Class: Feedzirra::Feed

Inherits:
Object
  • Object
show all
Defined in:
lib/feedzirra/feed.rb

Constant Summary collapse

USER_AGENT = 
"feedzirra http://github.com/pauldix/feedzirra/tree/master"

Class Method Summary collapse

Class Method Details

.add_feed_class(klass) ⇒ Object 



20
21
22
 
# File 'lib/feedzirra/feed.rb', line 20

def self.add_feed_class(klass)
  feed_classes.unshift klass
end

.add_feed_to_multi(multi, feed, feed_queue, responses, options) ⇒ Object 



128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
 
# File 'lib/feedzirra/feed.rb', line 128

def self.add_feed_to_multi(multi, feed, feed_queue, responses, options)
  # on_success = options[:on_success]
  # on_failure = options[:on_failure]
  # options[:on_success] = lambda do ||
  
  easy = Curl::Easy.new(feed.feed_url) do |curl|
    curl.headers["User-Agent"]        = (options[:user_agent] || USER_AGENT)
    curl.headers["If-Modified-Since"] = feed.last_modified.httpdate if feed.last_modified
    curl.headers["If-None-Match"]     = feed.etag if feed.etag
    curl.follow_location = true
    curl.on_success do |c|
      add_feed_to_multi(multi, feed_queue.shift, feed_queue, responses, options) unless feed_queue.empty?
      updated_feed = Feed.parse(c.body_str)
      updated_feed.feed_url = c.last_effective_url
      updated_feed.etag = etag_from_header(c.header_str)
      updated_feed.last_modified = last_modified_from_header(c.header_str)
      feed.update_from_feed(updated_feed)
      responses[feed.feed_url] = feed
      options[:on_success].call(feed) if options.has_key?(:on_success)
    end
    curl.on_failure do |c|
      add_feed_to_multi(multi, feed_queue.shift, feed_queue, responses, options) unless feed_queue.empty?
      response_code = c.response_code
      if response_code == 304 # it's not modified. this isn't an error condition
        responses[feed.feed_url] = feed
        options[:on_success].call(feed) if options.has_key?(:on_success)
      else
        responses[feed.url] = c.response_code
        options[:on_failure].call(feed, c.response_code, c.header_str, c.body_str) if options.has_key?(:on_failure)
      end
    end
  end
  multi.add(easy)
end

.add_url_to_multi(multi, url, url_queue, responses, options) ⇒ Object 



97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
 
# File 'lib/feedzirra/feed.rb', line 97

def self.add_url_to_multi(multi, url, url_queue, responses, options)
  easy = Curl::Easy.new(url) do |curl|
    curl.headers["User-Agent"]        = (options[:user_agent] || USER_AGENT)
    curl.headers["If-Modified-Since"] = options[:if_modified_since].httpdate if options.has_key?(:if_modified_since)
    curl.headers["If-None-Match"]     = options[:if_none_match] if options.has_key?(:if_none_match)
    curl.headers["Accept-encoding"]   = 'gzip, deflate'
    curl.follow_location = true
    curl.on_success do |c|
      add_url_to_multi(multi, url_queue.shift, url_queue, responses, options) unless url_queue.empty?
      xml = decode_content(c)
      klass = determine_feed_parser_for_xml(xml)
      if klass
        feed = klass.parse(xml)
        feed.feed_url = c.last_effective_url
        feed.etag = etag_from_header(c.header_str)
        feed.last_modified = last_modified_from_header(c.header_str)
        responses[url] = feed
        options[:on_success].call(url, feed) if options.has_key?(:on_success)
      else
        puts "Error determining parser for #{url} - #{c.last_effective_url}"
      end
    end
    curl.on_failure do |c|
      add_url_to_multi(multi, url_queue.shift, url_queue, responses, options) unless url_queue.empty?
      responses[url] = c.response_code
      options[:on_failure].call(url, c.response_code, c.header_str, c.body_str) if options.has_key?(:on_failure)
    end
  end
  multi.add(easy)
end

