cdamian-feedlib 0.0.1
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/LICENSE +20 -0
- data/README.markdown +19 -0
- data/Rakefile +61 -0
- data/VERSION +1 -0
- data/lib/feedlib/errors.rb +5 -0
- data/lib/feedlib/feed/atom.rb +4 -0
- data/lib/feedlib/feed/entry/atom.rb +4 -0
- data/lib/feedlib/feed/entry/rss.rb +4 -0
- data/lib/feedlib/feed/entry.rb +11 -0
- data/lib/feedlib/feed/rss.rb +4 -0
- data/lib/feedlib/feed.rb +14 -0
- data/lib/feedlib/parser/atom.rb +24 -0
- data/lib/feedlib/parser/rss.rb +24 -0
- data/lib/feedlib/parser.rb +50 -0
- data/lib/feedlib.rb +36 -0
- data/test/feedlib_test.rb +7 -0
- data/test/test_helper.rb +9 -0
- metadata +100 -0
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2009 Damian Caruso
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.markdown
ADDED
@@ -0,0 +1,19 @@
|
|
1
|
+
## feedlib
|
2
|
+
|
3
|
+
Usage:
|
4
|
+
|
5
|
+
feedlib = Feedlib.instance
|
6
|
+
feed = feedlib.fetch("http://domain")
|
7
|
+
puts feed.title
|
8
|
+
puts feed.description
|
9
|
+
feed.entries.each do |entry|
|
10
|
+
puts entry.link
|
11
|
+
puts entry.author
|
12
|
+
puts entry.title
|
13
|
+
puts entry.content
|
14
|
+
puts entry.published_at
|
15
|
+
end
|
16
|
+
|
17
|
+
## Copyright
|
18
|
+
|
19
|
+
Copyright (c) 2009 Damian Caruso. See LICENSE for details.
|
data/Rakefile
ADDED
@@ -0,0 +1,61 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |gem|
|
7
|
+
gem.name = "feedlib"
|
8
|
+
gem.summary = %Q{Feed library for building and parsing Atom and RSS feeds}
|
9
|
+
gem.email = "damian.caruso@gmail.com"
|
10
|
+
gem.homepage = "http://github.com/cdamian/feedlib"
|
11
|
+
gem.authors = ["Damian Caruso"]
|
12
|
+
gem.description = %Q{Feed library for building and parsing Atom and RSS feeds}
|
13
|
+
gem.files = FileList['lib/**/*.rb', '[A-Z]*', 'test/**/*'].to_a
|
14
|
+
gem.add_dependency("hpricot", ">= 0.8.1")
|
15
|
+
gem.add_dependency("chardet", ">= 0.9.0")
|
16
|
+
gem.add_dependency("htmlentities", ">= 4.0.0")
|
17
|
+
# gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
|
18
|
+
end
|
19
|
+
|
20
|
+
rescue LoadError
|
21
|
+
puts "Jeweler (or a dependency) not available. Install it with: sudo gem install jeweler"
|
22
|
+
end
|
23
|
+
|
24
|
+
require 'rake/testtask'
|
25
|
+
Rake::TestTask.new(:test) do |test|
|
26
|
+
test.libs << 'lib' << 'test'
|
27
|
+
test.pattern = 'test/**/*_test.rb'
|
28
|
+
test.verbose = true
|
29
|
+
end
|
30
|
+
|
31
|
+
begin
|
32
|
+
require 'rcov/rcovtask'
|
33
|
+
Rcov::RcovTask.new do |test|
|
34
|
+
test.libs << 'test'
|
35
|
+
test.pattern = 'test/**/*_test.rb'
|
36
|
+
test.verbose = true
|
37
|
+
end
|
38
|
+
rescue LoadError
|
39
|
+
task :rcov do
|
40
|
+
abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
|
45
|
+
task :default => :test
|
46
|
+
|
47
|
+
require 'rake/rdoctask'
|
48
|
+
Rake::RDocTask.new do |rdoc|
|
49
|
+
if File.exist?('VERSION.yml')
|
50
|
+
config = YAML.load(File.read('VERSION.yml'))
|
51
|
+
version = "#{config[:major]}.#{config[:minor]}.#{config[:patch]}"
|
52
|
+
else
|
53
|
+
version = ""
|
54
|
+
end
|
55
|
+
|
56
|
+
rdoc.rdoc_dir = 'rdoc'
|
57
|
+
rdoc.title = "feedlib #{version}"
