newscrapi 0.0.11
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/.gitignore +23 -0
- data/LICENSE +20 -0
- data/README.rdoc +17 -0
- data/Rakefile +56 -0
- data/VERSION +1 -0
- data/config/content_scrapper.rb +3 -0
- data/doc/classes/ContentMapping.html +242 -0
- data/doc/classes/ContentMapping.src/M000001.html +18 -0
- data/doc/classes/ContentMapping.src/M000002.html +18 -0
- data/doc/classes/ContentMapping.src/M000003.html +18 -0
- data/doc/classes/ContentMapping.src/M000004.html +19 -0
- data/doc/classes/ContentMapping.src/M000005.html +18 -0
- data/doc/classes/ContentMapping.src/M000006.html +25 -0
- data/doc/classes/ContentScrapper.html +297 -0
- data/doc/classes/ContentScrapper.src/M000007.html +18 -0
- data/doc/classes/ContentScrapper.src/M000008.html +18 -0
- data/doc/classes/ContentScrapper.src/M000009.html +20 -0
- data/doc/classes/ContentScrapper.src/M000010.html +20 -0
- data/doc/classes/ContentScrapper.src/M000011.html +18 -0
- data/doc/classes/ContentScrapper.src/M000012.html +21 -0
- data/doc/classes/ContentScrapper.src/M000013.html +21 -0
- data/doc/classes/ContentScrapper.src/M000014.html +33 -0
- data/doc/classes/ContentScrapper.src/M000015.html +18 -0
- data/doc/classes/ContentScrapper.src/M000016.html +18 -0
- data/doc/classes/Feedzirra.html +111 -0
- data/doc/classes/Feedzirra/FeedEntryUtilities.html +152 -0
- data/doc/classes/Feedzirra/FeedEntryUtilities.src/M000017.html +18 -0
- data/doc/classes/Feedzirra/FeedEntryUtilities.src/M000018.html +18 -0
- data/doc/created.rid +1 -0
- data/doc/files/lib/content_scrapper/content_mapping_rb.html +108 -0
- data/doc/files/lib/content_scrapper/feedzirra_rb.html +115 -0
- data/doc/files/lib/content_scrapper_rb.html +112 -0
- data/doc/fr_class_index.html +30 -0
- data/doc/fr_file_index.html +29 -0
- data/doc/fr_method_index.html +44 -0
- data/doc/index.html +24 -0
- data/doc/rdoc-style.css +208 -0
- data/lib/newscrapi.rb +2 -0
- data/lib/newscrapi/encoding.rb +44 -0
- data/lib/newscrapi/feedzirra.rb +17 -0
- data/lib/newscrapi/mapping.rb +50 -0
- data/lib/newscrapi/scrapper.rb +129 -0
- data/lib/newscrapi/testing.rb +19 -0
- data/rails/init.rb +3 -0
- data/test/helper.rb +9 -0
- data/test/test_encoding.rb +43 -0
- data/test/test_mapping.rb +58 -0
- data/test/test_pages.rb +69 -0
- data/test/test_pages/cdata.html +23 -0
- data/test/test_pages/page_without_encoding_meta_tag.html +401 -0
- data/test/test_pages/pretty.html +17 -0
- data/test/test_pages/pretty_missing_content.html +17 -0
- data/test/test_pages/twocontent.html +11 -0
- data/test/test_pages/ugly.html +399 -0
- data/test/test_pages/utf-8_page.html +405 -0
- data/test/test_pages/windows-1250_page.html +460 -0
- data/test/test_scrapper.rb +257 -0
- metadata +191 -0
@@ -0,0 +1,257 @@
|
|
1
|
+
require 'helper'
|
2
|
+
require 'mocha'
|
3
|
+
|
4
|
+
class TestScrapper < Test::Unit::TestCase
|
5
|
+
|
6
|
+
Newscrapi::Scrapper.default_config_file = nil
|
7
|
+
|
8
|
+
context "on settings without sanitization tags" do
|
9
|
+
setup do
|
10
|
+
@scrapper = Newscrapi::Scrapper.new
|
11
|
+
@scrapper.instance_eval do
|
12
|
+
content_mapping do
|
13
|
+
url_pattern /.*/
|
14
|
+
content_at '//div[@id="itext_content"]'
|
15
|
+
end
|
16
|
+
end
|
17
|
+
content = File.open("#{File.dirname(__FILE__)}/test_pages/pretty.html").read
|
18
|
+
stringio = StringIO.new(content)
|
19
|
+
Kernel.expects(:open).returns(stringio)
|
20
|
+
end
|
21
|
+
should 'not sanitize' do
|
22
|
+
assert !@scrapper.scrap_content('http://www.pretty.url/fsdsd').nil?
