truffle-hog 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/README.textile +66 -0
- data/lib/truffle-hog.rb +27 -0
- data/spec/spec.opts +2 -0
- data/spec/spec_helper.rb +10 -0
- data/spec/truffle-hog_spec.rb +44 -0
- metadata +59 -0
data/README.textile
ADDED
@@ -0,0 +1,66 @@
|
|
1
|
+
h1. TruffleHog
|
2
|
+
|
3
|
+
"http://github.com/pauldix/truffle-hog":http://github.com/pauldix/truffle-hog
|
4
|
+
|
5
|
+
If you have issues please use the "Feedzirra group":http://groups.google.com/group/feedzirra
|
6
|
+
|
7
|
+
h2. Summary
|
8
|
+
|
9
|
+
Finds RSS and Atom feed urls in html like a hog finds truffles. Tasty, delicious feeds... er, truffles.
|
10
|
+
|
11
|
+
h2. Description
|
12
|
+
|
13
|
+
This is a simple library. It doesn't GET the html for you. It doesn't use an HTML or XML parser. It just uses a little regex to find feed urls. If you want to GET the web pages, use "Typhoeus":http://github.com/pauldix/typhoeus/. If you want to fetch and parse the feeds use "Feedzirra":http://github.com/pauldix/feedzirra.
|
14
|
+
|
15
|
+
h2. Installation
|
16
|
+
|
17
|
+
<pre>
|
18
|
+
gem install truffle-hog --source http://gemcutter.org
|
19
|
+
</pre>
|
20
|
+
|
21
|
+
h2. Use
|
22
|
+
|
23
|
+
<pre>
|
24
|
+
require 'rubygems'
|
25
|
+
require 'truffle-hog'
|
26
|
+
|
27
|
+
# get atom and rss
|
28
|
+
feed_urls = TruffleHog.parse_feed_urls(some_html)
|
29
|
+
|
30
|
+
# get atom if available, otherwise rss
|
31
|
+
feed_urls = TruffleHog.parse_feed_urls(some_html, :atom)
|
32
|
+
|
33
|
+
# get rss if available, otherwise atom
|
34
|
+
feed_urls = TruffleHog.parse_feed_urls(some_html, :rss)
|
35
|
+
</pre>
|
36
|
+
|
37
|
+
h2. Next
|
38
|
+
|
39
|
+
I may want to make a fun Nokogiri backed version and test speed and stuff. This thing hasn't been benchmarked yet.
|
40
|
+
|
41
|
+
h2. LICENSE
|
42
|
+
|
43
|
+
(The MIT License)
|
44
|
+
|
45
|
+
Copyright (c) 2009:
|
46
|
+
|
47
|
+
"Paul Dix":http://pauldix.net
|
48
|
+
|
49
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
50
|
+
a copy of this software and associated documentation files (the
|
51
|
+
'Software'), to deal in the Software without restriction, including
|
52
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
53
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
54
|
+
permit persons to whom the Software is furnished to do so, subject to
|
55
|
+
the following conditions:
|
56
|
+
|
57
|
+
The above copyright notice and this permission notice shall be
|
58
|
+
included in all copies or substantial portions of the Software.
|
59
|
+
|
60
|
+
THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
|
61
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
62
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
63
|
+
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
|
64
|
+
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
|
65
|
+
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
66
|
+
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/lib/truffle-hog.rb
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
module TruffleHog
|
2
|
+
VERSION = "0.0.1"
|
3
|
+
|
4
|
+
def self.parse_feed_urls(html, favor = :all)
|
5
|
+
rss_links = []
|
6
|
+
atom_links = []
|
7
|
+
|
8
|
+
rss_links = (scan_for_tag(html, "a", "rss") + scan_for_tag(html, "link", "rss")).flatten.uniq
|
9
|
+
atom_links = (scan_for_tag(html, "a", "atom") + scan_for_tag(html, "link", "atom")).flatten.uniq
|
10
|
+
|
11
|
+
case favor
|
12
|
+
when :all
|
13
|
+
(rss_links + atom_links).uniq
|
14
|
+
when :rss
|
15
|
+
rss_links.empty? ? atom_links : rss_links
|
16
|
+
when :atom
|
17
|
+
atom_links.empty? ? rss_links : atom_links
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
def self.scan_for_tag(html, tag, type)
|
22
|
+
href_first = html.scan(/<#{tag}.*href\=['"](.*?)['"].*type\=['"]application\/#{type}\+xml['"].*?>/)
|
23
|
+
return href_first unless href_first.empty?
