rfeedreader 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/History.txt +3 -0
- data/License.txt +20 -0
- data/Manifest.txt +16 -0
- data/README.txt +5 -0
- data/Rakefile +132 -0
- data/lib/rfeedreader.rb +194 -0
- data/lib/rfeedreader/version.rb +9 -0
- data/scripts/txt2html +67 -0
- data/setup.rb +1585 -0
- data/test/test_helper.rb +8 -0
- data/test/test_rfeedreader.rb +158 -0
- data/website/index.html +100 -0
- data/website/index.txt +43 -0
- data/website/javascripts/rounded_corners_lite.inc.js +285 -0
- data/website/stylesheets/screen.css +138 -0
- data/website/template.rhtml +48 -0
- metadata +67 -0
data/History.txt
ADDED
data/License.txt
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2007 Alexandre Girard
|
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/Manifest.txt
ADDED
@@ -0,0 +1,16 @@
|
|
1
|
+
History.txt
|
2
|
+
License.txt
|
3
|
+
Manifest.txt
|
4
|
+
README.txt
|
5
|
+
Rakefile
|
6
|
+
lib/rfeedreader.rb
|
7
|
+
lib/rfeedreader/version.rb
|
8
|
+
scripts/txt2html
|
9
|
+
setup.rb
|
10
|
+
test/test_helper.rb
|
11
|
+
test/test_rfeedreader.rb
|
12
|
+
website/index.html
|
13
|
+
website/index.txt
|
14
|
+
website/javascripts/rounded_corners_lite.inc.js
|
15
|
+
website/stylesheets/screen.css
|
16
|
+
website/template.rhtml
|
data/README.txt
ADDED
data/Rakefile
ADDED
@@ -0,0 +1,132 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
require 'rake/clean'
|
4
|
+
require 'rake/testtask'
|
5
|
+
require 'rake/packagetask'
|
6
|
+
require 'rake/gempackagetask'
|
7
|
+
require 'rake/rdoctask'
|
8
|
+
require 'rake/contrib/rubyforgepublisher'
|
9
|
+
require 'fileutils'
|
10
|
+
require 'hoe'
|
11
|
+
|
12
|
+
include FileUtils
|
13
|
+
require File.join(File.dirname(__FILE__), 'lib', 'rfeedreader', 'version')
|
14
|
+
|
15
|
+
AUTHOR = 'Alexandre Girard' # can also be an array of Authors
|
16
|
+
EMAIL = "alx.girard@gmail.com"
|
17
|
+
DESCRIPTION = "Feed parser to read feed and return first posts of this feed. Special parsing from sources like Flickr, Jumcut, Google video, ..."
|
18
|
+
GEM_NAME = 'rfeedreader' # what ppl will type to install your gem
|
19
|
+
|
20
|
+
@config_file = "~/.rubyforge/user-config.yml"
|
21
|
+
@config = nil
|
22
|
+
def rubyforge_username
|
23
|
+
unless @config
|
24
|
+
begin
|
25
|
+
@config = YAML.load(File.read(File.expand_path(@config_file)))
|
26
|
+
rescue
|
27
|
+
puts <<-EOS
|
28
|
+
ERROR: No rubyforge config file found: #{@config_file}"
|
29
|
+
Run 'rubyforge setup' to prepare your env for access to Rubyforge
|
30
|
+
- See http://newgem.rubyforge.org/rubyforge.html for more details
|
31
|
+
EOS
|
32
|
+
exit
|
33
|
+
end
|
34
|
+
end
|
35
|
+
@rubyforge_username ||= @config["username"]
|
36
|
+
end
|
37
|
+
|
38
|
+
RUBYFORGE_PROJECT = 'rfeedreader' # The unix name for your project
|
39
|
+
HOMEPATH = "http://#{RUBYFORGE_PROJECT}.rubyforge.org"
|
40
|
+
DOWNLOAD_PATH = "http://rubyforge.org/projects/#{RUBYFORGE_PROJECT}"
|
41
|
+
|
42
|
+
NAME = "rfeedreader"
|
43
|
+
REV = nil
|
44
|
+
# UNCOMMENT IF REQUIRED:
|
45
|
+
# REV = `svn info`.each {|line| if line =~ /^Revision:/ then k,v = line.split(': '); break v.chomp; else next; end} rescue nil
|
46
|
+
VERS = Rfeedreader::VERSION::STRING + (REV ? ".#{REV}" : "")
|
47
|
+
CLEAN.include ['**/.*.sw?', '*.gem', '.config', '**/.DS_Store']
|
48
|
+
RDOC_OPTS = ['--quiet', '--title', 'rfeedreader documentation',
|
49
|
+
"--opname", "index.html",
|
50
|
+
"--line-numbers",
|
51
|
+
"--main", "README",
|
52
|
+
"--inline-source"]
|
53
|
+
|
54
|
+
class Hoe
|
55
|
+
def extra_deps
|
56
|
+
@extra_deps.reject { |x| Array(x).first == 'hoe' }
|
57
|
+
end
|
58
|
+
end
|
59
|
+
|
60
|
+
# Generate all the Rake tasks
|
61
|
+
# Run 'rake -T' to see list of generated tasks (from gem root directory)
|
62
|
+
hoe = Hoe.new(GEM_NAME, VERS) do |p|
|
63
|
+
p.author = AUTHOR
|
64
|
+
p.description = DESCRIPTION
|
65
|
+
p.email = EMAIL
|
66
|
+
p.summary = DESCRIPTION
|
67
|
+
p.url = HOMEPATH
|
68
|
+
p.rubyforge_name = RUBYFORGE_PROJECT if RUBYFORGE_PROJECT
|
69
|
+
p.test_globs = ["test/**/test_*.rb"]
|
70
|
+
p.clean_globs |= CLEAN #An array of file patterns to delete on clean.