|
23
|
+
end
|
24
|
+
end
|
25
|
+
|
26
|
+
context "on common settings" do
|
27
|
+
setup do
|
28
|
+
@scrapper = Newscrapi::Scrapper.new
|
29
|
+
@scrapper.instance_eval do
|
30
|
+
content_mapping do
|
31
|
+
url_pattern /^http:\/\/www\.pretty\.url/
|
32
|
+
content_at '//div[@id="failing_content"]'
|
33
|
+
content_at '//div[@id="itext_content"]'
|
34
|
+
end
|
35
|
+
|
36
|
+
content_mapping do
|
37
|
+
url_pattern /^http:\/\/www\.twopatterns\.url/
|
38
|
+
content_at '//div[@id="failing_content"]'
|
39
|
+
content_at '//div[@id="itext_content"]'
|
40
|
+
end
|
41
|
+
|
42
|
+
content_mapping do
|
43
|
+
url_pattern /^http:\/\/www\.twopatterns\.url/
|
44
|
+
content_at '//div[@id="itext_second_content"]'
|
45
|
+
end
|
46
|
+
|
47
|
+
content_mapping do
|
48
|
+
url_pattern /^http:\/\/www\.skipper\.url/
|
49
|
+
end
|
50
|
+
|
51
|
+
content_mapping do
|
52
|
+
url_pattern /^http:\/\/www\.skipper\.url/
|
53
|
+
content_at '//div[@id="never_should_be_here"]'
|
54
|
+
end
|
55
|
+
|
56
|
+
sanitize_tags do
|
57
|
+
{:elements => ['p','br', 'b', 'em', 'i', 'strong', 'u', 'a', 'h1', 'h2', 'h3', 'li', 'ol', 'ul'], \
|
58
|
+
:attributes => { 'a' => ['href'] }}
|
59
|
+
end
|
60
|
+
end
|
61
|
+
end
|
62
|
+
|
63
|
+
should "identify the correct content mapper" do
|
64
|
+
content_mapper = @scrapper.matching_content_mapper('http://www.pretty.url/fsdsd')
|
65
|
+
assert !content_mapper.nil?
|
66
|
+
assert_equal /^http:\/\/www\.pretty\.url/, content_mapper.url_pattern_regexp
|
67
|
+
end
|
68
|
+
|
69
|
+
context "for known sources with expected content scrapping" do
|
70
|
+
setup do
|
71
|
+
pretty_content = File.open("#{File.dirname(__FILE__)}/test_pages/pretty.html").read
|
72
|
+
stringio = StringIO.new(pretty_content)
|
73
|
+
Kernel.expects(:open).returns(stringio)
|
74
|
+
@entry_content = @scrapper.scrap_content('http://www.pretty.url/fsdsd')
|
75
|
+
end
|
76
|
+
should("identify the content") do
|
77
|
+
assert_match(%r{<p><strong>This is a strong text</strong></p>}, @entry_content)
|
78
|
+
end
|
79
|
+
end
|
80
|
+
|
81
|
+
context "for known pages with unexpected content scrapping" do
|
82
|
+
setup do
|
83
|
+
ugly_content = File.open("#{File.dirname(__FILE__)}/test_pages/ugly.html").read
|
84
|
+
stringio = StringIO.new(ugly_content)
|
85
|
+
Kernel.expects(:open).returns(stringio)
|
86
|
+
@entry_content = @scrapper.scrap_content('http://www.pretty.url/hsdae')
|
87
|
+
end
|
88
|
+
should("return nil") { assert_nil @entry_content }
|
89
|
+
end
|
90
|
+
|
91
|
+
context "for unknown pages" do
|
92
|
+
setup { @entry_content = @scrapper.scrap_content('http://www.unknown.url/hsdae') }
|
93
|
+
should("return nil") { assert_nil @entry_content }
|
94
|
+
end
|
95
|
+
|
96
|
+
context "multiple matching url patterns" do
|
97
|
+
setup do
|
98
|
+
twocontent = File.open("#{File.dirname(__FILE__)}/test_pages/twocontent.html").read
|
99
|
+
stringio = StringIO.new(twocontent)
|
100
|
+
Kernel.expects(:open).with('http://www.twopatterns.url').returns(stringio)
|
101
|
+
@entry_content = @scrapper.scrap_content('http://www.twopatterns.url')
