feedzirra 0.0.18.1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (32) hide show
  1. data/README.textile +196 -0
  2. data/Rakefile +56 -0
  3. data/lib/core_ext/date.rb +21 -0
  4. data/lib/core_ext/string.rb +9 -0
  5. data/lib/feedzirra.rb +34 -0
  6. data/lib/feedzirra/feed.rb +324 -0
  7. data/lib/feedzirra/feed_entry_utilities.rb +45 -0
  8. data/lib/feedzirra/feed_utilities.rb +71 -0
  9. data/lib/feedzirra/parser/atom.rb +47 -0
  10. data/lib/feedzirra/parser/atom_entry.rb +51 -0
  11. data/lib/feedzirra/parser/atom_feed_burner.rb +27 -0
  12. data/lib/feedzirra/parser/atom_feed_burner_entry.rb +35 -0
  13. data/lib/feedzirra/parser/itunes_rss.rb +50 -0
  14. data/lib/feedzirra/parser/itunes_rss_item.rb +31 -0
  15. data/lib/feedzirra/parser/itunes_rss_owner.rb +12 -0
  16. data/lib/feedzirra/parser/rss.rb +40 -0
  17. data/lib/feedzirra/parser/rss_entry.rb +55 -0
  18. data/spec/feedzirra/feed_entry_utilities_spec.rb +52 -0
  19. data/spec/feedzirra/feed_spec.rb +546 -0
  20. data/spec/feedzirra/feed_utilities_spec.rb +149 -0
  21. data/spec/feedzirra/parser/atom_entry_spec.rb +49 -0
  22. data/spec/feedzirra/parser/atom_feed_burner_entry_spec.rb +42 -0
  23. data/spec/feedzirra/parser/atom_feed_burner_spec.rb +39 -0
  24. data/spec/feedzirra/parser/atom_spec.rb +63 -0
  25. data/spec/feedzirra/parser/itunes_rss_item_spec.rb +48 -0
  26. data/spec/feedzirra/parser/itunes_rss_owner_spec.rb +18 -0
  27. data/spec/feedzirra/parser/itunes_rss_spec.rb +50 -0
  28. data/spec/feedzirra/parser/rss_entry_spec.rb +91 -0
  29. data/spec/feedzirra/parser/rss_spec.rb +88 -0
  30. data/spec/spec.opts +2 -0
  31. data/spec/spec_helper.rb +66 -0
  32. metadata +144 -0
data/spec/feedzirra/parser/rss_entry_spec.rb ADDED
@@ -0,0 +1,91 @@
1
+ require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
2
+
3
+ describe Feedzirra::Parser::RSSEntry do
4
+ describe "parsing of simple rss feed item" do
5
+ before(:each) do
6
+ # I don't really like doing it this way because these unit test should only rely on RSSEntry,
7
+ # but this is actually how it should work. You would never just pass entry xml straight to the AtomEnry
8
+ @entry = Feedzirra::Parser::RSS.parse(sample_rss_feed).entries.first
9
+ end
10
+
11
+ it "should parse the title" do
12
+ @entry.title.should == "Nokogiri’s Slop Feature"
13
+ end
14
+
15
+ it "should parse the url" do
16
+ @entry.url.should == "http://tenderlovemaking.com/2008/12/04/nokogiris-slop-feature/"
17
+ end
18
+
19
+ it "should parse the author" do
20
+ @entry.author.should == "Aaron Patterson"
21
+ end
22
+
23
+ it "should parse the content" do
24
+ @entry.content.should == sample_rss_entry_content
25
+ end
26
+
27
+ it "should provide a summary" do
28
+ @entry.summary.should == "Oops! When I released nokogiri version 1.0.7, I totally forgot to talk about Nokogiri::Slop() feature that was added. Why is it called \"slop\"? It lets you sloppily explore documents. Basically, it decorates your document with method_missing() that allows you to search your document via method calls.\nGiven this document:\n\ndoc = Nokogiri::Slop(<<-eohtml)\n<html>\n  <body>\n  [...]"