|
58
|
+
rdoc.rdoc_files.include('README*')
|
59
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
60
|
+
end
|
61
|
+
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.0.1
|
data/lib/feedlib/feed.rb
ADDED
@@ -0,0 +1,24 @@
|
|
1
|
+
require 'feedlib/parser'
|
2
|
+
require 'feedlib/feed/atom'
|
3
|
+
require 'feedlib/feed/entry/atom'
|
4
|
+
|
5
|
+
class FeedAtomParser < FeedParser
|
6
|
+
def parse_feed
|
7
|
+
@feed = FeedAtom.new
|
8
|
+
(@source_xml/:entry).each do |entry|
|
9
|
+
new_entry = parse_entry(entry)
|
10
|
+
@feed.add_entry(new_entry)
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
protected
|
15
|
+
def parse_entry(entry)
|
16
|
+
new_entry = FeedEntryAtom.new
|
17
|
+
new_entry.link = (entry/:link).attr('href')
|
18
|
+
new_entry.author = (entry/:author/:name).inner_html
|
19
|
+
new_entry.title = sanitize((entry/:title).inner_html)
|
20
|
+
new_entry.content = (entry/:content).inner_html.blank? ? sanitize((entry/:content).inner_html) : sanitize((entry/:summary).inner_html)
|
21
|
+
new_entry.published_at = (entry/:published).inner_html
|
22
|
+
new_entry
|
23
|
+
end
|
24
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
require 'feedlib/parser'
|
2
|
+
require 'feedlib/feed/rss'
|
3
|
+
require 'feedlib/feed/entry/rss'
|
4
|
+
|
5
|
+
class FeedRssParser < FeedParser
|
6
|
+
def parse_feed
|
7
|
+
@feed = FeedRss.new
|
8
|
+
(@source_xml/:channel/:item).each do |entry|
|
9
|
+
new_entry = parse_entry(entry)
|
10
|
+
@feed.add_entry(new_entry)
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
protected
|
15
|
+
def parse_entry(entry)
|
16
|
+
new_entry = FeedEntryRss.new
|
17
|
+
new_entry.link = (item/:link).inner_html
|
18
|
+
new_entry.author = (item/:author).inner_html
|
19
|
+
new_entry.title = sanitize((item/:title).inner_html)
|
20
|
+
new_entry.content = sanitize((item/:description).inner_html)
|
21
|
+
new_entry.published_at = (item/:pubDate).inner_html
|
22
|
+
new_entry
|
23
|
+
end
|
24
|
+
end
|
@@ -0,0 +1,50 @@
|
|
1
|
+
class FeedParser
|
2
|
+
attr_reader :feed
|
3
|
+
|
4
|
+
def initialize(source_xml)
|
5
|
+
@source_xml = source_xml
|
6
|
+
parse_feed
|
7
|
+
end
|
8
|
+
|
9
|
+
protected
|
10
|
+
def sanitize(html)
|
11
|
+
whitelist = %w(em i strong u)
|
12
|
+
attrs = {}
|
13
|
+
blacklist = %w(script)
|
14
|
+
|
15
|
+
whitelist += attrs.keys
|
16
|
+
|
17
|
+
html.gsub!('<', '<')
|
18
|
+
html.gsub!('>', '>')
|
19
|
+
html.gsub!('&', '&')
|
20
|
+
html.gsub!(''', "'")
|
21
|
+
html.gsub!('"', '"')
|
22
|
+
html.gsub!('<![CDATA[<![CDATA[', '')
|
23
|
+
html.gsub!('<![CDATA[', '')
|
24
|
+
html.gsub!(']]>', '')
|
25
|
+
html.gsub!(']>', '')
|
26
|
+
page = Hpricot(html)
|
27
|
+
|
28
|
+
page.search("*").each do |e|
|
29
|
+
if e.elem?
|
30
|
+
tagname = e.name.downcase
|
31
|
+
if blacklist.include?(tagname)
|
32
|
+
e.swap("")
|
33
|
+
elsif !whitelist.include?(tagname)
|
34
|
+
e.parent.replace_child(e, e.children)
|
35
|
+
elsif attrs.has_key?(tagname)
|
36
|
+
e.attributes.delete_if { |key,val| !attrs[tagname].include?(key.downcase)}
|
37
|
+
else
|
38
|
+
e.attributes = {}
|
39
|
+
end
|
40
|
+
elsif e.comment?
