Class: Feedjira::Feed

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

Constant Summary

USER_AGENT =
'feedjira http://feedjira.com'

Class Method Summary collapse

Class Method Details

.add_common_feed_element(element_tag, options = {}) ⇒ Object

Makes all registered feeds types look for the passed in element to parse. This is actually just a call to element (a SAXMachine call) in the class.

Parameters

element_tag<String>

The element tag

options<Hash>

Valid keys are same as with SAXMachine



80
81
82
83
84
# File 'lib/feedjira/feed.rb', line 80

def self.add_common_feed_element(element_tag, options = {})
  feed_classes.each do |k|
    k.element element_tag, options
  end
end

.add_common_feed_elements(element_tag, options = {}) ⇒ Object

Makes all registered feeds types look for the passed in elements to parse. This is actually just a call to elements (a SAXMachine call) in the class.

Parameters

element_tag<String>

The element tag

options<Hash>

Valid keys are same as with SAXMachine



92
93
94
95
96
# File 'lib/feedjira/feed.rb', line 92

def self.add_common_feed_elements(element_tag, options = {})
  feed_classes.each do |k|
    k.elements element_tag, options
  end
end

.add_common_feed_entry_element(element_tag, options = {}) ⇒ Object

Makes all registered entry types look for the passed in element to parse. This is actually just a call to element (a SAXMachine call) in the class.

Parameters

element_tag<String>
options<Hash>

Valid keys are same as with SAXMachine



104
105
106
# File 'lib/feedjira/feed.rb', line 104

def self.add_common_feed_entry_element(element_tag, options = {})
  call_on_each_feed_entry :element, element_tag, options
end

.add_common_feed_entry_elements(element_tag, options = {}) ⇒ Object

Makes all registered entry types look for the passed in elements to parse. This is actually just a call to element (a SAXMachine call) in the class.

Parameters

element_tag<String>
options<Hash>

Valid keys are same as with SAXMachine



114
115
116
# File 'lib/feedjira/feed.rb', line 114

def self.add_common_feed_entry_elements(element_tag, options = {})
  call_on_each_feed_entry :elements, element_tag, options
end

.add_feed_class(klass) ⇒ Object

Adds a new feed parsing class that will be used for parsing.

Parameters

klass<Constant>

The class/constant that you want to register.

Returns

A updated array of feed parser class names.



55
56
57
# File 'lib/feedjira/feed.rb', line 55

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

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

An abstraction for adding a feed by a Feed object to the passed Curb::multi stack.

Parameters

multi<Curl::Multi>

The Curl::Multi object that the request should be added too.

feed<Feed>

A feed object that you would like to be fetched.

url_queue<Array>

An array of feed objects that are queued for request.

responses<Hash>

Existing responses that you want the response from the request added to.

feeds<String>

or <Array> A single feed object, or an array of feed objects.

options<Hash>

Valid keys for this argument as as followed:

  • :on_success - Block that gets executed after a successful request.

  • :on_failure - Block that gets executed after a failed request.

  • all parameters defined in setup_easy

Returns

The updated Curl::Multi object with the request details added to it's stack.



374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
# File 'lib/feedjira/feed.rb', line 374

def self.add_feed_to_multi(multi, feed, feed_queue, responses, options)
  easy = Curl::Easy.new(feed.feed_url) do |curl|
    setup_easy curl, options
    curl.headers["If-Modified-Since"] = feed.last_modified.httpdate if feed.last_modified
    curl.headers["If-Modified-Since"] = options[:if_modified_since] if options[:if_modified_since] && (!feed.last_modified || (Time.parse(options[:if_modified_since].to_s) > feed.last_modified))
    curl.headers["If-None-Match"]     = feed.etag if feed.etag

    curl.on_success do |c|
      begin
        updated_feed = Feed.parse c.body_str, &on_parser_failure(feed.feed_url)

