html_massage 0.2.1 → 0.3.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.travis.yml +6 -0
- data/README.md +103 -59
- data/lib/html_massage/version.rb +1 -1
- metadata +21 -34
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 9a3fc809a01adfac1d58cd81df25ac7aaea1ebc7
|
4
|
+
data.tar.gz: 00662d083333766c7b79f16e70b8ce5f565bebc3
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 06ff063b79bc5f7a12058ff179d2d65c30f089d2225e8452c616393d9e27136a6f7b4924dfb4890e9d9ca4f75b1537c53b4d9d10fab1434f8e8eb828dcd5e4ee
|
7
|
+
data.tar.gz: de7cbde0140cfb12581f3bf97b3534742ce248a16d7efa92b84c2475625554efc0ef6cf894a78108b75c48d91a0397b5f1a15f2ee2490da0eafbc5d0abb6c1ac
|
data/.travis.yml
ADDED
data/README.md
CHANGED
@@ -1,81 +1,125 @@
|
|
1
|
-
# html_massage
|
1
|
+
# HTML Massage [![Build Status](https://secure.travis-ci.org/harlantwood/html_massage.png)](https://travis-ci.org/harlantwood/html_massage) [![Gem Version](https://badge.fury.io/rb/html_massage.png)](http://badge.fury.io/rb/html_massage)
|
2
2
|
|
3
|
-
|
3
|
+
## Supported Ruby versions
|
4
|
+
|
5
|
+
- 1.9.2
|
6
|
+
- 1.9.3
|
7
|
+
- 2.0.0
|
8
|
+
|
9
|
+
Note that ruby 1.8.x is _not_ supported.
|
10
|
+
|
11
|
+
## Summary
|
4
12
|
|
5
13
|
* Remove headers and footers and navigation, and strip to only the "content" part of the HTML
|
6
14
|
* Sanitize tags, removing javascript and styling
|
7
|
-
* Convert
|
15
|
+
* Convert HTML to markdown, plain text, or sanitized HTML
|
16
|
+
|
17
|
+
## Massaging from the command line
|
18
|
+
|
19
|
+
html_massage html https://en.wikipedia.org/wiki/Technological_singularity > singularity.html
|
20
|
+
html_massage text https://en.wikipedia.org/wiki/Technological_singularity > singularity.txt
|
21
|
+
html_massage markdown https://en.wikipedia.org/wiki/Technological_singularity > singularity.md
|
22
|
+
|
23
|
+
These files will look something like:
|
24
|
+
|
25
|
+
==> singularity.html <==
|
26
|
+
<h1 id="firstHeading" class="firstHeading"><span dir="auto">Technological singularity</span></h1>
|
8
27
|
|
9
|
-
|
28
|
+
<p>The <b>technological singularity</b> is the theoretical emergence of greater-than-human <a href="/wiki/Superintelligence" title="Superintelligence">superintelligence</a> through technological means.<sup id="cite_ref-1" class="reference"><a href="#cite_note-1"><span>[</span>1<span>]</span></a></sup> Since the capabilities of such intelligence would be difficult for an unaided human mind to comprehend, the occurrence of a technological singularity is seen as an intellectual <a href="/wiki/Event_horizon" title="Event horizon">event horizon</a>, beyond which events cannot be predicted or understood.</p>
|
29
|
+
...
|
30
|
+
|
31
|
+
==> singularity.md <==
|
32
|
+
# Technological singularity
|
33
|
+
|
34
|
+
The **technological singularity** is the theoretical emergence of greater-than-human [superintelligence](https://en.wikipedia.org/wiki/Superintelligence "Superintelligence") through technological means. [1] Since the capabilities of such intelligence would be difficult for an unaided human mind to comprehend, the occurrence of a technological singularity is seen as an intellectual [event horizon](https://en.wikipedia.org/wiki/Event_horizon "Event horizon") , beyond which events cannot be predicted or understood.