.decode_content(c) ⇒ Object 



71
72
73
74
75
76
77
78
79
80
81
82
83
 
# File 'lib/feedzirra/feed.rb', line 71

def self.decode_content(c)
  if c.header_str.match(/Content-Encoding: gzip/)
    gz =  Zlib::GzipReader.new(StringIO.new(c.body_str))
    xml = gz.read
    gz.close
  elsif c.header_str.match(/Content-Encoding: deflate/)
    xml = Zlib::Deflate.inflate(c.body_str)
  else
    xml = c.body_str
  end
  
  xml
end

.determine_feed_parser_for_xml(xml) ⇒ Object 



15
16
17
18
 
# File 'lib/feedzirra/feed.rb', line 15

def self.determine_feed_parser_for_xml(xml)
  start_of_doc = xml.slice(0, 1000)
  feed_classes.detect {|klass| klass.able_to_parse?(start_of_doc)}
end

.etag_from_header(header) ⇒ Object 



163
164
165
166
 
# File 'lib/feedzirra/feed.rb', line 163

def self.etag_from_header(header)
  header =~ /.*ETag:\s(.*)\r/
  $1
end

.feed_classes ⇒ Object 



24
25
26
 
# File 'lib/feedzirra/feed.rb', line 24

def self.feed_classes
  @feed_classes ||= [RSS, AtomFeedBurner, Atom]
end

.fetch_and_parse(urls, options = {}) ⇒ Object 



56
57
58
59
60
61
62
63
64
65
66
67
68
69
 
# File 'lib/feedzirra/feed.rb', line 56

def self.fetch_and_parse(urls, options = {})
  url_queue = [*urls]
  multi = Curl::Multi.new

  # I broke these down so I would only try to do 30 simultaneously because 
  # I was getting weird errors when doing a lot. As one finishes it pops another off the queue.
  responses = {}
  url_queue.slice!(0, 30).each do |url|
    add_url_to_multi(multi, url, url_queue, responses, options)
  end

  multi.perform
  return urls.is_a?(String) ? responses.values.first : responses
end

.fetch_raw(urls, options = {}) ⇒ Object

can take a single url or an array of urls when passed a single url it returns the body of the response when passed an array of urls it returns a hash with the urls as keys and body of responses as values



31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
 
# File 'lib/feedzirra/feed.rb', line 31

def self.fetch_raw(urls, options = {})
  url_queue = [*urls]
  multi = Curl::Multi.new
  responses = {}
  url_queue.each do |url|
    easy = Curl::Easy.new(url) do |curl|
      curl.headers["User-Agent"]        = (options[:user_agent] || USER_AGENT)
      curl.headers["If-Modified-Since"] = options[:if_modified_since].httpdate if options.has_key?(:if_modified_since)
      curl.headers["If-None-Match"]     = options[:if_none_match] if options.has_key?(:if_none_match)
      curl.headers["Accept-encoding"]   = 'gzip, deflate'
      curl.follow_location = true
      curl.on_success do |c|
        responses[url] = decode_content(c)
      end
      curl.on_failure do |c|
        responses[url] = c.response_code
      end
    end
    multi.add(easy)
  end

  multi.perform
  return urls.is_a?(String) ? responses.values.first : responses
end

.last_modified_from_header(header) ⇒ Object 



168
169
170
171
 
# File 'lib/feedzirra/feed.rb', line 168

def self.last_modified_from_header(header)
  header =~ /.*Last-Modified:\s(.*)\r/
  Time.parse($1) if $1
end

.parse(xml) ⇒ Object 



7
8
9
10
11
12
13
 
# File 'lib/feedzirra/feed.rb', line 7

def self.parse(xml)
  if parser = determine_feed_parser_for_xml(xml)
    parser.parse(xml)
  else
    raise NoParserAvailable.new("no valid parser for content.")
  end
end

.update(feeds, options = {}) ⇒ Object 



85
86
87
88
89
90
91
92
93
94
95
 
# File 'lib/feedzirra/feed.rb', line 85

def self.update(feeds, options = {})
  feed_queue = [*feeds]
  multi = Curl::Multi.new
  responses = {}
  feed_queue.slice!(0, 30).each do |feed|
    add_feed_to_multi(multi, feed, feed_queue, responses, options)
  end

  multi.perform
  return responses.size == 1 ? responses.values.first : responses.values
end