        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)
      rescue Exception => e
        call_on_failure(c, e, options[:on_failure])
      end
    end

    curl.on_failure do |c, err| # response code 50X
      responses[feed.feed_url] = c.response_code
      call_on_failure(c, 'Server returned a 404', options[:on_failure])
    end

    curl.on_redirect do |c, err| # response code 30X
      if c.response_code == 304
        options[:on_success].call(feed) if options.has_key?(:on_success)
      else
        responses[feed.feed_url] = c.response_code
        call_on_failure(c, err, options[:on_failure])
      end
    end

    curl.on_complete do |c|
      add_feed_to_multi(multi, feed_queue.shift, feed_queue, responses, options) unless feed_queue.empty?
      responses[feed.feed_url] = feed unless responses.has_key?(feed.feed_url)
    end
  end
  multi.add(easy)
end

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

An abstraction for adding a feed by URL to the passed Curb::multi stack.

Parameters

multi<Curl::Multi>

The Curl::Multi object that the request should be added too.

url<String>

The URL of the feed that you would like to be fetched.

url_queue<Array>

An array of URLs that are queued for request.

responses<Hash>

Existing responses that you want the response from the request added to.

feeds<String> or <Array>

A single feed object, or an array of feed objects.

options<Hash>

Valid keys for this argument as as followed:

  • :on_success - Block that gets executed after a successful request.

  • :on_failure - Block that gets executed after a failed request.

  • all parameters defined in setup_easy

Returns

The updated Curl::Multi object with the request details added to it's stack.



305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
# File 'lib/feedjira/feed.rb', line 305

def self.add_url_to_multi(multi, url, url_queue, responses, options)
  easy = Curl::Easy.new(url) do |curl|
    setup_easy curl, options
    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.on_success do |c|
      xml = decode_content(c)
      klass = determine_feed_parser_for_xml(xml)

      if klass
        begin
          feed = parse_with klass, xml, &on_parser_failure(url)

          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)
        rescue Exception => e
          call_on_failure(c, e, options[:on_failure])
        end
      else
        call_on_failure(c, "Can't determine a parser", options[:on_failure])
      end
    end

    #
    # trigger on_failure for 404s
    #
    curl.on_complete do |c|
      add_url_to_multi(multi, url_queue.shift, url_queue, responses, options) unless url_queue.empty?
      responses[url] = c.response_code unless responses.has_key?(url)
    end

    curl.on_redirect do |c|
      if c.response_code == 304 # it's not modified. this isn't an error condition
        options[:on_success].call(url, nil) if options.has_key?(:on_success)
      end
    end

    curl.on_missing do |c|
      if c.response_code == 404 && options.has_key?(:on_failure)
        call_on_failure(c, 'Server returned a 404', options[:on_failure])
      end
    end

    curl.on_failure do |c, err|
      responses[url] = c.response_code
      call_on_failure(c, err, options[:on_failure])
    end
  end
  multi.add(easy)
end

.call_on_each_feed_entry(method, *parameters) ⇒ Object

Call a method on all feed entries classes.

Parameters

method<Symbol>

The method name

parameters<Array>

The method parameters



123
124
125
126
127
128
129
130
131
132
133
134
# File 'lib/feedjira/feed.rb', line 123

def self.call_on_each_feed_entry(method, *parameters)
  feed_classes.each do |k|
    # iterate on the collections defined in the sax collection
    k.sax_config.collection_elements.each_value do |vl|
      # vl is a list of CollectionConfig mapped to an attribute name
      # we'll look for the one set as 'entries' and add the new element
      vl.find_all{|v| (v.accessor == 'entries') && (v.data_class.class == Class)}.each do |v|
          v.data_class.send(method, *parameters)
      end
    end
  end
end

.decode_content(c) ⇒ Object

Decodes the XML document if it was compressed.

Parameters

curl_request<Curl::Easy>

The Curl::Easy response object from the request.

Returns

A decoded string of XML.