|
71
|
+
|
72
|
+
# == Optional
|
73
|
+
p.changes = p.paragraphs_of("History.txt", 0..1).join("\n\n")
|
74
|
+
#p.extra_deps = [] # An array of rubygem dependencies [name, version], e.g. [ ['active_support', '>= 1.3.1'] ]
|
75
|
+
#p.spec_extras = {} # A hash of extra values to set in the gemspec.
|
76
|
+
end
|
77
|
+
|
78
|
+
CHANGES = hoe.paragraphs_of('History.txt', 0..1).join("\n\n")
|
79
|
+
PATH = (RUBYFORGE_PROJECT == GEM_NAME) ? RUBYFORGE_PROJECT : "#{RUBYFORGE_PROJECT}/#{GEM_NAME}"
|
80
|
+
hoe.remote_rdoc_dir = File.join(PATH.gsub(/^#{RUBYFORGE_PROJECT}\/?/,''), 'rdoc')
|
81
|
+
|
82
|
+
desc 'Generate website files'
|
83
|
+
task :website_generate do
|
84
|
+
Dir['website/**/*.txt'].each do |txt|
|
85
|
+
sh %{ ruby scripts/txt2html #{txt} > #{txt.gsub(/txt$/,'html')} }
|
86
|
+
end
|
87
|
+
end
|
88
|
+
|
89
|
+
desc 'Upload website files to rubyforge'
|
90
|
+
task :website_upload do
|
91
|
+
host = "#{rubyforge_username}@rubyforge.org"
|
92
|
+
remote_dir = "/var/www/gforge-projects/#{PATH}/"
|
93
|
+
local_dir = 'website'
|
94
|
+
sh %{rsync -aCv #{local_dir}/ #{host}:#{remote_dir}}
|
95
|
+
end
|
96
|
+
|
97
|
+
desc 'Generate and upload website files'
|
98
|
+
task :website => [:website_generate, :website_upload, :publish_docs]
|
99
|
+
|
100
|
+
desc 'Release the website and new gem version'
|
101
|
+
task :deploy => [:check_version, :website, :release] do
|
102
|
+
puts "Remember to create SVN tag:"
|
103
|
+
puts "svn copy svn+ssh://#{rubyforge_username}@rubyforge.org/var/svn/#{PATH}/trunk " +
|
104
|
+
"svn+ssh://#{rubyforge_username}@rubyforge.org/var/svn/#{PATH}/tags/REL-#{VERS} "
|
105
|
+
puts "Suggested comment:"
|
106
|
+
puts "Tagging release #{CHANGES}"
|
107
|
+
end
|
108
|
+
|
109
|
+
desc 'Runs tasks website_generate and install_gem as a local deployment of the gem'
|
110
|
+
task :local_deploy => [:website_generate, :install_gem]
|
111
|
+
|
112
|
+
task :check_version do
|
113
|
+
unless ENV['VERSION']
|
114
|
+
puts 'Must pass a VERSION=x.y.z release version'
|
115
|
+
exit
|
116
|
+
end
|
117
|
+
unless ENV['VERSION'] == VERS
|
118
|
+
puts "Please update your version.rb to match the release version, currently #{VERS}"
|
119
|
+
exit
|
120
|
+
end
|
121
|
+
end
|
122
|
+
|
123
|
+
rule "" do |t|
|
124
|
+
# test:file:method
|
125
|
+
if /test:(.*)(:([^.]+))?$/.match(t.name)
|
126
|
+
arguments = t.name.split(":")[1..-1]
|
127
|
+
test_name = arguments.first
|
128
|
+
run_file_name = "test_rfeedreader.rb"
|
129
|
+
|
130
|
+
sh "ruby -Ilib:test test/#{run_file_name} -n /#{test_name}/"
|
131
|
+
end
|
132
|
+
end
|
data/lib/rfeedreader.rb
ADDED
@@ -0,0 +1,194 @@
|
|
1
|
+
require 'net/http'
|
2
|
+
require 'rubygems'
|
3
|
+
require 'open-uri'
|
4
|
+
require 'hpricot'
|
5
|
+
require 'timeout'
|
6
|
+
require 'rfeedfinder'
|
7
|
+
require 'helper/texty_helper'