|
35
|
+
...
|
36
|
+
|
37
|
+
==> singularity.txt <==
|
38
|
+
Technological singularity
|
39
|
+
|
40
|
+
The technological singularity is the theoretical emergence of greater-than-human superintelligence through technological means.[1] Since the capabilities of such intelligence would be difficult for an unaided human mind to comprehend, the occurrence of a technological singularity is seen as an intellectual event horizon, beyond which events cannot be predicted or understood.
|
41
|
+
...
|
42
|
+
|
43
|
+
## Massaging from Ruby
|
10
44
|
|
11
45
|
### Full Massage
|
12
46
|
|
13
|
-
|
47
|
+
* Use default whitelist of tags and attributes to sanitize HTML
|
48
|
+
* Use default selectors (both include and exclude lists) to attempt to capture only the "content" part of the HTML page
|
49
|
+
|
50
|
+
```ruby
|
51
|
+
require 'html_massage'
|
14
52
|
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
|
23
|
-
|
24
|
-
|
25
|
-
|
53
|
+
html = %{
|
54
|
+
<html>
|
55
|
+
<head>
|
56
|
+
<script type="text/javascript">document.write('I am a bad script');</script>
|
57
|
+
</head>
|
58
|
+
<body>
|
59
|
+
<div id="header">My Site</div>
|
60
|
+
<div>This is some <i>great</i> content!</div>
|
61
|
+
</body>
|
62
|
+
</html>
|
63
|
+
}
|
26
64
|
|
27
|
-
|
28
|
-
|
65
|
+
HtmlMassage.html( html )
|
66
|
+
# => "<div>This is some <i>great</i> content!</div>"
|
29
67
|
|
30
|
-
|
31
|
-
|
68
|
+
HtmlMassage.markdown( html )
|
69
|
+
# => "This is some _great_ content!"
|
32
70
|
|
33
|
-
|
34
|
-
|
71
|
+
HtmlMassage.text( html )
|
72
|
+
# => "This is some great content!"
|
73
|
+
```
|
35
74
|
|
36
75
|
### Custom includes and excludes
|
37
76
|
|
38
|
-
|
39
|
-
|
40
|
-
|
41
|
-
|
42
|
-
|
43
|
-
|
44
|
-
|
45
|
-
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
|
50
|
-
|
51
|
-
|
77
|
+
```ruby
|
78
|
+
html = %{
|
79
|
+
<html>
|
80
|
+
<body>
|
81
|
+
<div class="custom_navigation">some links to other pages...</div>
|
82
|
+
<div>This is some <i>great</i> content!</div>
|
83
|
+
</body>
|
84
|
+
</html>
|
85
|
+
}
|
86
|
+
|
87
|
+
html_massage = HtmlMassage.new( html )
|
88
|
+
html_massage.exclude!( [ '.custom_navigation' ] )
|
89
|
+
html_massage.include!( [ 'body' ] )
|
90
|
+
html_massage.to_html
|
91
|
+
# => <div>This is some <i>great</i> content!</div>
|
92
|
+
```
|
52
93
|
|
53
94
|
### Sanitize HTML
|
54
95
|
|
55
|
-
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
96
|
+
```ruby
|
97
|
+
html = %{
|
98
|
+
<html>
|
99
|
+
<head>
|
100
|
+
<script type="text/javascript">document.write('I am a bad script');</script>
|
101
|
+
</head>
|
102
|
+
<body>
|
103
|
+
<div>This is some <i>great</i> content!</div>
|
104
|
+
</body>
|
105
|
+
</html>
|
106
|
+
}
|
107
|
+
|
108
|
+
html_massage = HtmlMassage.new( html )
|
109
|
+
html_massage.sanitize!( :elements => ['div'] )
