distillery 0.2.9 → 0.2.10
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.
- data/.gitignore +1 -0
- data/lib/distillery/document.rb +1 -1
- data/lib/distillery/version.rb +1 -1
- data/spec/acceptance_spec.rb +23 -2
- data/spec/fixtures/maple_cookies.html +1878 -0
- data/spec/lib/distillery/document_spec.rb +6 -0
- metadata +20 -18
|
@@ -261,6 +261,12 @@ module Distillery
|
|
|
261
261
|
::Nokogiri::HTML.fragment(doc.dup.distill!(:images => true)).css('img').should_not be_empty
|
|
262
262
|
end
|
|
263
263
|
|
|
264
|
+
it 'finds images when multiple images are wrapped by an unrelated element that would be cleaned' do
|
|
265
|
+
doc = Document.new(File.open('./spec/fixtures/maple_cookies.html').read)
|
|
266
|
+
::Nokogiri::HTML.fragment(doc.dup.distill!).css('img').should be_empty
|
|
267
|
+
::Nokogiri::HTML.fragment(doc.dup.distill!(:images => true)).css('img').length.should be > 3
|
|
268
|
+
end
|
|
269
|
+
|
|
264
270
|
it 'works with a HTML document that has no winner' do
|
|
265
271
|
document_of('foo').distill!.should == 'foo'
|
|
266
272
|
end
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: distillery
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.2.
|
|
4
|
+
version: 0.2.10
|
|
5
5
|
prerelease:
|
|
6
6
|
platform: ruby
|
|
7
7
|
authors:
|
|
@@ -9,11 +9,11 @@ authors:
|
|
|
9
9
|
autorequire:
|
|
10
10
|
bindir: bin
|
|
11
11
|
cert_chain: []
|
|
12
|
-
date: 2011-
|
|
12
|
+
date: 2011-12-07 00:00:00.000000000Z
|
|
13
13
|
dependencies:
|
|
14
14
|
- !ruby/object:Gem::Dependency
|
|
15
15
|
name: nokogiri
|
|
16
|
-
requirement: &
|
|
16
|
+
requirement: &2161473880 !ruby/object:Gem::Requirement
|
|
17
17
|
none: false
|
|
18
18
|
requirements:
|
|
19
19
|
- - ! '>'
|
|
@@ -21,10 +21,10 @@ dependencies:
|
|
|
21
21
|
version: '1.0'
|
|
22
22
|
type: :runtime
|
|
23
23
|
prerelease: false
|
|
24
|
-
version_requirements: *
|
|
24
|
+
version_requirements: *2161473880
|
|
25
25
|
- !ruby/object:Gem::Dependency
|
|
26
26
|
name: slop
|
|
27
|
-
requirement: &
|
|
27
|
+
requirement: &2161473380 !ruby/object:Gem::Requirement
|
|
28
28
|
none: false
|
|
29
29
|
requirements:
|
|
30
30
|
- - ! '>'
|
|
@@ -32,10 +32,10 @@ dependencies:
|
|
|
32
32
|
version: '1.0'
|
|
33
33
|
type: :runtime
|
|
34
34
|
prerelease: false
|
|
35
|
-
version_requirements: *
|
|
35
|
+
version_requirements: *2161473380
|
|
36
36
|
- !ruby/object:Gem::Dependency
|
|
37
37
|
name: rspec
|
|
38
|
-
requirement: &
|
|
38
|
+
requirement: &2161472920 !ruby/object:Gem::Requirement
|
|
39
39
|
none: false
|
|
40
40
|
requirements:
|
|
41
41
|
- - ! '>'
|
|
@@ -43,10 +43,10 @@ dependencies:
|
|
|
43
43
|
version: '2.0'
|
|
44
44
|
type: :development
|
|
45
45
|
prerelease: false
|
|
46
|
-
version_requirements: *
|
|
46
|
+
version_requirements: *2161472920
|
|
47
47
|
- !ruby/object:Gem::Dependency
|
|
48
48
|
name: guard
|
|
49
|
-
requirement: &
|
|
49
|
+
requirement: &2161472540 !ruby/object:Gem::Requirement
|
|
50
50
|
none: false
|
|
51
51
|
requirements:
|
|
52
52
|
- - ! '>='
