html_massage 0.2.0 → 0.2.1
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/Gemfile +0 -2
- data/README.md +44 -43
- data/html_massage.gemspec +2 -1
- data/lib/html_massage/version.rb +1 -1
- data/lib/html_massage.rb +4 -4
- data/spec/html_massage_spec.rb +9 -0
- metadata +19 -3
data/Gemfile
CHANGED
data/README.md
CHANGED
|
@@ -19,62 +19,63 @@ Give your HTML a massage, in just the ways it loves:
|
|
|
19
19
|
</head>
|
|
20
20
|
<body>
|
|
21
21
|
<div id="header">My Site</div>
|
|
22
|
-
<div>This is some great content!</div>
|
|
23
|
-
<a href ="foo/bar.html">Click this link</a>
|
|
22
|
+
<div>This is some <i>great</i> content!</div>
|
|
24
23
|
</body>
|
|
25
24
|
</html>
|
|
26
25
|
}
|
|
27
26
|
|
|
28
|
-
|
|
29
|
-
# => "<div>This is some great content!</div>"
|
|
27
|
+
HtmlMassage.html( html )
|
|
28
|
+
# => "<div>This is some <i>great</i> content!</div>"
|
|
30
29
|
|
|
31
|
-
|
|
32
|
-
# => "This is some
|
|
30
|
+
HtmlMassage.markdown( html )
|
|
31
|
+
# => "This is some _great_ content!"
|
|
33
32
|
|
|
34
|
-
|
|
33
|
+
HtmlMassage.text( html )
|
|
34
|
+
# => "This is some great content!"
|
|
35
35
|
|
|
36
|
-
|
|
37
|
-
:exclude => [ '#header' ] )
|
|
38
|
-
# => #<HtmlMassager::HtmlMassage ... >
|
|
36
|
+
### Custom includes and excludes
|
|
39
37
|
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
|
|
38
|
+
html = %{
|
|
39
|
+
<html>
|
|
40
|
+
<body>
|
|
41
|
+
<div class="custom_navigation">some links to other pages...</div>
|
|
42
|
+
<div>This is some <i>great</i> content!</div>
|
|
43
|
+
</body>
|
|
44
|
+
</html>
|
|
45
|
+
}
|
|
46
|
+
|
|
47
|
+
html_massage = HtmlMassage.new( html )
|
|
48
|
+
html_massage.exclude!( [ '.custom_navigation' ] )
|
|
49
|
+
html_massage.include!( [ 'body' ] )
|
|
50
|
+
html_massage.to_html
|
|
51
|
+
# => <div>This is some <i>great</i> content!</div>
|
|
43
52
|
|
|
44
53
|
### Sanitize HTML
|
|
45
54
|
|
|
46
|
-
|
|
47
|
-
|
|
48
|
-
|
|
55
|
+
html = %{
|
|
56
|
+
<html>
|
|
57
|
+
<head>
|
|
58
|
+
<script type="text/javascript">document.write('I am a bad script');</script>
|
|
59
|
+
</head>
|
|
60
|
+
<body>
|
|
61
|
+
<div>This is some <i>great</i> content!</div>
|
|
62
|
+
</body>
|
|
63
|
+
</html>
|
|
64
|
+
}
|
|
49
65
|
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
#
|
|
54
|
-
# <body>
|
|
55
|
-
# <div id="header">My Site</div>
|
|
56
|
-
# <div>This is some great content!</div>
|
|
57
|
-
# </body>
|
|
58
|
-
# </html>
|
|
66
|
+
html_massage = HtmlMassage.new( html )
|
|
67
|
+
html_massage.sanitize!( :elements => ['div'] )
|
|
68
|
+
html_massage.to_html
|
|
69
|
+
# => <div>This is some <i>great</i> content!</div>
|
|
59
70
|
|
|
60
71
|
### Make Links Absolute
|
|
61
72
|
|
|
62
|
-
|
|
63
|
-
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
# <
|
|
70
|
-
# </head>
|
|
71
|
-
# <body>
|
|
72
|
-
# <div id="header">My Site</div>
|
|
73
|
-
# <div>This is some great content!</div>
|
|
74
|
-
# <a href ="http://example.com/joe/foo/bar.html">Click this link</a>
|
|
75
|
-
# </body>
|
|
76
|
-
# </html>
|
|
77
|
-
|
|
78
|
-
puts html_massage.absolutify_images!