247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
# File 'lib/feedjira/feed.rb', line 247

def self.decode_content(c)
  if c.header_str.match(/Content-Encoding: gzip/i)
    begin
      gz =  Zlib::GzipReader.new(StringIO.new(c.body_str))
      xml = gz.read
      gz.close
    rescue Zlib::GzipFile::Error
      # Maybe this is not gzipped?
      xml = c.body_str
    end
  elsif c.header_str.match(/Content-Encoding: deflate/i)
    xml = Zlib::Inflate.inflate(c.body_str)
  else
    xml = c.body_str
  end

  xml
end

.determine_feed_parser_for_xml(xml) ⇒ Object

Determines the correct parser class to use for parsing the feed.

Parameters

xml<String>

The XML that you would like determine the parser for.

Returns

The class name of the parser that can handle the XML.



44
45
46
47
# File 'lib/feedjira/feed.rb', line 44

def self.determine_feed_parser_for_xml(xml)
  start_of_doc = xml.slice(0, 2000)
  feed_classes.detect {|klass| klass.able_to_parse?(start_of_doc)}
end

.etag_from_header(header) ⇒ Object

Determines the etag from the request headers.

Parameters

header<String>

Raw request header returned from the request

Returns

A string of the etag or nil if it cannot be found in the headers.



424
425
426
427
# File 'lib/feedjira/feed.rb', line 424

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

.feed_classesObject

Provides a list of registered feed parsing classes.

Returns

A array of class names.



63
64
65
66
67
68
69
70
71
72
# File 'lib/feedjira/feed.rb', line 63

def self.feed_classes
  @feed_classes ||= [
    Feedjira::Parser::RSSFeedBurner,
    Feedjira::Parser::GoogleDocsAtom,
    Feedjira::Parser::AtomFeedBurner,
    Feedjira::Parser::Atom,
    Feedjira::Parser::ITunesRSS,
    Feedjira::Parser::RSS
  ]
end

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

Fetches and returns the parsed XML for each URL provided.

Parameters

urls<String> or <Array>

A single feed URL, or an array of feed URLs.

options<Hash>

Valid keys for this argument as as followed:

  • :user_agent - String that overrides the default user agent.

  • :if_modified_since - Time object representing when the feed was last updated.

  • :if_none_match - String, an etag for the request that was stored previously.

  • :on_success - Block that gets executed after a successful request.

  • :on_failure - Block that gets executed after a failed request.

Returns

A Feed object if a single URL is passed.

A Hash if multiple URL's are passed. The key will be the URL, and the value the Feed object.



226
227
228
229
230
231
232
233
234
235
236
237
238
239
# File 'lib/feedjira/feed.rb', line 226

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

  # 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.
  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

Fetches and returns the raw XML for each URL provided.

Parameters

urls<String> or <Array>

A single feed URL, or an array of feed URLs.

options<Hash>

Valid keys for this argument as as followed: :if_modified_since - Time object representing when the feed was last updated. :if_none_match - String that's normally an etag for the request that was stored previously. :on_success - Block that gets executed after a successful request. :on_failure - Block that gets executed after a failed request.

  • all parameters defined in setup_easy

Returns

A String of XML if a single URL is passed.

A Hash if multiple URL's are passed. The key will be the URL, and the value the XML.



186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
# File 'lib/feedjira/feed.rb', line 186

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|
      setup_easy curl, options

      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.on_success do |c|
        responses[url] = decode_content(c)
      end

      curl.on_complete do |c, err|
        responses[url] = c.response_code unless responses.has_key?(url)
      end
    end
    multi.add(easy)
  end

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

.last_modified_from_header(header) ⇒ Object

Determines the last modified date from the request headers.

Parameters

header<String>

Raw request header returned from the request

Returns

A Time object of the last modified date or nil if it cannot be found in the headers.



435
436
437
438
# File 'lib/feedjira/feed.rb', line 435

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

.parse(xml, &block) ⇒ Object

Takes a raw XML feed and attempts to parse it. If no parser is available a Feedjira::NoParserAvailable exception is raised. You can pass a block to be called when there's an error during the parsing.

Parameters

xml<String>

The XML that you would like parsed.