|
110
|
+
html_massage.to_html
|
111
|
+
# => <div>This is some <i>great</i> content!</div>
|
112
|
+
```
|
70
113
|
|
71
114
|
### Make Links Absolute
|
72
115
|
|
73
|
-
|
74
|
-
|
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>
|
116
|
+
```ruby
|
117
|
+
html = %{
|
118
|
+
<a href ="/foo/bar.html">Click this link</a>
|
119
|
+
}
|
81
120
|
|
121
|
+
html_massage = HtmlMassage.new( html )
|
122
|
+
html_massage.absolutify_links!( 'http://example.com/joe/page1.html' )
|
123
|
+
html_massage.to_html
|
124
|
+
# => <a href ="http://example.com/foo/bar.html">Click this link</a>
|
125
|
+
```
|
data/lib/html_massage/version.rb
CHANGED
metadata
CHANGED
@@ -1,113 +1,100 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: html_massage
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
5
|
-
prerelease:
|
4
|
+
version: 0.3.0
|
6
5
|
platform: ruby
|
7
6
|
authors:
|
8
7
|
- Harlan T Wood
|
9
8
|
autorequire:
|
10
9
|
bindir: bin
|
11
10
|
cert_chain: []
|
12
|
-
date:
|
11
|
+
date: 2013-08-29 00:00:00.000000000 Z
|
13
12
|
dependencies:
|
14
13
|
- !ruby/object:Gem::Dependency
|
15
14
|
name: nokogiri
|
16
15
|
requirement: !ruby/object:Gem::Requirement
|
17
|
-
none: false
|
18
16
|
requirements:
|
19
|
-
- -
|
17
|
+
- - '>='
|
20
18
|
- !ruby/object:Gem::Version
|
21
19
|
version: '1.4'
|
22
20
|
type: :runtime
|
23
21
|
prerelease: false
|
24
22
|
version_requirements: !ruby/object:Gem::Requirement
|
25
|
-
none: false
|
26
23
|
requirements:
|
27
|
-
- -
|
24
|
+
- - '>='
|
28
25
|
- !ruby/object:Gem::Version
|
29
26
|
version: '1.4'
|
30
27
|
- !ruby/object:Gem::Dependency
|
31
28
|
name: sanitize
|
32
29
|
requirement: !ruby/object:Gem::Requirement
|
33
|
-
none: false
|
34
30
|
requirements:
|
35
|
-
- -
|
31
|
+
- - '>='
|
36
32
|
- !ruby/object:Gem::Version
|
37
33
|
version: '2.0'
|
38
34
|
type: :runtime
|
39
35
|
prerelease: false
|
40
36
|
version_requirements: !ruby/object:Gem::Requirement
|
41
|
-
none: false
|
42
37
|
requirements:
|
43
|
-
- -
|
38
|
+
- - '>='
|
44
39
|
- !ruby/object:Gem::Version
|
45
40
|
version: '2.0'
|
46
41
|
- !ruby/object:Gem::Dependency
|
47
42
|
name: thor
|
48
43
|
requirement: !ruby/object:Gem::Requirement
|
49
|
-
none: false
|
50
44
|
requirements:
|
51
|
-
- -
|
45
|
+
- - '>='
|
52
46
|
- !ruby/object:Gem::Version
|
53
47
|
version: '0'
|
54
48
|
type: :runtime
|
55
49
|
prerelease: false
|
56
50
|
version_requirements: !ruby/object:Gem::Requirement
|
57
|
-
none: false
|
58
51
|
requirements:
|
59
|
-
- -
|
52
|
+
- - '>='
|
60
53
|
- !ruby/object:Gem::Version
|
61
54
|
version: '0'
|
62
55
|
- !ruby/object:Gem::Dependency
|
63
56
|
name: rest-client
|
64
57
|
requirement: !ruby/object:Gem::Requirement
|
65
|
-
none: false
|
66
58
|
requirements:
|
67
|
-
- -
|
59
|
+
- - '>='
|
68
60
|
