extractula 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/README.textile +0 -0
- data/lib/extractula/dom_extractor.rb +68 -0
- data/lib/extractula/extracted_content.rb +32 -0
- data/lib/extractula.rb +24 -0
- data/spec/extractula/dom_extractor_spec.rb +109 -0
- data/spec/extractula/extracted_content_spec.rb +48 -0
- data/spec/extractula_spec.rb +45 -0
- data/spec/spec.opts +2 -0
- data/spec/spec_helper.rb +14 -0
- data/spec/test-files/10-stunning-web-site-prototype-sketches.html +986 -0
- data/spec/test-files/nytimes.html +1967 -0
- data/spec/test-files/nytimes_story.html +1112 -0
- data/spec/test-files/totlol-youtube.html +563 -0
- data/spec/test-files/typhoeus-the-best-ruby-http-client-just-got-better.html +576 -0
- data/spec/test-files/ustream-new-years-eve.html +840 -0
- data/spec/test-files/weather-channel-marriage-proposal-touching-with-a-chance-of-viral-status-video.html +949 -0
- metadata +79 -0
metadata
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: extractula
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.0.1
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Paul Dix
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
|
|
12
|
+
date: 2009-12-18 00:00:00 -05:00
|
|
13
|
+
default_executable:
|
|
14
|
+
dependencies:
|
|
15
|
+
- !ruby/object:Gem::Dependency
|
|
16
|
+
name: nokogiri
|
|
17
|
+
type: :runtime
|
|
18
|
+
version_requirement:
|
|
19
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
20
|
+
requirements:
|
|
21
|
+
- - ">"
|
|
22
|
+
- !ruby/object:Gem::Version
|
|
23
|
+
version: 0.0.0
|
|
24
|
+
version:
|
|
25
|
+
description:
|
|
26
|
+
email: paul@pauldix.net
|
|
27
|
+
executables: []
|
|
28
|
+
|
|
29
|
+
extensions: []
|
|
30
|
+
|
|
31
|
+
extra_rdoc_files: []
|
|
32
|
+
|
|
33
|
+
files:
|
|
34
|
+
- lib/extractula.rb
|
|
35
|
+
- lib/extractula/extracted_content.rb
|
|
36
|
+
- lib/extractula/dom_extractor.rb
|
|
37
|
+
- README.textile
|
|
38
|
+
- spec/spec.opts
|
|
39
|
+
- spec/spec_helper.rb
|
|
40
|
+
- spec/extractula_spec.rb
|
|
41
|
+
- spec/extractula/extracted_content_spec.rb
|
|
42
|
+
- spec/extractula/dom_extractor_spec.rb
|
|
43
|
+
- spec/test-files/10-stunning-web-site-prototype-sketches.html
|
|
44
|
+
- spec/test-files/totlol-youtube.html
|
|
45
|
+
- spec/test-files/typhoeus-the-best-ruby-http-client-just-got-better.html
|
|
46
|
+
- spec/test-files/ustream-new-years-eve.html
|
|
47
|
+
- spec/test-files/weather-channel-marriage-proposal-touching-with-a-chance-of-viral-status-video.html
|
|
48
|
+
- spec/test-files/nytimes.html
|
|
49
|
+
- spec/test-files/nytimes_story.html
|
|
50
|
+
has_rdoc: true
|
|
51
|
+
homepage: http://github.com/pauldix/extractula
|
|
52
|
+
licenses: []
|
|
53
|
+
|
|
54
|
+
post_install_message:
|
|
55
|
+
rdoc_options: []
|
|
56
|
+
|
|
57
|
+
require_paths:
|
|
58
|
+
- lib
|
|
59
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
60
|
+
requirements:
|
|
61
|
+
- - ">="
|
|
62
|
+
- !ruby/object:Gem::Version
|
|
63
|
+
version: "0"
|
|
64
|
+
version:
|
|
65
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
66
|
+
requirements:
|
|
67
|
+
- - ">="
|
|
68
|
+
- !ruby/object:Gem::Version
|
|
69
|
+
version: "0"
|
|
70
|
+
version:
|
|
71
|
+
requirements: []
|
|
72
|
+
|
|
73
|
+
rubyforge_project:
|
|
74
|
+
rubygems_version: 1.3.5
|
|
75
|
+
signing_key:
|
|
76
|
+
specification_version: 2
|
|
77
|
+
summary: "Extracts content like title, summary, and images from web pages like Dracula extracts blood: with care and finesse."
|
|
78
|
+
test_files: []
|
|
79
|
+
|