29
+ end
30
+
31
+ it "should parse the published date" do
32
+ @entry.published.to_s.should == "Thu Dec 04 17:17:49 UTC 2008"
33
+ end
34
+
35
+ it "should parse the categories" do
36
+ @entry.categories.should == ['computadora', 'nokogiri', 'rails']
37
+ end
38
+
39
+ it "should parse the guid as id" do
40
+ @entry.id.should == "http://tenderlovemaking.com/?p=198"
41
+ end
42
+ end
43
+
44
+ describe "parsing of media rss feed item" do
45
+ before(:each) do
46
+ # I don't really like doing it this way because these unit test should only rely on RSSEntry,
47
+ # but this is actually how it should work. You would never just pass entry xml straight to the AtomEnry
48
+ @entry = Feedzirra::Parser::RSS.parse(sample_media_rss_feed).entries.first
49
+ end
50
+
51
+ it "should parse the title" do
52
+ @entry.title.should == "the new boy on the block"
53
+ end
54
+
55
+ it "should parse the url" do
56
+ @entry.url.should == "http://horowhenua.kete.net.nz/site/images/show/15535-the-new-boy-on-the-block"
57
+ end
58
+
59
+ it "should parse link rel='related' as related" do
60
+ @entry.related.should == ["http://horowhenua.kete.net.nz/", "http://horowhenua.kete.net.nz/site/all/images"]
61
+ end
62
+
63
+ it "should provide a summary" do
64
+ @entry.summary.should == sample_media_rss_entry_content
65
+ end
66
+
67
+ it "should parse the published date" do
68
+ @entry.published.to_s.should == "Mon Mar 23 07:55:43 UTC 2009"
69
+ end
70
+
71
+ it "should parse the guid as id" do
72
+ @entry.id.should == "http://horowhenua.kete.net.nz/site/images/show/15535-the-new-boy-on-the-block"
73
+ end
74
+
75
+ it "should parse media:content url as media_content" do
76
+ @entry.media_content.should == "http://horowhenua.kete.net.nz/image_files/0000/0008/1232/DSCF1122_large.JPG"
77
+ end
78
+
79
+ it "should parse media:description as media_description" do
80
+ @entry.media_description.should == "big crane from Wellington visits the site for the week"
81
+ end
82
+
83
+ it "should parse media:thumbnail url as media_thumbnail" do
84
+ @entry.media_thumbnail.should == "http://horowhenua.kete.net.nz/image_files/0000/0008/1232/DSCF1122_medium.JPG"
85
+ end
86
+
87
+ it "should parse enclosure url as enclosure" do
88
+ @entry.enclosure.should == "http://horowhenua.kete.net.nz/image_files/0000/0008/1232/DSCF1122_large.JPG"
89
+ end
90
+ end
91
+ end
data/spec/feedzirra/parser/rss_spec.rb ADDED
@@ -0,0 +1,88 @@
1
+ require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
2
+
3
+ describe Feedzirra::Parser::RSS do
4
+ describe "#will_parse?" do
5
+ it "should return true for an RSS feed" do
6
+ Feedzirra::Parser::RSS.should be_able_to_parse(sample_rss_feed)
7
+ end
8
+
9
+ # this is no longer true. combined rdf and rss into one
10
+ # it "should return false for an rdf feed" do
11
+ # Feedzirra::RSS.should_not be_able_to_parse(sample_rdf_feed)
12
+ # end
13
+
14
+ it "should return fase for an atom feed" do
15
+ Feedzirra::Parser::RSS.should_not be_able_to_parse(sample_atom_feed)
16
+ end
17
+ end
18
+
19
+ describe "parsing of simple rss feed" do
20
+ before(:each) do
21
+ @feed = Feedzirra::Parser::RSS.parse(sample_rss_feed)
22
+ end
23
+
24
+ it "should parse the title" do
25
+ @feed.title.should == "Tender Lovemaking"
26
+ end
27
+
28
+ it "should parse the url" do
29
+ @feed.url.should == "http://tenderlovemaking.com"
30
+ end
31
+
32
+ it "should provide an accessor for the feed_url" do
33
+ @feed.respond_to?(:feed_url).should == true
34
+ @feed.respond_to?(:feed_url=).should == true
35
+ end
36
+
37
+ it "should parse entries" do
38
+ @feed.entries.size.should == 10