|
|
@@ -54,10 +54,10 @@ dependencies:
|
|
|
54
54
|
version: '0'
|
|
55
55
|
type: :development
|
|
56
56
|
prerelease: false
|
|
57
|
-
version_requirements: *
|
|
57
|
+
version_requirements: *2161472540
|
|
58
58
|
- !ruby/object:Gem::Dependency
|
|
59
59
|
name: guard-rspec
|
|
60
|
-
requirement: &
|
|
60
|
+
requirement: &2161472080 !ruby/object:Gem::Requirement
|
|
61
61
|
none: false
|
|
62
62
|
requirements:
|
|
63
63
|
- - ! '>='
|
|
@@ -65,10 +65,10 @@ dependencies:
|
|
|
65
65
|
version: '0'
|
|
66
66
|
type: :development
|
|
67
67
|
prerelease: false
|
|
68
|
-
version_requirements: *
|
|
68
|
+
version_requirements: *2161472080
|
|
69
69
|
- !ruby/object:Gem::Dependency
|
|
70
70
|
name: ruby-debug19
|
|
71
|
-
requirement: &
|
|
71
|
+
requirement: &2161471660 !ruby/object:Gem::Requirement
|
|
72
72
|
none: false
|
|
73
73
|
requirements:
|
|
74
74
|
- - ! '>='
|
|
@@ -76,10 +76,10 @@ dependencies:
|
|
|
76
76
|
version: '0'
|
|
77
77
|
type: :development
|
|
78
78
|
prerelease: false
|
|
79
|
-
version_requirements: *
|
|
79
|
+
version_requirements: *2161471660
|
|
80
80
|
- !ruby/object:Gem::Dependency
|
|
81
81
|
name: rb-fsevent
|
|
82
|
-
requirement: &
|
|
82
|
+
requirement: &2161471240 !ruby/object:Gem::Requirement
|
|
83
83
|
none: false
|
|
84
84
|
requirements:
|
|
85
85
|
- - ! '>='
|
|
@@ -87,10 +87,10 @@ dependencies:
|
|
|
87
87
|
version: '0'
|
|
88
88
|
type: :development
|
|
89
89
|
prerelease: false
|
|
90
|
-
version_requirements: *
|
|
90
|
+
version_requirements: *2161471240
|
|
91
91
|
- !ruby/object:Gem::Dependency
|
|
92
92
|
name: growl
|
|
93
|
-
requirement: &
|
|
93
|
+
requirement: &2161470820 !ruby/object:Gem::Requirement
|
|
94
94
|
none: false
|
|
95
95
|
requirements:
|
|
96
96
|
- - ! '>='
|
|
@@ -98,7 +98,7 @@ dependencies:
|
|
|
98
98
|
version: '0'
|
|
99
99
|
type: :development
|
|
100
100
|
prerelease: false
|
|
101
|
-
version_requirements: *
|
|
101
|
+
version_requirements: *2161470820
|
|
102
102
|
description: Distillery extracts the "content" portion out of an HTML document. It
|
|
103
103
|
applies heuristics based on element type, location, class/id name and other attributes
|
|
104
104
|
to try and find the content part of the HTML document and return it.
|
|
@@ -135,6 +135,7 @@ files:
|
|
|
135
135
|
- spec/fixtures/game_blog.html
|
|
136
136
|
- spec/fixtures/ginger_cookies.html
|
|
137
137
|
- spec/fixtures/js_this_keyword.html
|
|
138
|
+
- spec/fixtures/maple_cookies.html
|
|
138
139
|
- spec/fixtures/nyt_social_media.html
|
|
139
140
|
- spec/fixtures/pina_collada_cupcakes.html
|
|
140
141
|
- spec/fixtures/pumpkin_scones.html
|
|
@@ -183,6 +184,7 @@ test_files:
|
|
|
183
184
|
- spec/fixtures/game_blog.html
|
|
184
185
|
- spec/fixtures/ginger_cookies.html
|
|
185
186
|
- spec/fixtures/js_this_keyword.html
|
|
187
|
+
- spec/fixtures/maple_cookies.html
|
|
186
188
|
- spec/fixtures/nyt_social_media.html
|
|
187
189
|
- spec/fixtures/pina_collada_cupcakes.html
|
|
188
190
|
- spec/fixtures/pumpkin_scones.html
|