnivore/version.rb
|
|
45
|
+
- lib/omnivore/xpath_extractor.rb
|
|
46
|
+
- omnivore.gemspec
|
|
47
|
+
- spec/http_client_spec.rb
|
|
48
|
+
- spec/xpath_extractor_spec.rb
|
|
49
|
+
has_rdoc: true
|
|
50
|
+
homepage: ""
|
|
51
|
+
licenses: []
|
|
52
|
+
|
|
53
|
+
post_install_message:
|
|
54
|
+
rdoc_options: []
|
|
55
|
+
|
|
56
|
+
require_paths:
|
|
57
|
+
- lib
|
|
58
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
59
|
+
none: false
|
|
60
|
+
requirements:
|
|
61
|
+
- - ">="
|
|
62
|
+
- !ruby/object:Gem::Version
|
|
63
|
+
version: "0"
|
|
64
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
65
|
+
none: false
|
|
66
|
+
requirements:
|
|
67
|
+
- - ">="
|
|
68
|
+
- !ruby/object:Gem::Version
|
|
69
|
+
version: "0"
|
|
70
|
+
requirements: []
|
|
71
|
+
|
|
72
|
+
rubyforge_project: omnivore
|
|
73
|
+
rubygems_version: 1.5.0
|
|
74
|
+
signing_key:
|
|
75
|
+
specification_version: 3
|
|
76
|
+
summary: Content extraction and analysis
|
|
77
|
+
test_files: []
|
|
78
|
+
|