|
8
|
+
require 'helper/html_entities'
|
9
|
+
|
10
|
+
module Rfeedreader
|
11
|
+
module_function
|
12
|
+
|
13
|
+
class Feed
|
14
|
+
attr_accessor :title, :link, :charset, :entries
|
15
|
+
|
16
|
+
def initialize(link, hpricot_doc)
|
17
|
+
@link = link
|
18
|
+
read_title hpricot_doc
|
19
|
+
read_charset hpricot_doc
|
20
|
+
@entries = []
|
21
|
+
end
|
22
|
+
|
23
|
+
def parse_entries(hpricot_doc, nb_posts=10)
|
24
|
+
@entries = []
|
25
|
+
type = self.source_type
|
26
|
+
|
27
|
+
# Parse each item
|
28
|
+
(hpricot_doc/"item|entry")[0..nb_posts - 1].each do |item|
|
29
|
+
case type
|
30
|
+
when "source_flickr"
|
31
|
+
@entries<<Entry_Flickr.new(item, self.charset)
|
32
|
+
when "source_fotolog"
|
33
|
+
@entries<<Entry_Fotolog.new(item, self.charset)
|
34
|
+
when "source_google_video"
|
35
|
+
@entries<<Entry_Google_Video.new(item, self.charset)
|
36
|
+
when "source_jumpcut"
|
37
|
+
@entries<<Entry_Jumpcut.new(item, self.charset)
|
38
|
+
when "source_picasa"
|
39
|
+
@entries<<Entry_Picasa.new(item, self.charset)
|
40
|
+
else
|
41
|
+
@entries<<Entry.new(item, self.charset)
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
46
|
+
def to_s
|
47
|
+
"Feed: title: #{title} - charset: #{charset}\n\rlink: #{link} - Entries: #{entries.size}"
|
48
|
+
end
|
49
|
+
|
50
|
+
def display_entries
|
51
|
+
i = 0
|
52
|
+
@entries.each do |entry|
|
53
|
+
i += 1
|
54
|
+
puts "#{i} - #{entry}"
|
55
|
+
end
|
56
|
+
end
|
57
|
+
|
58
|
+
protected
|
59
|
+
|
60
|
+
def read_charset(hpricot_doc)
|
61
|
+
@charset = hpricot_doc.to_s.scan(/encoding=['"]?([^'"]*)['" ]/)
|
62
|
+
@charset = @charset[0] if @charset.is_a? Array
|
63
|
+
@charset = @charset.to_s.downcase
|
64
|
+
end
|
65
|
+
|
66
|
+
def read_title(hpricot_doc)
|
67
|
+
@title = (hpricot_doc/"//title:first").text
|
68
|
+
end
|
69
|
+
|
70
|
+
def source_type
|
71
|
+
return "source_flickr" if link =~ /http:\/\/api\.flickr\.com/
|
72
|
+
return "source_fotolog" if link =~ /\.fotolog\.com/
|
73
|
+
return "source_google_video" if link =~ /http:\/\/video\.google\.com/
|
74
|
+
return "source_jumpcut" if link =~ /http:\/\/rss\.jumpcut\.com/
|
75
|
+
return "source_picasa" if link =~ /http:\/\/picasaweb\.google\.com/
|
76
|
+
return ""
|
77
|
+
end
|
78
|
+
end
|
79
|
+
|
80
|
+
class Entry
|
81
|
+
attr_accessor :title, :link, :description, :charset
|
82
|
+
|
83
|
+
def initialize(item, charset)
|
84
|
+
@charset = charset
|
85
|
+
@link = read_link item
|
86
|
+
@title = read_title item
|
87
|
+
@description = read_description item
|
88
|
+
end
|
89
|
+
|
90
|
+
# Return the rss item link
|
91
|
+
def read_link(item)
|
92
|
+
post_url = nil
|
93
|
+
if link = item.search("link:first")
|
94
|
+
post_url = link.text
|
95
|
+
post_url = link.to_s.scan(/href=['"]?([^'"]*)['" ]/).to_s if (post_url.nil? or post_url.empty?)
