pauldix-feedzirra 0.0.8 → 0.0.9

data/README.textile

@@ -116,6 +116,12 @@ Feedzirra::Feed.add_common_feed_entry_element("wfw:commentRss", :as => :comment_
 # AtomEntry classes. Now you can access those in an atom feed:
 Feedzirra::Feed.parse(some_atom_xml).entries.first.comment_rss_ # => wfw:commentRss is now parsed!
 
+
+# You can also define your own parsers and add them to the ones Feedzirra knows about. Here's an example that adds 
+# ITunesRSS parsing. It's included in the library, but not part of Feedzirra by default because some of the field names 
+# differ from other classes, thus breaking normalization.
+Feedzirra::Feed.add_feed_class(ITunesRSS) # now all feeds will be checked to see if they match ITunesRSS before others
+
 # You can also access http basic auth feeds. Unfortunately, you can't get to these inside of a bulk get of a bunch of feeds.
 # You'll have to do it on its own like so:
 Feedzirra::Feed.fetch_and_parse(some_url, :http_authentication => ["myusername", "mypassword"])
@@ -149,13 +155,15 @@ h2. Next Steps
 This thing needs to hammer on many different feeds in the wild. I'm sure there will be bugs. I want to find them and crush them. I didn't bother using the test suite for feedparser. i wanted to start fresh.
 
 Here are some more specific TODOs.
+* Fix the iTunes parser so things are normalized again
+* Fix the Zlib deflate error
+* Fix this error: http://github.com/inbox/70508
+* Convert to use Typhoeus instead of taf2-curb
+* Make the entries parse all link fields
 * Make a feedzirra-rails gem to integrate feedzirra seamlessly with Rails and ActiveRecord.
-* Add support for authenticated feeds.
 * Create a super sweet DSL for defining new parsers.
 * Test against Ruby 1.9.1 and fix any bugs.
-* I'm not keeping track of modified on entries. Should I add this?
 * Clean up the fetching code inside feed.rb so it doesn't suck so hard.
-* Make the feed_spec actually mock stuff out so it doesn't hit the net.
 * Readdress how feeds determine if they can parse a document. Maybe I should use namespaces instead?
 
 h2. LICENSE

data/lib/feedzirra.rb

@@ -30,5 +30,5 @@ require 'feedzirra/atom'
 require 'feedzirra/atom_feed_burner'
 
 module Feedzirra
-  VERSION = "0.0.8"
+  VERSION = "0.0.9"
 end

data/lib/feedzirra/feed.rb

@@ -46,7 +46,7 @@ module Feedzirra
     # === Returns
     # A array of class names.
     def self.feed_classes
-      @feed_classes ||= [ITunesRSS, RSS, AtomFeedBurner, Atom]
+      @feed_classes ||= [RSS, AtomFeedBurner, Atom]
     end
     
     # Makes all entry types look for the passed in element to parse. This is actually just a call to 
@@ -58,7 +58,7 @@ module Feedzirra
     def self.add_common_feed_entry_element(element_tag, options = {})
       # need to think of a better way to do this. will break for people who want this behavior
       # across their added classes
-      [RSSEntry, AtomFeedBurnerEntry, AtomEntry].each do |klass|
+      feed_classes.each do |klass|
         klass.send(:element, element_tag, options)
       end
     end
@@ -100,7 +100,7 @@ module Feedzirra
           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.headers["Accept-encoding"]   = 'gzip, deflate'
           curl.follow_location = true
           curl.userpwd = options[:http_authentication].join(':') if options.has_key?(:http_authentication)
 
@@ -216,7 +216,7 @@ module Feedzirra
         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.headers["Accept-encoding"]   = 'gzip, deflate'
         curl.follow_location = true
         curl.userpwd = options[:http_authentication].join(':') if options.has_key?(:http_authentication)
         
@@ -226,12 +226,16 @@ module Feedzirra
           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)
+            begin
+              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)
+            rescue Exception => e
+              options[:on_failure].call(url, c.response_code, c.header_str, c.body_str) if options.has_key?(:on_failure)
+            end
           else
             # puts "Error determining parser for #{url} - #{c.last_effective_url}"
             # raise NoParserAvailable.new("no valid parser for content.") (this would unfirtunately fail the whole 'multi', so it's not really useable)
@@ -271,14 +275,18 @@ module Feedzirra
         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)
+          begin
+            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)
+          rescue Exception => e
+            options[:on_failure].call(feed, c.response_code, c.header_str, c.body_str) if options.has_key?(:on_failure)
+          end
         end
 
         curl.on_failure do |c|

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: pauldix-feedzirra
 version: !ruby/object:Gem::Version 
-  version: 0.0.8
+  version: 0.0.9
 platform: ruby
 authors: 
 - Paul Dix