assaf-scrapi 1.2.1
Sign up to get free protection for your applications and to get access to all the features.
- data/CHANGELOG +36 -0
- data/MIT-LICENSE +20 -0
- data/README.rdoc +88 -0
- data/Rakefile +33 -0
- data/lib/html/document.rb +64 -0
- data/lib/html/htmlparser.rb +407 -0
- data/lib/html/node.rb +534 -0
- data/lib/html/node_ext.rb +86 -0
- data/lib/html/selector.rb +825 -0
- data/lib/html/tokenizer.rb +105 -0
- data/lib/html/version.rb +11 -0
- data/lib/scraper/base.rb +990 -0
- data/lib/scraper/microformats.rb +93 -0
- data/lib/scraper/reader.rb +240 -0
- data/lib/scrapi.rb +8 -0
- data/lib/tidy/libtidy.dll +0 -0
- data/lib/tidy/libtidy.so +0 -0
- data/test/mock_net_http.rb +54 -0
- data/test/node_ext_test.rb +24 -0
- data/test/reader_test.rb +318 -0
- data/test/scraper_test.rb +804 -0
- data/test/selector_test.rb +637 -0
- metadata +89 -0
metadata
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: assaf-scrapi
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 1.2.1
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Assaf Arkin
|
|
8
|
+
autorequire: scrapi.rb
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
|
|
12
|
+
date: 2008-08-13 00:00:00 -07:00
|
|
13
|
+
default_executable:
|
|
14
|
+
dependencies:
|
|
15
|
+
- !ruby/object:Gem::Dependency
|
|
16
|
+
name: tidy
|
|
17
|
+
version_requirement:
|
|
18
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
19
|
+
requirements:
|
|
20
|
+
- - ">="
|
|
21
|
+
- !ruby/object:Gem::Version
|
|
22
|
+
version: 1.1.0
|
|
23
|
+
version:
|
|
24
|
+
description: 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.
|
|
25
|
+
email: assaf@labnotes.org
|
|
26
|
+
executables: []
|
|
27
|
+
|
|
28
|
+
extensions: []
|
|
29
|
+
|
|
30
|
+
extra_rdoc_files:
|
|
31
|
+
- README.rdoc
|
|
32
|
+
files:
|
|
33
|
+
- test/selector_test.rb
|
|
34
|
+
- test/node_ext_test.rb
|
|
35
|
+
- test/scraper_test.rb
|
|
36
|
+
- test/mock_net_http.rb
|
|
37
|
+
- test/reader_test.rb
|
|
38
|
+
- lib/html
|
|
39
|
+
- lib/html/node_ext.rb
|
|
40
|
+
- lib/html/selector.rb
|
|
41
|
+
- lib/html/htmlparser.rb
|
|
42
|
+
- lib/html/node.rb
|
|
43
|
+
- lib/html/tokenizer.rb
|
|
44
|
+
- lib/html/document.rb
|
|
45
|
+
- lib/html/version.rb
|
|
46
|
+
- lib/tidy
|
|
47
|
+
- lib/tidy/libtidy.so
|
|
48
|
+
- lib/tidy/libtidy.dll
|
|
49
|
+
- lib/scraper
|
|
50
|
+
- lib/scraper/microformats.rb
|
|
51
|
+
- lib/scraper/base.rb
|
|
52
|
+
- lib/scraper/reader.rb
|
|
53
|
+
- lib/scrapi.rb
|
|
54
|
+
- README.rdoc
|
|
55
|
+
- CHANGELOG
|
|
56
|
+
- Rakefile
|
|
57
|
+
- MIT-LICENSE
|
|
58
|
+
has_rdoc: true
|
|
59
|
+
homepage: http://github.com/assaf/scrapi
|
|
60
|
+
post_install_message:
|
|
61
|
+
rdoc_options:
|
|
62
|
+
- --main
|
|
63
|
+
- README.rdoc
|
|
64
|
+
- --title
|
|
65
|
+
- scrAPI toolkit for Ruby
|
|
66
|
+
- --line-numbers
|
|
67
|
+
require_paths:
|
|
68
|
+
- lib
|
|
69
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
70
|
+
requirements:
|
|
71
|
+
- - ">="
|
|
72
|
+
- !ruby/object:Gem::Version
|
|
73
|
+
version: "0"
|
|
74
|
+
version:
|
|
75
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
76
|
+
requirements:
|
|
77
|
+
- - ">="
|
|
78
|
+
- !ruby/object:Gem::Version
|
|
79
|
+
version: "0"
|
|
80
|
+
version:
|
|
81
|
+
requirements:
|
|
82
|
+
- Tidy
|
|
83
|
+
rubyforge_project: scrapi
|
|
84
|
+
rubygems_version: 1.2.0
|
|
85
|
+
signing_key:
|
|
86
|
+
specification_version: 2
|
|
87
|
+
summary: scrAPI toolkit for Ruby. Uses CSS selectors to write easy, maintainable HTML scraping rules.
|
|
88
|
+
test_files: []
|
|
89
|
+
|