|
96
|
+
end
|
97
|
+
return post_url
|
98
|
+
end
|
99
|
+
|
100
|
+
def read_title(item)
|
101
|
+
return TextyHelper::convertEncoding((item/:title).text, @charset).downcase
|
102
|
+
end
|
103
|
+
|
104
|
+
def read_description(item)
|
105
|
+
description = (item/"description|summary|content|[@type='text']").text
|
106
|
+
if description.include? "<"
|
107
|
+
description = HTMLEntities.decode_entities(description)
|
108
|
+
else
|
109
|
+
description = HTMLEntities.encode_entities(description, :named, :decimal) if @charset == 'utf-8'
|
110
|
+
end
|
111
|
+
description = TextyHelper::clean(TextyHelper::convertEncoding(description, @charset), 200) unless description.empty?
|
112
|
+
description.gsub!(/((https?):\/\/([^\/]+)\/(.*))/, '[<a href=\'\1\'>link</a>]') unless description.empty?
|
113
|
+
return description.strip
|
114
|
+
end
|
115
|
+
|
116
|
+
def to_s
|
117
|
+
"Entry: title: #{title} - link: #{link}\n\rdescription: #{description}"
|
118
|
+
end
|
119
|
+
end
|
120
|
+
|
121
|
+
class Entry_Flickr<Entry
|
122
|
+
def read_description(item)
|
123
|
+
image = item.search("media:thumbnail").to_s.scan(/url=['"]?([^'"]*)['" ]/).to_s
|
124
|
+
image = item.search("content|description").text.scan(/(http:\/\/farm.*_.\.jpg)/).to_s if image.nil? or image.empty?
|
125
|
+
image.gsub!(/_.\.jpg/,"_t.jpg")
|
126
|
+
return "<a href='#{@link}' class='image_link'><img src='#{image}' class='flickr_image'/></a><br/>"
|
127
|
+
end
|
128
|
+
end
|
129
|
+
|
130
|
+
class Entry_Fotolog<Entry
|
131
|
+
def read_description(item)
|
132
|
+
image = item.search("media:thumbnail").to_s.scan(/url=['"]?([^'"]*)['" ]/).to_s
|
133
|
+
return "<a href='#{@link}' class='image_link'><img src='#{image}' class='post_image'/></a>"
|
134
|
+
end
|
135
|
+
end
|
136
|
+
|
137
|
+
class Entry_Google_Video<Entry
|
138
|
+
def read_description(item)
|
139
|
+
image = item.search("media:thumbnail").to_s.scan(/url=['"]?([^'"]*)['" ]/).to_s.gsub(/&/, '&')
|
140
|
+
return "<a href='#{@link}' class='image_link'><img src='#{image}' class='google_video_image' width='160px' height='160px'/></a><br/>"
|
141
|
+
end
|
142
|
+
end
|
143
|
+
|
144
|
+
class Entry_Jumpcut<Entry
|
145
|
+
def read_description(item)
|
146
|
+
image = item.search("description").to_s.scan(/src=['"]?([^'"]*)['" ]/).to_s
|
147
|
+
return "<a href='#{@link}' class='image_link'><img src='#{image}' class='jumpcut_image' width='160px' height='120px'/></a><br/>"
|
148
|
+
end
|
149
|
+
end
|
150
|
+
|
151
|
+
class Entry_Picasa<Entry
|
152
|
+
def read_description(item)
|
153
|
+
image = item.search("media:thumbnail").to_s.scan(/url=['"]?([^'"]*)['" ]/).to_s
|
154
|
+
return "<a href='#{@link}' class='image_link'><img src='#{image}' class='picasa_image'/></a>"
|
155
|
+
end
|
156
|
+
end
|
157
|
+
|
158
|
+
def read(uri, nb_posts=10)
|
159
|
+
|
160
|
+
link = Rfeedfinder::feed(uri)
|
161
|
+
doc = open_doc(link)
|
162
|
+
|
163
|
+
unless doc.nil?
