SFAscrapi 1.2.2

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.
Files changed (23) hide show
  1. data/CHANGELOG +36 -0
  2. data/MIT-LICENSE +20 -0
  3. data/README.rdoc +88 -0
  4. data/Rakefile +33 -0
  5. data/lib/html/document.rb +64 -0
  6. data/lib/html/htmlparser.rb +407 -0
  7. data/lib/html/node.rb +534 -0
  8. data/lib/html/node_ext.rb +86 -0
  9. data/lib/html/selector.rb +825 -0
  10. data/lib/html/tokenizer.rb +105 -0
  11. data/lib/html/version.rb +11 -0
  12. data/lib/scraper/base.rb +990 -0
  13. data/lib/scraper/microformats.rb +93 -0
  14. data/lib/scraper/reader.rb +240 -0
  15. data/lib/scrapi.rb +8 -0
  16. data/lib/tidy/libtidy.dll +0 -0
  17. data/lib/tidy/libtidy.so +0 -0
  18. data/test/mock_net_http.rb +54 -0
  19. data/test/node_ext_test.rb +24 -0
  20. data/test/reader_test.rb +318 -0
  21. data/test/scraper_test.rb +804 -0
  22. data/test/selector_test.rb +637 -0
  23. metadata +107 -0
metadata ADDED
@@ -0,0 +1,107 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: SFAscrapi
3
+ version: !ruby/object:Gem::Version
4
+ hash: 27
5
+ prerelease: false
6
+ segments:
7
+ - 1
8
+ - 2
9
+ - 2
10
+ version: 1.2.2
11
+ platform: ruby
12
+ authors:
13
+ - Assaf Arkin
14
+ autorequire: scrapi.rb
15
+ bindir: bin
16
+ cert_chain: []
17
+
18
+ date: 2010-10-19 00:00:00 -04:00
19
+ default_executable:
20
+ dependencies:
21
+ - !ruby/object:Gem::Dependency
22
+ name: SFAtidy
23
+ prerelease: false
24
+ requirement: &id001 !ruby/object:Gem::Requirement
25
+ none: false
26
+ requirements:
27
+ - - ">="
28
+ - !ruby/object:Gem::Version
29
+ hash: 3
30
+ segments:
31
+ - 0
32
+ version: "0"
33
+ type: :runtime
34
+ version_requirements: *id001
35
+ description: |
36
+ scrAPI is an HTML scraping toolkit for Ruby. It uses CSS selectors to write easy, maintainable scraping rules to select, extract and store data from HTML content.
37
+
38
+ email: assaf@labnotes.org
39
+ executables: []
40
+
41
+ extensions: []
42
+
43
+ extra_rdoc_files:
44
+ - README.rdoc
45
+ files:
46
+ - test/mock_net_http.rb
47
+ - test/node_ext_test.rb
48
+ - test/reader_test.rb
49
+ - test/scraper_test.rb
50
+ - test/selector_test.rb
51
+ - lib/html/document.rb
52
+ - lib/html/htmlparser.rb
53
+ - lib/html/node.rb
54
+ - lib/html/node_ext.rb
55
+ - lib/html/selector.rb
56
+ - lib/html/tokenizer.rb
57
+ - lib/html/version.rb
58
+ - lib/scraper/base.rb
59
+ - lib/scraper/microformats.rb
60
+ - lib/scraper/reader.rb
61
+ - lib/scrapi.rb
62
+ - lib/tidy/libtidy.dll
63
+ - lib/tidy/libtidy.so
64
+ - README.rdoc
65
+ - CHANGELOG
66
+ - Rakefile
67
+ - MIT-LICENSE
68
+ has_rdoc: true
69
+ homepage: http://github.com/assaf/scrapi
70
+ licenses: []
71
+
72
+ post_install_message:
73
+ rdoc_options:
74
+ - --main
75
+ - README.rdoc
76
+ - --title
77
+ - scrAPI toolkit for Ruby
78
+ - --line-numbers
79
+ require_paths:
80
+ - lib
81
+ required_ruby_version: !ruby/object:Gem::Requirement
82
+ none: false
83
+ requirements:
84
+ - - ">="
85
+ - !ruby/object:Gem::Version
86
+ hash: 3
87
+ segments:
88
+ - 0
89
+ version: "0"
90
+ required_rubygems_version: !ruby/object:Gem::Requirement
91
+ none: false
92
+ requirements:
93
+ - - ">="
94
+ - !ruby/object:Gem::Version
95
+ hash: 3
96
+ segments:
97
+ - 0
98
+ version: "0"
99
+ requirements:
100
+ - Tidy
101
+ rubyforge_project: scrapi
102
+ rubygems_version: 1.3.7
103
+ signing_key:
104
+ specification_version: 3
105
+ summary: scrAPI toolkit for Ruby. Uses CSS selectors to write easy, maintainable HTML scraping rules.
106
+ test_files: []
107
+