Returns

An instance of the determined feed type. By default, one of these:

  • Feedjira::Parser::RSSFeedBurner

  • Feedjira::Parser::GoogleDocsAtom

  • Feedjira::Parser::AtomFeedBurner

  • Feedjira::Parser::Atom

  • Feedjira::Parser::ITunesRSS

  • Feedjira::Parser::RSS

Raises

Feedjira::NoParserAvailable : If no valid parser classes could be found for the feed.



30
31
32
33
34
35
36
# File 'lib/feedjira/feed.rb', line 30

def self.parse(xml, &block)
  if parser = determine_feed_parser_for_xml(xml)
    parse_with parser, xml, &block
  else
    raise NoParserAvailable.new("No valid parser for XML.")
  end
end

.parse_with(parser, xml, &block) ⇒ Object

Passes raw XML and callbacks to a parser.

Parameters

parser<Object>

The parser to pass arguments to - must respond to

`parse` and should return a Feed object.

xml<String>

The XML that you would like parsed.

Returns

An instance of the parser feed type.



12
13
14
# File 'lib/feedjira/feed.rb', line 12

def self.parse_with(parser, xml, &block)
  parser.parse xml, &block
end

.setup_easy(curl, options = {}) ⇒ Object

Setup curl from options. Possible parameters:

  • :user_agent - overrides the default user agent.

  • :language - accept language value.

  • :compress - any value to enable compression

  • :enable_cookies - boolean

  • :cookiefile - file to read cookies

  • :cookies - contents of cookies header

  • :http_authentication - array containing username, then password

  • :proxy_url - proxy url

  • :proxy_port - proxy port

  • :max_redirects - max number of redirections

  • :timeout - timeout

  • :ssl_verify_host - boolean

  • :ssl_verify_peer - boolean

  • :ssl_version - the ssl version to use, see OpenSSL::SSL::SSLContext::METHODS for options



152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
# File 'lib/feedjira/feed.rb', line 152

def self.setup_easy(curl, options={})
  curl.headers["Accept-encoding"]   = 'gzip, deflate' if options.has_key?(:compress)
  curl.headers["User-Agent"]        = (options[:user_agent] || USER_AGENT)
  curl.headers["Accept-Language"]   = options[:language] if options.has_key?(:language)
  curl.enable_cookies               = options[:enable_cookies] if options.has_key?(:enable_cookies)
  curl.cookiefile                   = options[:cookiefile] if options.has_key?(:cookiefile)
  curl.cookies                      = options[:cookies] if options.has_key?(:cookies)

  curl.userpwd = options[:http_authentication].join(':') if options.has_key?(:http_authentication)
  curl.proxy_url = options[:proxy_url] if options.has_key?(:proxy_url)
  curl.proxy_port = options[:proxy_port] if options.has_key?(:proxy_port)
  curl.max_redirects = options[:max_redirects] if options[:max_redirects]
  curl.timeout = options[:timeout] if options[:timeout]
  curl.ssl_verify_host = options[:ssl_verify_host] if options.has_key?(:ssl_verify_host)
  curl.ssl_verify_peer = options[:ssl_verify_peer] if options.has_key?(:ssl_verify_peer)
  curl.ssl_version = options[:ssl_version] if options.has_key?(:ssl_version)

  curl.follow_location = true
end

.update(feeds, options = {}) ⇒ Object

Updates each feed for each Feed object provided.

Parameters

feeds<Feed> or <Array>

A single feed object, or an array of feed objects.

options<Hash>

Valid keys for this argument as as followed:

  • :on_success - Block that gets executed after a successful request.

  • :on_failure - Block that gets executed after a failed request.

  • all parameters defined in setup_easy

Returns

A updated Feed object if a single URL is passed.

A Hash if multiple Feeds are passed. The key will be the URL, and the value the updated Feed object.



278
279
280
281
282
283
284
285
286
287
288
289
# File 'lib/feedjira/feed.rb', line 278

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
  feeds.is_a?(Array) ? responses : responses.values.first
end