|
164
|
+
feed = Feed.new(link, doc)
|
165
|
+
entries = feed.parse_entries(doc, nb_posts)
|
166
|
+
end
|
167
|
+
|
168
|
+
return feed
|
169
|
+
end
|
170
|
+
|
171
|
+
def read_first(uri)
|
172
|
+
return read(uri, nb_post=1)
|
173
|
+
end
|
174
|
+
|
175
|
+
def open_doc(link)
|
176
|
+
begin
|
177
|
+
data = Hpricot(open(link,
|
178
|
+
"User-Agent" => "Ruby/#{RUBY_VERSION} - Rfeedreader",
|
179
|
+
"From" => "rfeedreader@googlegroups.com",
|
180
|
+
"Referer" => "http://rfeedreader.rubyforge.org/"), :xml => true)
|
181
|
+
rescue Timeout::Error
|
182
|
+
return nil
|
183
|
+
rescue OpenURI::HTTPError
|
184
|
+
html = Net::HTTP.get(URI.parse(link))
|
185
|
+
data = Hpricot(html, :xml => true)
|
186
|
+
rescue => err
|
187
|
+
puts "Error while opening #{link} with Hpricot: #{err.class} " << $!
|
188
|
+
return nil
|
189
|
+
end
|
190
|
+
return data
|
191
|
+
end
|
192
|
+
end
|
193
|
+
|
194
|
+
require 'rfeedreader/version'
|
data/scripts/txt2html
ADDED
@@ -0,0 +1,67 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'rubygems'
|
4
|
+
require 'redcloth'
|
5
|
+
require 'syntax/convertors/html'
|
6
|
+
require 'erb'
|
7
|
+
require File.dirname(__FILE__) + '/../lib/rfeedreader/version.rb'
|
8
|
+
|
9
|
+
version = Rfeedreader::VERSION::STRING
|
10
|
+
download = 'http://rubyforge.org/projects/rfeedreader'
|
11
|
+
|
12
|
+
class Fixnum
|
13
|
+
def ordinal
|
14
|
+
# teens
|
15
|
+
return 'th' if (10..19).include?(self % 100)
|
16
|
+
# others
|
17
|
+
case self % 10
|
18
|
+
when 1: return 'st'
|
19
|
+
when 2: return 'nd'
|
20
|
+
when 3: return 'rd'
|
21
|
+
else return 'th'
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
25
|
+
|
26
|
+
class Time
|
27
|
+
def pretty
|
28
|
+
return "#{mday}#{mday.ordinal} #{strftime('%B')} #{year}"
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
def convert_syntax(syntax, source)
|
33
|
+
return Syntax::Convertors::HTML.for_syntax(syntax).convert(source).gsub(%r!^<pre>|</pre>$!,'')
|
34
|
+
end
|
35
|
+
|
36
|
+
if ARGV.length >= 1
|
37
|
+
src, template = ARGV
|
38
|
+
template ||= File.dirname(__FILE__) + '/../website/template.rhtml'
|
39
|
+
|
40
|
+
else
|
41
|
+
puts("Usage: #{File.split($0).last} source.txt [template.rhtml] > output.html")
|
42
|
+
exit!
|
43
|
+
end
|
44
|
+
|
45
|
+
template = ERB.new(File.open(template).read)
|
46
|
+
|
47
|
+
title = nil
|
48
|
+
body = nil
|
49
|
+
File.open(src) do |fsrc|
|
50
|
+
title_text = fsrc.readline
|
51
|
+
body_text = fsrc.read
|
52
|
+
syntax_items = []
|
53
|
+
body_text.gsub!(%r!<(pre|code)[^>]*?syntax=['"]([^'"]+)[^>]*>(.*?)</>!m){
|
54
|
+
ident = syntax_items.length
|
55
|
+
element, syntax, source = $1, $2, $3
|
56
|
+
syntax_items << "<#{element} class='syntax'>#{convert_syntax(syntax, source)}</#{element}>"
|
57
|
+
"syntax-temp-#{ident}"
|
58
|
+
}
|
59
|
+
title = RedCloth.new(title_text).to_html.gsub(%r!<.*?>!,'').strip
|
60
|
+
body = RedCloth.new(body_text).to_html
|
61
|
+
body.gsub!(%r!(?:<pre><code>)?syntax-temp-(d+)(?:</code></pre>)?!){ syntax_items[$1.to_i] }
|
62
|
+
end
|
63
|
+
stat = File.stat(src)
|
64
|
+
created = stat.ctime
|
65
|
+
modified = stat.mtime
|
66
|
+
|
67
|
+
$stdout << template.result(binding)
|