|
102
|
+
end
|
103
|
+
should "match the first content" do
|
104
|
+
assert_equal 'The first one is matched', @entry_content
|
105
|
+
end
|
106
|
+
end
|
107
|
+
|
108
|
+
context "skipper patterns" do
|
109
|
+
setup do
|
110
|
+
Kernel.expects(:open).with('http://www.skipper.url/fdgsw').never
|
111
|
+
@entry_content = @scrapper.scrap_content('http://www.skipper.url/fdgsw')
|
112
|
+
end
|
113
|
+
should("not match enything") { assert_nil @entry_content }
|
114
|
+
end
|
115
|
+
|
116
|
+
context "on already downloaded document" do
|
117
|
+
setup do
|
118
|
+
pretty_content = File.open("#{File.dirname(__FILE__)}/test_pages/pretty.html").read
|
119
|
+
Kernel.expects(:open).never
|
120
|
+
@scrapped_content = @scrapper.scrap_content('http://www.pretty.url/hsdae',
|
121
|
+
:use_page => pretty_content)
|
122
|
+
end
|
123
|
+
should "scrap from the provided full page" do
|
124
|
+
assert_match(%r{<p><strong>This is a strong text</strong></p>}, @scrapped_content)
|
125
|
+
end
|
126
|
+
end
|
127
|
+
|
128
|
+
context "on scrapping with feedzirra" do
|
129
|
+
setup do
|
130
|
+
require 'newscrapi/feedzirra'
|
131
|
+
require 'sax-machine'
|
132
|
+
require 'feedzirra/parser/rss_entry'
|
133
|
+
require 'feedzirra/parser/atom_entry'
|
134
|
+
end
|
135
|
+
|
136
|
+
context "feed entry with not parsable remote content, but with feed content set" do
|
137
|
+
setup do
|
138
|
+
@feed_entries = [ Feedzirra::Parser::RSSEntry.new, Feedzirra::Parser::AtomEntry.new ]
|
139
|
+
@feed_entries.each do |feed_entry|
|
140
|
+
feed_entry.url = 'http://www.unknown.url/wedhsf'
|
141
|
+
feed_entry.content = 'Pretty well written content is this.'
|
142
|
+
end
|
143
|
+
Kernel.expects(:open).with('http://www.unknown.url/wedhsf').never
|
144
|
+
end
|
145
|
+
should("return the original feed content") do
|
146
|
+
@feed_entries.each do |feed_entry|
|
147
|
+
assert_equal 'Pretty well written content is this.', feed_entry.scrap_content(@scrapper)
|
148
|
+
feed_entry.scrap_content!(@scrapper)
|
149
|
+
assert_equal 'Pretty well written content is this.', feed_entry.content
|
150
|
+
end
|
151
|
+
end
|
152
|
+
end
|
153
|
+
|
154
|
+
context "on feed entry with url and scrapping with full_page" do
|
155
|
+
setup do
|
156
|
+
@feed_entries = [ Feedzirra::Parser::RSSEntry.new, Feedzirra::Parser::AtomEntry.new ]
|
157
|
+
@feed_entries.each do |feed_entry|
|
158
|
+
feed_entry.url = 'http://www.pretty.url/wedhsf'
|
159
|
+
end
|
160
|
+
@pretty_content = File.open("#{File.dirname(__FILE__)}/test_pages/pretty.html").read
|
161
|
+
Kernel.expects(:open).never
|
162
|
+
end
|
163
|
+
should("return the original feed content") do
|
164
|
+
@feed_entries.each do |feed_entry|
|
165
|
+
assert_match(%r{<p><strong>This is a strong text</strong></p>},
|
166
|
+
feed_entry.scrap_content(@scrapper, :use_page => @pretty_content))
|
167
|
+
feed_entry.scrap_content!(@scrapper, :use_page => @pretty_content)
|
168
|
+
assert_match(%r{<p><strong>This is a strong text</strong></p>}, feed_entry.content)
|
169
|
+
end
|
170
|
+
end
|
171
|
+
end
|
172
|
+
end
|
173
|
+
|