|
41
|
+
# HTML comments can contain executable scripts, depending on the browser, so we'll
|
42
|
+
# be paranoid and just get rid of all of them
|
43
|
+
# e.g. <!--[if lt IE 7]><script type="text/javascript">h4x0r();</script><![endif]-->
|
44
|
+
e.swap('')
|
45
|
+
end
|
46
|
+
end
|
47
|
+
coder = HTMLEntities.new
|
48
|
+
coder.decode(page.to_s)
|
49
|
+
end
|
50
|
+
end
|
data/lib/feedlib.rb
ADDED
@@ -0,0 +1,36 @@
|
|
1
|
+
require 'open-uri'
|
2
|
+
require 'hpricot'
|
3
|
+
require 'UniversalDetector'
|
4
|
+
require 'feedlib/errors'
|
5
|
+
require 'feedlib/parser/atom'
|
6
|
+
require 'feedlib/parser/rss'
|
7
|
+
|
8
|
+
class Feedlib
|
9
|
+
include Singleton
|
10
|
+
|
11
|
+
def fetch(url)
|
12
|
+
begin
|
13
|
+
f = open(url, 'r')
|
14
|
+
xml = f.read()
|
15
|
+
encoding = UniversalDetector::encoding(xml)
|
16
|
+
xml = Iconv.iconv("UTF-8", encoding, xml).join
|
17
|
+
f.close
|
18
|
+
parser = get_parser(xml)
|
19
|
+
parser.feed
|
20
|
+
rescue OpenURI::HTTPError => e
|
21
|
+
raise UnavailableFeedSourceError
|
22
|
+
end
|
23
|
+
end
|
24
|
+
|
25
|
+
private
|
26
|
+
def get_parser(xml)
|
27
|
+
doc = Hpricot.XML(xml)
|
28
|
+
if doc.search(:rss).size > 0
|
29
|
+
FeedRssParser.new(doc)
|
30
|
+
elsif doc.search(:feed).size > 0
|
31
|
+
FeedAtomParser.new(doc)
|
32
|
+
else
|
33
|
+
raise UnknownFeedTypeError
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
data/test/test_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,100 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: cdamian-feedlib
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Damian Caruso
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2009-07-11 00:00:00 -07:00
|
13
|
+
default_executable:
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: hpricot
|
17
|
+
type: :runtime
|
18
|
+
version_requirement:
|
19
|
+
version_requirements: !ruby/object:Gem::Requirement
|
20
|
+
requirements:
|
21
|
+
- - ">="
|
22
|
+
- !ruby/object:Gem::Version
|
23
|
+
version: 0.8.1
|
24
|
+
version:
|
25
|
+
- !ruby/object:Gem::Dependency
|
26
|
+
name: chardet
|
27
|
+
type: :runtime
|
28
|
+
version_requirement:
|
29
|
+
version_requirements: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 0.9.0
|
34
|
+
version:
|
35
|
+
- !ruby/object:Gem::Dependency
|
36
|
+
name: htmlentities
|
37
|
+
type: :runtime
|
38
|
+
version_requirement:
|
39
|
+
version_requirements: !ruby/object:Gem::Requirement
|
40
|
+
requirements:
|
41
|
+
- - ">="
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
version: 4.0.0
|
44
|
+
version:
|
45
|
+
description: Feed library for building and parsing Atom and RSS feeds
|
46
|
+
email: damian.caruso@gmail.com
|
47
|
+
executables: []
|
48
|
+
|
49
|
+
extensions: []
|
50
|
+
|
51
|
+
extra_rdoc_files:
|
52
|
+
- LICENSE
|
53
|
+
- README.markdown
|
54
|
+
files:
|
55
|
+
- LICENSE
|
56
|
+
- README.markdown
|
57
|
+
- Rakefile
|
58
|
+
- VERSION
|
59
|
+
- lib/feedlib.rb
|
60
|
+
- lib/feedlib/errors.rb
|
61
|
+
- lib/feedlib/feed.rb
|
62
|
+
- lib/feedlib/feed/atom.rb
|
63
|
+
- lib/feedlib/feed/entry.rb
|
64
|
+
- lib/feedlib/feed/entry/atom.rb
|
65
|
+
- lib/feedlib/feed/entry/rss.rb
|
66
|
+
- lib/feedlib/feed/rss.rb
|
67
|
+
- lib/feedlib/parser.rb
|
68
|
+
- lib/feedlib/parser/atom.rb
|
69
|
+
- lib/feedlib/parser/rss.rb
|
70
|
+
- test/feedlib_test.rb
|
71
|
+
- test/test_helper.rb
|
72
|
+
has_rdoc: false
|
73
|
+
homepage: http://github.com/cdamian/feedlib
|
74
|
+
post_install_message:
|
75
|
+
rdoc_options:
|
76
|
+
- --charset=UTF-8
|
77
|
+
require_paths:
|
78
|
+
- lib
|
79
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
80
|
+
requirements:
|
81
|
+
- - ">="
|
82
|
+
- !ruby/object:Gem::Version
|
83
|
+
version: "0"
|
84
|
+
version:
|
85
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: "0"
|
90
|
+
version:
|
91
|
+
requirements: []
|
92
|
+
|
93
|
+
rubyforge_project:
|
94
|
+
rubygems_version: 1.2.0
|
95
|
+
signing_key:
|
96
|
+
specification_version: 3
|
97
|
+
summary: Feed library for building and parsing Atom and RSS feeds
|
98
|
+
test_files:
|
99
|
+
- test/feedlib_test.rb
|
100
|
+
- test/test_helper.rb
|