mechanize-content 0.1.0 → 0.1.1
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/README.rdoc +26 -1
- data/Rakefile +1 -0
- data/VERSION +1 -1
- data/mechanize-content.gemspec +58 -0
- metadata +17 -2
data/README.rdoc
CHANGED
@@ -1,6 +1,31 @@
|
|
1
1
|
= mechanize-content
|
2
2
|
|
3
|
-
|
3
|
+
Returns the most important pieces of content on a web page. Finds the best block of text, image and title by analysing the page content.
|
4
|
+
|
5
|
+
=== Usage
|
6
|
+
|
7
|
+
Pass in a URL on initialisation and then call the helpers to pull the best content out.
|
8
|
+
|
9
|
+
<tt>mc = MechanizeContent.new("http://www.joystiq.com/2010/03/19/mag-gets-free-trooper-gear-pack-dlc-next-week/")</tt>
|
10
|
+
|
11
|
+
<tt>mc.best_title</tt>
|
12
|
+
|
13
|
+
<tt>"MAG gets free 'Trooper Gear Pack' DLC next week -- Joystiq"</tt>
|
14
|
+
|
15
|
+
<tt>mc.best_text</tt>
|
16
|
+
|
17
|
+
<tt>"Ten-hut, soldiers! HQ has just sent word that some new gear will be shipping to the front lines of MAG next week, free of charge: the Trooper Gear Pack. In this parcel, we'll finally get access to the Flashbang grenade..."</tt>
|
18
|
+
|
19
|
+
<tt>mc.best_image</tt>
|
20
|
+
|
21
|
+
<tt>"http://www.blogcdn.com/www.joystiq.com/media/2010/03/580mage302.jpg"</tt>
|
22
|
+
|
23
|
+
The gem also supports multiple URLs and will find the best content between them. The order in which they are inserted determines priority.
|
24
|
+
|
25
|
+
=== Dependancies
|
26
|
+
|
27
|
+
* Mechanize
|
28
|
+
* imagesize
|
4
29
|
|
5
30
|
== Note on Patches/Pull Requests
|
6
31
|
|
data/Rakefile
CHANGED
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
0.1.
|
1
|
+
0.1.1
|
@@ -0,0 +1,58 @@
|
|
1
|
+
# Generated by jeweler
|
2
|
+
# DO NOT EDIT THIS FILE DIRECTLY
|
3
|
+
# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
|
4
|
+
# -*- encoding: utf-8 -*-
|
5
|
+
|
6
|
+
Gem::Specification.new do |s|
|
7
|
+
s.name = %q{mechanize-content}
|
8
|
+
s.version = "0.1.1"
|
9
|
+
|
10
|
+
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
|
+
s.authors = ["John Griffin"]
|
12
|
+
s.date = %q{2010-03-19}
|
13
|
+
s.description = %q{pass in a url or urls and mechanize-content will select the best block of text, image and title by analysing the page content}
|
14
|
+
s.email = %q{johnog@gmail.com}
|
15
|
+
s.extra_rdoc_files = [
|
16
|
+
"LICENSE",
|
17
|
+
"README.rdoc"
|
18
|
+
]
|
19
|
+
s.files = [
|
20
|
+
".document",
|
21
|
+
".gitignore",
|
22
|
+
"LICENSE",
|
23
|
+
"README.rdoc",
|
24
|
+
"Rakefile",
|
25
|
+
"VERSION",
|
26
|
+
"lib/mechanize-content.rb",
|
27
|
+
"mechanize-content.gemspec",
|
28
|
+
"spec/mechanize-content_spec.rb",
|
29
|
+
"spec/spec.opts",
|
30
|
+
"spec/spec_helper.rb"
|
31
|
+
]
|
32
|
+
s.homepage = %q{http://github.com/john-griffin/mechanize-content}
|
33
|
+
s.rdoc_options = ["--charset=UTF-8"]
|
34
|
+
s.require_paths = ["lib"]
|
35
|
+
s.rubygems_version = %q{1.3.6}
|
36
|
+
s.summary = %q{scrape the best content from a page}
|
37
|
+
s.test_files = [
|
38
|
+
"spec/mechanize-content_spec.rb",
|
39
|
+
"spec/spec_helper.rb"
|
40
|
+
]
|
41
|
+
|
42
|
+
if s.respond_to? :specification_version then
|
43
|
+
current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
|
44
|
+
s.specification_version = 3
|
45
|
+
|
46
|
+
if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
|
47
|
+
s.add_runtime_dependency(%q<mechanize>, [">= 1.0.0"])
|
48
|
+
s.add_runtime_dependency(%q<imagesize>, [">= 0.1.1"])
|
49
|
+
else
|
50
|
+
s.add_dependency(%q<mechanize>, [">= 1.0.0"])
|
51
|
+
s.add_dependency(%q<imagesize>, [">= 0.1.1"])
|
52
|
+
end
|
53
|
+
else
|
54
|
+
s.add_dependency(%q<mechanize>, [">= 1.0.0"])
|
55
|
+
s.add_dependency(%q<imagesize>, [">= 0.1.1"])
|
56
|
+
end
|
57
|
+
end
|
58
|
+
|
metadata
CHANGED
@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
|
|
5
5
|
segments:
|
6
6
|
- 0
|
7
7
|
- 1
|
8
|
-
-
|
9
|
-
version: 0.1.
|
8
|
+
- 1
|
9
|
+
version: 0.1.1
|
10
10
|
platform: ruby
|
11
11
|
authors:
|
12
12
|
- John Griffin
|
@@ -31,6 +31,20 @@ dependencies:
|
|
31
31
|
version: 1.0.0
|
32
32
|
type: :runtime
|
33
33
|
version_requirements: *id001
|
34
|
+
- !ruby/object:Gem::Dependency
|
35
|
+
name: imagesize
|
36
|
+
prerelease: false
|
37
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
38
|
+
requirements:
|
39
|
+
- - ">="
|
40
|
+
- !ruby/object:Gem::Version
|
41
|
+
segments:
|
42
|
+
- 0
|
43
|
+
- 1
|
44
|
+
- 1
|
45
|
+
version: 0.1.1
|
46
|
+
type: :runtime
|
47
|
+
version_requirements: *id002
|
34
48
|
description: pass in a url or urls and mechanize-content will select the best block of text, image and title by analysing the page content
|
35
49
|
email: johnog@gmail.com
|
36
50
|
executables: []
|
@@ -48,6 +62,7 @@ files:
|
|
48
62
|
- Rakefile
|
49
63
|
- VERSION
|
50
64
|
- lib/mechanize-content.rb
|
65
|
+
- mechanize-content.gemspec
|
51
66
|
- spec/mechanize-content_spec.rb
|
52
67
|
- spec/spec.opts
|
53
68
|
- spec/spec_helper.rb
|