39
+ end
40
+ end
41
+
42
+ describe "parsing of media rss feed" do
43
+ before(:each) do
44
+ @feed = Feedzirra::Parser::RSS.parse(sample_media_rss_feed)
45
+ end
46
+
47
+ it "should parse the title" do
48
+ @feed.title.should == "horowhenua.kete.net.nz - Latest 50 Results in images"
49
+ end
50
+
51
+ it "should parse the url" do
52
+ @feed.url.should == "http://horowhenua.kete.net.nz/site/all/images/rss.xml?search_terms=wellington"
53
+ end
54
+
55
+ it "should parse link rel='related' as related" do
56
+ @feed.related.should == ["http://horowhenua.kete.net.nz/", "http://horowhenua.kete.net.nz/site/all/images"]
57
+ end
58
+
59
+ it "should parse the description" do
60
+ @feed.description.should == "Showing 1 - 50 results of 368"
61
+ end
62
+
63
+ it "should parse the language" do
64
+ @feed.language.should == "en-nz"
65
+ end
66
+
67
+ it "should provide an accessor for the feed_url" do
68
+ @feed.respond_to?(:feed_url).should == true
69
+ @feed.respond_to?(:feed_url=).should == true
70
+ end
71
+
72
+ it "should parse the prev atom:link" do
73
+ @feed.prev_page.should == "http://aws.typepad.com/aws/atom.xml?page=1"
74
+ end
75
+
76
+ it "should parse the next atom:link" do
77
+ @feed.next_page.should == "http://aws.typepad.com/aws/atom.xml?page=3"
78
+ end
79
+
80
+ it "should parse the last atom:link" do
81
+ @feed.last_page.should == "http://aws.typepad.com/aws/atom.xml?page=5"
82
+ end
83
+
84
+ it "should parse entries" do
85
+ @feed.entries.size.should == 50
86
+ end
87
+ end
88
+ end
data/spec/spec.opts ADDED
@@ -0,0 +1,2 @@
1
+ --diff
2
+ --color
data/spec/spec_helper.rb ADDED
@@ -0,0 +1,66 @@
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/feedzirra"
11
+
12
+ def load_sample(filename)
13
+ File.read("#{File.dirname(__FILE__)}/sample_feeds/#{filename}")
14
+ end
15
+
16
+ def sample_atom_feed
17
+ load_sample("AmazonWebServicesBlog.xml")
18
+ end
19
+
20
+ def sample_atom_entry_content
21
+ load_sample("AmazonWebServicesBlogFirstEntryContent.xml")
22
+ end
23
+
24
+ def sample_itunes_feed
25
+ load_sample("itunes.xml")
26
+ end
27
+
28
+ def sample_rdf_feed
29
+ load_sample("HREFConsideredHarmful.xml")
30
+ end
31
+
32
+ def sample_rdf_entry_content
33
+ load_sample("HREFConsideredHarmfulFirstEntry.xml")
34
+ end
35
+
36
+ def sample_rss_feed_burner_feed
37
+ load_sample("SamHarrisAuthorPhilosopherEssayistAtheist.xml")
38
+ end
39
+
40
+ def sample_rss_feed
41
+ load_sample("TenderLovemaking.xml")
42
+ end
43
+
44
+ def sample_rss_entry_content
45
+ load_sample("TenderLovemakingFirstEntry.xml")
46
+ end
47
+
48
+ def sample_feedburner_atom_feed
49
+ load_sample("PaulDixExplainsNothing.xml")
50
+ end
51
+
52
+ def sample_feedburner_atom_entry_content
53
+ load_sample("PaulDixExplainsNothingFirstEntryContent.xml")
54
+ end
55
+
56
+ def sample_wfw_feed
57
+ load_sample("PaulDixExplainsNothingWFW.xml")
58
+ end
59
+
60
+ def sample_media_rss_feed
61
+ load_sample("KeteHorowhenua.xml")
62
+ end
63
+
64
+ def sample_media_rss_entry_content
65
+ load_sample("KeteHorowhenuaFirstEntry.xml")
66
+ end
metadata ADDED
@@ -0,0 +1,144 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: feedzirra
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.0.18.1
5
+ platform: ruby
6
+ authors:
7
+ - Paul Dix
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+
12
+ date: 2009-08-03 00:00:00 +12:00
13
+ default_executable:
14
+ dependencies:
15
+ - !ruby/object:Gem::Dependency
16
+ name: nokogiri
17
+ type: :runtime
18
+ version_requirement:
19
+ version_requirements: !ruby/object:Gem::Requirement
20
+ requirements:
21
+ - - ">"