- !ruby/object:Gem::Version
|
69
61
|
version: '1.6'
|
70
62
|
type: :runtime
|
71
63
|
prerelease: false
|
72
64
|
version_requirements: !ruby/object:Gem::Requirement
|
73
|
-
none: false
|
74
65
|
requirements:
|
75
|
-
- -
|
66
|
+
- - '>='
|
76
67
|
- !ruby/object:Gem::Version
|
77
68
|
version: '1.6'
|
78
69
|
- !ruby/object:Gem::Dependency
|
79
70
|
name: reverse_markdown
|
80
71
|
requirement: !ruby/object:Gem::Requirement
|
81
|
-
none: false
|
82
72
|
requirements:
|
83
|
-
- -
|
73
|
+
- - '>='
|
84
74
|
- !ruby/object:Gem::Version
|
85
75
|
version: '0.4'
|
86
76
|
type: :runtime
|
87
77
|
prerelease: false
|
88
78
|
version_requirements: !ruby/object:Gem::Requirement
|
89
|
-
none: false
|
90
79
|
requirements:
|
91
|
-
- -
|
80
|
+
- - '>='
|
92
81
|
- !ruby/object:Gem::Version
|
93
82
|
version: '0.4'
|
94
83
|
- !ruby/object:Gem::Dependency
|
95
84
|
name: rspec
|
96
85
|
requirement: !ruby/object:Gem::Requirement
|
97
|
-
none: false
|
98
86
|
requirements:
|
99
|
-
- -
|
87
|
+
- - '>='
|
100
88
|
- !ruby/object:Gem::Version
|
101
89
|
version: '2.5'
|
102
90
|
type: :development
|
103
91
|
prerelease: false
|
104
92
|
version_requirements: !ruby/object:Gem::Requirement
|
105
|
-
none: false
|
106
93
|
requirements:
|
107
|
-
- -
|
94
|
+
- - '>='
|
108
95
|
- !ruby/object:Gem::Version
|
109
96
|
version: '2.5'
|
110
|
-
description:
|
97
|
+
description: 'Massages HTML how you want to: sanitize tags, remove headers and footers;
|
111
98
|
output to html, markdown, or plain text.'
|
112
99
|
email:
|
113
100
|
- code@harlantwood.net
|
@@ -117,6 +104,7 @@ extensions: []
|
|
117
104
|
extra_rdoc_files: []
|
118
105
|
files:
|
119
106
|
- .gitignore
|
107
|
+
- .travis.yml
|
120
108
|
- Gemfile
|
121
109
|
- License-MIT
|
122
110
|
- README.md
|
@@ -130,27 +118,26 @@ files:
|
|
130
118
|
- spec/html_massage_spec.rb
|
131
119
|
homepage: https://github.com/harlantwood/html_massage
|
132
120
|
licenses: []
|
121
|
+
metadata: {}
|
133
122
|
post_install_message:
|
134
123
|
rdoc_options: []
|
135
124
|
require_paths:
|
136
125
|
- lib
|
137
126
|
required_ruby_version: !ruby/object:Gem::Requirement
|
138
|
-
none: false
|
139
127
|
requirements:
|
140
|
-
- -
|
128
|
+
- - '>='
|
141
129
|
- !ruby/object:Gem::Version
|
142
130
|
version: '0'
|
143
131
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
144
|
-
none: false
|
145
132
|
requirements:
|
146
|
-
- -
|
133
|
+
- - '>='
|
147
134
|
- !ruby/object:Gem::Version
|
148
135
|
version: '0'
|
149
136
|
requirements: []
|
150
137
|
rubyforge_project:
|
151
|
-
rubygems_version:
|
138
|
+
rubygems_version: 2.0.7
|
152
139
|
signing_key:
|
153
|
-
specification_version:
|
140
|
+
specification_version: 4
|
154
141
|
summary: Massages HTML how you want to.
|
155
142
|
test_files:
|
156
143
|
- spec/html_massage_spec.rb
|