174
|
+
context "on failing scrapping" do
|
175
|
+
setup do
|
176
|
+
Kernel.expects(:open).raises(Exception, 'something failed')
|
177
|
+
@exception_handle_flag = nil
|
178
|
+
@scrapper.rescue_scrapping do |exception, url|
|
179
|
+
@exception_handle_flag = exception.message
|
180
|
+
@exception_url = url
|
181
|
+
end
|
182
|
+
end
|
183
|
+
should "catch the exception and handle it" do
|
184
|
+
assert_nil @scrapper.scrap_content('http://www.pretty.url')
|
185
|
+
assert_equal 'something failed', @exception_handle_flag
|
186
|
+
assert_equal 'http://www.pretty.url', @exception_url
|
187
|
+
end
|
188
|
+
end
|
189
|
+
|
190
|
+
context "on missing url matcher" do
|
191
|
+
setup do
|
192
|
+
Kernel.expects(:open).never
|
193
|
+
@missing_url_matcher_flag = nil
|
194
|
+
@scrapper.missing_url_matcher do |url|
|
195
|
+
@missing_url_matcher_flag = url
|
196
|
+
end
|
197
|
+
@scrapper.scrap_content('http://missing.url.matcher')
|
198
|
+
end
|
199
|
+
should "call the handler block" do
|
200
|
+
assert_equal 'http://missing.url.matcher', @missing_url_matcher_flag
|
201
|
+
end
|
202
|
+
end
|
203
|
+
|
204
|
+
context "on matching content mapper finding empty content" do
|
205
|
+
setup do
|
206
|
+
twocontent = File.open("#{File.dirname(__FILE__)}/test_pages/pretty_missing_content.html").read
|
207
|
+
stringio = StringIO.new(twocontent)
|
208
|
+
Kernel.expects(:open).with('http://www.pretty.url').returns(stringio)
|
209
|
+
@missing_content_flag = 0
|
210
|
+
@scrapper.missing_content do |url|
|
211
|
+
@missing_content_flag += 1
|
212
|
+
end
|
213
|
+
@scrapper.scrap_content('http://www.pretty.url')
|
214
|
+
end
|
215
|
+
should "call the handler block only once" do
|
216
|
+
assert_equal 1, @missing_content_flag
|
217
|
+
end
|
218
|
+
end
|
219
|
+
end
|
220
|
+
|
221
|
+
context "on setting default content scrapper" do
|
222
|
+
setup { @scrapper = Newscrapi::Scrapper.create_new_default }
|
223
|
+
should "set the default to the recently created" do
|
224
|
+
assert_equal @scrapper, Newscrapi::Scrapper.default
|
225
|
+
end
|
226
|
+
context "when changing default content scrapper" do
|
227
|
+
setup { @new_scrapper = Newscrapi::Scrapper.new.set_as_default }
|
228
|
+
should "change the default to the new content scrapper" do
|
229
|
+
assert_equal @new_scrapper, Newscrapi::Scrapper.default
|
230
|
+
end
|
231
|
+
end
|
232
|
+
|
233
|
+
context "for feed entry" do
|
234
|
+
setup do
|
235
|
+
@feed_entry = Feedzirra::Parser::RSSEntry.new
|
236
|
+
@feed_entry.url = 'http://www.unknown.url/gerhe'
|
237
|
+
@feed_entry.content = 'We should get this.'
|
238
|
+
end
|
239
|
+
should("scrap content by the default scrapper") do
|
240
|
+
assert_equal 'We should get this.', @feed_entry.scrap_content
|
241
|
+
end
|
242
|
+
end
|
243
|
+
end
|
244
|
+
|
245
|
+
context "on giving standard package of settings" do
|
246
|
+
setup do
|
247
|
+
@scrapper = Newscrapi::Scrapper.new
|
248
|
+
@scrapper.report_to_stderr
|
249
|
+
end
|
250
|
+
should "have the reporters set" do
|
251
|
+
assert !@scrapper.scrapping_exception_handler_block.nil?