|
24
|
+
|
25
|
+
html.scan(/<#{tag}.*type\=['"]application\/#{type}\+xml['"].*href=['"](.*?)['"].*?>/)
|
26
|
+
end
|
27
|
+
end
|
data/spec/spec.opts
ADDED
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,10 @@
|
|
1
|
+
require "rubygems"
|
2
|
+
require "spec"
|
3
|
+
|
4
|
+
# gem install redgreen for colored test output
|
5
|
+
begin require "redgreen" unless ENV['TM_CURRENT_LINE']; rescue LoadError; end
|
6
|
+
|
7
|
+
path = File.expand_path(File.dirname(__FILE__) + "/../lib/")
|
8
|
+
$LOAD_PATH.unshift(path) unless $LOAD_PATH.include?(path)
|
9
|
+
|
10
|
+
require "lib/truffle-hog"
|
@@ -0,0 +1,44 @@
|
|
1
|
+
require File.dirname(__FILE__) + '/spec_helper'
|
2
|
+
|
3
|
+
describe "parsing html" do
|
4
|
+
before(:all) do
|
5
|
+
@html = File.read(File.dirname(__FILE__) + "/pauldix_net.html")
|
6
|
+
end
|
7
|
+
|
8
|
+
it "parses all feed urls" do
|
9
|
+
TruffleHog.parse_feed_urls(@html).should == ["http://feeds.feedburner.com/PaulDixExplainsNothing/in_body/rss",
|
10
|
+
"http://www.pauldix.net/in_head/index.rdf", "http://www.pauldix.net/in_head/rss.xml",
|
11
|
+
"http://feeds.feedburner.com/PaulDixExplainsNothing/in_body/atom",
|
12
|
+
"http://www.pauldix.net/in_head/atom.xml"]
|
13
|
+
end
|
14
|
+
|
15
|
+
it "parses rss feeds from the link tags in head" do
|
16
|
+
feed_urls = TruffleHog.parse_feed_urls(@html, :rss)
|
17
|
+
feed_urls.should include("http://www.pauldix.net/in_head/index.rdf")
|
18
|
+
feed_urls.should include("http://www.pauldix.net/in_head/rss.xml")
|
19
|
+
feed_urls.should_not include("http://www.pauldix.net/in_head/atom.xml")
|
20
|
+
feed_urls.should_not include("http://feeds.feedburner.com/PaulDixExplainsNothing/in_body/atom")
|
21
|
+
end
|
22
|
+
|
23
|
+
it "parses atom feeds from the link tags in head" do
|
24
|
+
feed_urls = TruffleHog.parse_feed_urls(@html, :atom)
|
25
|
+
feed_urls.should include("http://www.pauldix.net/in_head/atom.xml")
|
26
|
+
feed_urls.should_not include("http://www.pauldix.net/in_head/index.rdf")
|
27
|
+
feed_urls.should_not include("http://www.pauldix.net/in_head/rss.xml")
|
28
|
+
end
|
29
|
+
|
30
|
+
it "parses rss feeds from the body" do
|
31
|
+
feed_urls = TruffleHog.parse_feed_urls(@html, :rss)
|
32
|
+
feed_urls.should include("http://feeds.feedburner.com/PaulDixExplainsNothing/in_body/rss")
|
33
|
+
feed_urls.should_not include("http://feeds.feedburner.com/PaulDixExplainsNothing/in_body/atom")
|
34
|
+
end
|
35
|
+
|
36
|
+
it "parses atom feeds from the body" do
|
37
|
+
feed_urls = TruffleHog.parse_feed_urls(@html, :atom)
|
38
|
+
feed_urls.should include("http://feeds.feedburner.com/PaulDixExplainsNothing/in_body/atom")
|
39
|
+
feed_urls.should_not include("http://feeds.feedburner.com/PaulDixExplainsNothing/in_body/rss")
|
40
|
+
end
|
41
|
+
|
42
|
+
it "returns atom feeds if rss is favored, but none are found"
|
43
|
+
it "returns rss feeds if atom is favored, but none are found"
|
44
|
+
end
|
metadata
ADDED
@@ -0,0 +1,59 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: truffle-hog
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Paul Dix
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2009-09-21 00:00:00 -04:00
|
13
|
+
default_executable:
|
14
|
+
dependencies: []
|
15
|
+
|
16
|
+
description:
|
17
|
+
email: paul@pauldix.net
|
18
|
+
executables: []
|
19
|
+
|
20
|
+
extensions: []
|
21
|
+
|
22
|
+
extra_rdoc_files: []
|
23
|
+
|
24
|
+
files:
|
25
|
+
- lib/truffle-hog.rb
|
26
|
+
- README.textile
|
27
|
+
- spec/spec.opts
|
28
|
+
- spec/spec_helper.rb
|
29
|
+
- spec/truffle-hog_spec.rb
|
30
|
+
has_rdoc: true
|
31
|
+
homepage: http://github.com/pauldix/truffle-hog
|
32
|
+
licenses: []
|
33
|
+
|
34
|
+
post_install_message:
|
35
|
+
rdoc_options: []
|
36
|
+
|
37
|
+
require_paths:
|
38
|
+
- lib
|
39
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
40
|
+
requirements:
|
41
|
+
- - ">="
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
version: "0"
|
44
|
+
version:
|
45
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
46
|
+
requirements:
|
47
|
+
- - ">="
|
48
|
+
- !ruby/object:Gem::Version
|
49
|
+
version: "0"
|
50
|
+
version:
|
51
|
+
requirements: []
|
52
|
+
|
53
|
+
rubyforge_project:
|
54
|
+
rubygems_version: 1.3.5
|
55
|
+
signing_key:
|
56
|
+
specification_version: 2
|
57
|
+
summary: Finds RSS and Atom feed urls in html like a hog finds truffles. Tasty, delicious feeds... er, truffles.
|
58
|
+
test_files: []
|
59
|
+
|