22
+ - !ruby/object:Gem::Version
23
+ version: 0.0.0
24
+ version:
25
+ - !ruby/object:Gem::Dependency
26
+ name: pauldix-sax-machine
27
+ type: :runtime
28
+ version_requirement:
29
+ version_requirements: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - ">="
32
+ - !ruby/object:Gem::Version
33
+ version: 0.0.12
34
+ version:
35
+ - !ruby/object:Gem::Dependency
36
+ name: taf2-curb
37
+ type: :runtime
38
+ version_requirement:
39
+ version_requirements: !ruby/object:Gem::Requirement
40
+ requirements:
41
+ - - ">="
42
+ - !ruby/object:Gem::Version
43
+ version: 0.2.3
44
+ version:
45
+ - !ruby/object:Gem::Dependency
46
+ name: builder
47
+ type: :runtime
48
+ version_requirement:
49
+ version_requirements: !ruby/object:Gem::Requirement
50
+ requirements:
51
+ - - ">="
52
+ - !ruby/object:Gem::Version
53
+ version: 2.1.2
54
+ version:
55
+ - !ruby/object:Gem::Dependency
56
+ name: activesupport
57
+ type: :runtime
58
+ version_requirement:
59
+ version_requirements: !ruby/object:Gem::Requirement
60
+ requirements:
61
+ - - ">="
62
+ - !ruby/object:Gem::Version
63
+ version: 2.0.0
64
+ version:
65
+ - !ruby/object:Gem::Dependency
66
+ name: mdalessio-dryopteris
67
+ type: :runtime
68
+ version_requirement:
69
+ version_requirements: !ruby/object:Gem::Requirement
70
+ requirements:
71
+ - - ">="
72
+ - !ruby/object:Gem::Version
73
+ version: 0.0.0
74
+ version:
75
+ description:
76
+ email: paul@pauldix.net
77
+ executables: []
78
+
79
+ extensions: []
80
+
81
+ extra_rdoc_files: []
82
+
83
+ files:
84
+ - lib/core_ext/date.rb
85
+ - lib/core_ext/string.rb
86
+ - lib/feedzirra.rb
87
+ - lib/feedzirra/feed.rb
88
+ - lib/feedzirra/parser/atom.rb
89
+ - lib/feedzirra/parser/atom_entry.rb
90
+ - lib/feedzirra/parser/atom_feed_burner.rb
91
+ - lib/feedzirra/parser/atom_feed_burner_entry.rb
92
+ - lib/feedzirra/parser/itunes_rss.rb
93
+ - lib/feedzirra/parser/itunes_rss_item.rb
94
+ - lib/feedzirra/parser/itunes_rss_owner.rb
95
+ - lib/feedzirra/parser/rss.rb
96
+ - lib/feedzirra/parser/rss_entry.rb
97
+ - lib/feedzirra/feed_utilities.rb
98
+ - lib/feedzirra/feed_entry_utilities.rb
99
+ - README.textile
100
+ - Rakefile
101
+ - spec/spec.opts
102
+ - spec/spec_helper.rb
103
+ - spec/feedzirra/feed_spec.rb
104
+ - spec/feedzirra/parser/atom_spec.rb
105
+ - spec/feedzirra/parser/atom_entry_spec.rb
106
+ - spec/feedzirra/parser/atom_feed_burner_spec.rb
107
+ - spec/feedzirra/parser/atom_feed_burner_entry_spec.rb
108
+ - spec/feedzirra/parser/itunes_rss_spec.rb
109
+ - spec/feedzirra/parser/itunes_rss_item_spec.rb
110
+ - spec/feedzirra/parser/itunes_rss_owner_spec.rb
111
+ - spec/feedzirra/parser/rss_spec.rb
112
+ - spec/feedzirra/parser/rss_entry_spec.rb
113
+ - spec/feedzirra/feed_utilities_spec.rb
114
+ - spec/feedzirra/feed_entry_utilities_spec.rb
115
+ has_rdoc: true
116
+ homepage: http://github.com/pauldix/feedzirra
117
+ licenses: []
118
+
119
+ post_install_message:
120
+ rdoc_options: []
121
+
122
+ require_paths:
123
+ - lib
124
+ required_ruby_version: !ruby/object:Gem::Requirement
125
+ requirements:
126
+ - - ">="
127
+ - !ruby/object:Gem::Version
128
+ version: "0"
129
+ version:
130
+ required_rubygems_version: !ruby/object:Gem::Requirement
131
+ requirements:
132
+ - - ">="
133
+ - !ruby/object:Gem::Version
134
+ version: "0"
135
+ version:
136
+ requirements: []
137
+
138
+ rubyforge_project:
139
+ rubygems_version: 1.3.5
140
+ signing_key:
141
+ specification_version: 2
142
+ summary: "A feed fetching and parsing library that treats the internet like Godzilla treats Japan: it dominates and eats all."
143
+ test_files: []
144
+