|
252
|
+
assert !@scrapper.missing_url_matcher_handler_block.nil?
|
253
|
+
assert !@scrapper.missing_content_handler_block.nil?
|
254
|
+
end
|
255
|
+
end
|
256
|
+
end
|
257
|
+
|
metadata
ADDED
@@ -0,0 +1,191 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: newscrapi
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 9
|
5
|
+
prerelease: false
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 0
|
9
|
+
- 11
|
10
|
+
version: 0.0.11
|
11
|
+
platform: ruby
|
12
|
+
authors:
|
13
|
+
- Gyorgy Frivolt
|
14
|
+
autorequire:
|
15
|
+
bindir: bin
|
16
|
+
cert_chain: []
|
17
|
+
|
18
|
+
date: 2010-10-11 00:00:00 +02:00
|
19
|
+
default_executable:
|
20
|
+
dependencies:
|
21
|
+
- !ruby/object:Gem::Dependency
|
22
|
+
name: thoughtbot-shoulda
|
23
|
+
prerelease: false
|
24
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ">="
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
hash: 35
|
30
|
+
segments:
|
31
|
+
- 2
|
32
|
+
- 10
|
33
|
+
- 2
|
34
|
+
version: 2.10.2
|
35
|
+
type: :development
|
36
|
+
version_requirements: *id001
|
37
|
+
- !ruby/object:Gem::Dependency
|
38
|
+
name: mocha
|
39
|
+
prerelease: false
|
40
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ">="
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
hash: 43
|
46
|
+
segments:
|
47
|
+
- 0
|
48
|
+
- 9
|
49
|
+
- 8
|
50
|
+
version: 0.9.8
|
51
|
+
type: :development
|
52
|
+
version_requirements: *id002
|
53
|
+
- !ruby/object:Gem::Dependency
|
54
|
+
name: nokogiri
|
55
|
+
prerelease: false
|
56
|
+
requirement: &id003 !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
hash: 5
|
62
|
+
segments:
|
63
|
+
- 1
|
64
|
+
- 4
|
65
|
+
- 1
|
66
|
+
version: 1.4.1
|
67
|
+
type: :runtime
|
68
|
+
version_requirements: *id003
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: rchardet
|
71
|
+
prerelease: false
|
72
|
+
requirement: &id004 !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ">="
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
hash: 3
|
78
|
+
segments:
|
79
|
+
- 0
|
80
|
+
version: "0"
|
81
|
+
type: :runtime
|
82
|
+
version_requirements: *id004
|
83
|
+
description: If you want to cut only the content of pages, without any other part (like the menu, header, footer, commercials, etc.), you might find this gem very handy. A DSL is also defined for nifty definitions for your screen scrapping and sanitization.
|
84
|
+
email: gyorgy.frivolt@gmail.com
|
85
|
+
executables: []
|
86
|
+
|
87
|
+
extensions: []
|
88
|
+
|
89
|
+
extra_rdoc_files:
|
90
|
+
- LICENSE
|
91
|
+
- README.rdoc
|
92
|
+
files:
|
93
|
+
- .document
|
94
|
+
- .gitignore
|
95
|
+
- LICENSE
|
96
|
+
- README.rdoc
|
97
|
+
- Rakefile
|
98
|
+
- VERSION
|
99
|
+
- config/content_scrapper.rb
|
100
|
+
- doc/classes/ContentMapping.html
|
101
|
+
- doc/classes/ContentMapping.src/M000001.html
|
102
|
+
- doc/classes/ContentMapping.src/M000002.html
|
103
|
+
- doc/classes/ContentMapping.src/M000003.html
|
104
|
+
- doc/classes/ContentMapping.src/M000004.html
|
105
|
+
- doc/classes/ContentMapping.src/M000005.html
|
106
|
+
- doc/classes/ContentMapping.src/M000006.html
|
107
|
+
- doc/classes/ContentScrapper.html