|
|
79
|
-
#
|
|
73
|
+
html = %{
|
|
74
|
+
<a href ="/foo/bar.html">Click this link</a>
|
|
75
|
+
}
|
|
76
|
+
|
|
77
|
+
html_massage = HtmlMassage.new( html )
|
|
78
|
+
html_massage.absolutify_links!( 'http://example.com/joe/page1.html' )
|
|
79
|
+
html_massage.to_html
|
|
80
|
+
# <a href ="http://example.com/foo/bar.html">Click this link</a>
|
|
80
81
|
|
data/html_massage.gemspec
CHANGED
|
@@ -10,7 +10,7 @@ Gem::Specification.new do |gem|
|
|
|
10
10
|
gem.email = ["code@harlantwood.net"]
|
|
11
11
|
gem.homepage = "https://github.com/harlantwood/html_massage"
|
|
12
12
|
gem.summary = %{Massages HTML how you want to.}
|
|
13
|
-
gem.description = %{Massages HTML how you want to: sanitize tags, remove headers and footers
|
|
13
|
+
gem.description = %{Massages HTML how you want to: sanitize tags, remove headers and footers; output to html, markdown, or plain text.}
|
|
14
14
|
|
|
15
15
|
gem.files = `git ls-files`.split($/)
|
|
16
16
|
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
|
@@ -21,6 +21,7 @@ Gem::Specification.new do |gem|
|
|
|
21
21
|
gem.add_dependency "sanitize", ">= 2.0"
|
|
22
22
|
gem.add_dependency "thor"
|
|
23
23
|
gem.add_dependency "rest-client", ">= 1.6"
|
|
24
|
+
gem.add_dependency "reverse_markdown", ">= 0.4"
|
|
24
25
|
|
|
25
26
|
gem.add_development_dependency "rspec", ">= 2.5"
|
|
26
27
|
|
data/lib/html_massage/version.rb
CHANGED
data/lib/html_massage.rb
CHANGED
|
@@ -185,8 +185,9 @@ module HtmlMassager
|
|
|
185
185
|
def massage!( options={} )
|
|
186
186
|
self.class.translate_old_options( options )
|
|
187
187
|
options = DEFAULTS.merge( options )
|
|
188
|
-
|
|
189
|
-
|
|
188
|
+
source_url = options.delete( :source_url )
|
|
189
|
+
absolutify_links!(source_url) if options.delete( :links ) == :absolute
|
|
190
|
+
absolutify_images!(source_url) if options.delete( :images ) == :absolute
|
|
190
191
|
include!( options.delete( :include ) )
|
|
191
192
|
exclude!( options.delete( :exclude ) )
|
|
192
193
|
sanitize!( options.delete( :sanitize ) )
|
|
@@ -204,7 +205,7 @@ module HtmlMassager
|
|
|
204
205
|
selectors_to_exclude.to_a.each do |selector_to_exclude|
|
|
205
206
|
( doc / selector_to_exclude ).remove
|
|
206
207
|
end
|
|
207
|
-
@html = doc.
|
|
208
|
+
@html = doc.inner_html
|
|
208
209
|
end
|
|
209
210
|
|
|
210
211
|
def include!( selectors_to_include )
|
|
@@ -225,7 +226,6 @@ module HtmlMassager
|
|
|
225
226
|
end
|
|
226
227
|
|
|
227
228
|
@html = Sanitize.clean( @html, sanitize_options )
|
|
228
|
-
@html
|
|
229
229
|
end
|
|
230
230
|
|
|
231
231
|
def absolutify_links!(source_url)
|
data/spec/html_massage_spec.rb
CHANGED
|
@@ -146,6 +146,15 @@ describe HtmlMassager::HtmlMassage do
|
|
|
146
146
|
end
|
|
147
147
|
|
|
148
148
|
it 'should work for relative links' do
|
|
149
|
+
pending
|
|
150
|
+
source_url = 'http://en.wikipedia.org/wiki/Singularity'
|
|
151
|
+
original_html = '<a href="Ray_Kurzweil">Ray</a>'
|
|
152
|
+
html_massager = HtmlMassage.new( original_html )
|
|
153
|
+
html_massager.absolutify_links!(source_url).should ==
|
|
154
|
+
'<a href="http://en.wikipedia.org/wiki/Ray_Kurzweil">Ray</a>'
|
|
155
|
+
end
|
|
156
|
+
|
|
157
|
+
it 'should work for relative links to a parent director' do
|
|
149
158
|
source_url = 'http://en.wikipedia.org/wiki/Singularity'
|
|
150
159
|
original_html = '<a href="../wiki/Ray_Kurzweil">Ray</a>'
|
|
151
160
|
html_massager = HtmlMassage.new( original_html )
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: html_massage
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.2.
|
|
4
|
+
version: 0.2.1
|
|
5
5
|
prerelease:
|
|
6
6
|
platform: ruby
|
|
7
7
|
authors:
|
|
@@ -75,6 +75,22 @@ dependencies:
|
|
|
75
75
|
- - ! '>='
|
|
76
76
|
- !ruby/object:Gem::Version
|
|
77
77
|
version: '1.6'
|
|
78
|
+
- !ruby/object:Gem::Dependency
|
|
79
|
+
name: reverse_markdown
|
|
80
|
+
requirement: !ruby/object:Gem::Requirement
|
|
81
|
+
none: false
|
|
82
|
+
requirements:
|
|
83
|
+
- - ! '>='
|
|
84
|
+
- !ruby/object:Gem::Version
|
|
85
|
+
version: '0.4'
|
|
86
|
+
type: :runtime
|
|
87
|
+
prerelease: false
|
|
88
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
89
|
+
none: false
|
|
90
|
+
requirements:
|
|
91
|
+
- - ! '>='
|
|
92
|
+
- !ruby/object:Gem::Version
|
|
93
|
+
version: '0.4'
|
|
78
94
|
- !ruby/object:Gem::Dependency
|
|
79
95
|
name: rspec
|
|
80
96
|
requirement: !ruby/object:Gem::Requirement
|
|
@@ -91,8 +107,8 @@ dependencies:
|
|
|
91
107
|
- - ! '>='
|
|
92
108
|
- !ruby/object:Gem::Version
|
|
93
109
|
version: '2.5'
|
|
94
|
-
description: ! 'Massages HTML how you want to: sanitize tags, remove headers and footers
|
|
95
|
-
|
|
110
|
+
description: ! 'Massages HTML how you want to: sanitize tags, remove headers and footers;
|
|
111
|
+
output to html, markdown, or plain text.'
|
|
96
112
|
email:
|
|
97
113
|
- code@harlantwood.net
|
|
98
114
|
executables:
|