|
108
|
+
- doc/classes/ContentScrapper.src/M000007.html
|
109
|
+
- doc/classes/ContentScrapper.src/M000008.html
|
110
|
+
- doc/classes/ContentScrapper.src/M000009.html
|
111
|
+
- doc/classes/ContentScrapper.src/M000010.html
|
112
|
+
- doc/classes/ContentScrapper.src/M000011.html
|
113
|
+
- doc/classes/ContentScrapper.src/M000012.html
|
114
|
+
- doc/classes/ContentScrapper.src/M000013.html
|
115
|
+
- doc/classes/ContentScrapper.src/M000014.html
|
116
|
+
- doc/classes/ContentScrapper.src/M000015.html
|
117
|
+
- doc/classes/ContentScrapper.src/M000016.html
|
118
|
+
- doc/classes/Feedzirra.html
|
119
|
+
- doc/classes/Feedzirra/FeedEntryUtilities.html
|
120
|
+
- doc/classes/Feedzirra/FeedEntryUtilities.src/M000017.html
|
121
|
+
- doc/classes/Feedzirra/FeedEntryUtilities.src/M000018.html
|
122
|
+
- doc/created.rid
|
123
|
+
- doc/files/lib/content_scrapper/content_mapping_rb.html
|
124
|
+
- doc/files/lib/content_scrapper/feedzirra_rb.html
|
125
|
+
- doc/files/lib/content_scrapper_rb.html
|
126
|
+
- doc/fr_class_index.html
|
127
|
+
- doc/fr_file_index.html
|
128
|
+
- doc/fr_method_index.html
|
129
|
+
- doc/index.html
|
130
|
+
- doc/rdoc-style.css
|
131
|
+
- lib/newscrapi.rb
|
132
|
+
- lib/newscrapi/encoding.rb
|
133
|
+
- lib/newscrapi/feedzirra.rb
|
134
|
+
- lib/newscrapi/mapping.rb
|
135
|
+
- lib/newscrapi/scrapper.rb
|
136
|
+
- lib/newscrapi/testing.rb
|
137
|
+
- newscrapi.gemspec
|
138
|
+
- rails/init.rb
|
139
|
+
- test/helper.rb
|
140
|
+
- test/test_encoding.rb
|
141
|
+
- test/test_mapping.rb
|
142
|
+
- test/test_pages.rb
|
143
|
+
- test/test_pages/cdata.html
|
144
|
+
- test/test_pages/page_without_encoding_meta_tag.html
|
145
|
+
- test/test_pages/pretty.html
|
146
|
+
- test/test_pages/pretty_missing_content.html
|
147
|
+
- test/test_pages/twocontent.html
|
148
|
+
- test/test_pages/ugly.html
|
149
|
+
- test/test_pages/utf-8_page.html
|
150
|
+
- test/test_pages/windows-1250_page.html
|
151
|
+
- test/test_scrapper.rb
|
152
|
+
has_rdoc: true
|
153
|
+
homepage: http://github.com/fifigyuri/newscrapi
|
154
|
+
licenses: []
|
155
|
+
|
156
|
+
post_install_message:
|
157
|
+
rdoc_options:
|
158
|
+
- --charset=UTF-8
|
159
|
+
require_paths:
|
160
|
+
- lib
|
161
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
162
|
+
none: false
|
163
|
+
requirements:
|
164
|
+
- - ">="
|
165
|
+
- !ruby/object:Gem::Version
|
166
|
+
hash: 3
|
167
|
+
segments:
|
168
|
+
- 0
|
169
|
+
version: "0"
|
170
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
171
|
+
none: false
|
172
|
+
requirements:
|
173
|
+
- - ">="
|
174
|
+
- !ruby/object:Gem::Version
|
175
|
+
hash: 3
|
176
|
+
segments:
|
177
|
+
- 0
|
178
|
+
version: "0"
|
179
|
+
requirements: []
|
180
|
+
|
181
|
+
rubyforge_project:
|
182
|
+
rubygems_version: 1.3.7
|
183
|
+
signing_key:
|
184
|
+
specification_version: 3
|
185
|
+
summary: Gem for those who want to screen scrap only the content part of web pages, blogs or articles.
|
186
|
+
test_files:
|
187
|
+
- test/helper.rb
|
188
|
+
- test/test_encoding.rb
|
189
|
+
- test/test_mapping.rb
|
190
|
+
- test/test_pages.rb
|
191
|
+
- test/test_scrapper.rb
|