pismo 0.2.3 → 0.4.0

data/lib/pismo.rb

@@ -4,6 +4,7 @@ require 'open-uri'
 require 'nokogiri'
 require 'fast_stemmer'
 require 'chronic'
+require 'tempfile'
 
 $: << File.dirname(__FILE__)
 require 'pismo/document'
@@ -28,8 +29,9 @@ class Nokogiri::HTML::Document
     self.search(search).first rescue nil
   end
   
-  def match(*queries)
-    queries.each do |query|
+  def match(queries = [], all = false)
+    r = [] if all
+    [*queries].each do |query|
       if query.is_a?(String)
         result = self.search(query).first.inner_text.strip rescue nil
       elsif query.is_a?(Array)
@@ -41,9 +43,13 @@ class Nokogiri::HTML::Document
       #  result.gsub!(/\342\200\224/, '-')
         result.gsub!('’', '\'')
         result.gsub!('—', '-')
-        return result
+        if all
+          r << result
+        else
+          return result
+        end
       end
     end
-    return nil
+    all && !r.empty? ? r : nil
   end
 end

data/pismo.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{pismo}
-  s.version = "0.2.3"
+  s.version = "0.4.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Peter Cooper"]
-  s.date = %q{2010-05-03}
+  s.date = %q{2010-05-15}
   s.default_executable = %q{pismo}
   s.description = %q{Pismo extracts and retrieves content-related metadata from HTML pages - you can use the resulting data in an organized way, such as a summary/first paragraph, body text, keywords, RSS feed URL, favicon, etc.}
   s.email = %q{git@peterc.org}

data/test/corpus/metadata_expected.yaml

@@ -2,6 +2,9 @@
 :rww: 
   :title: "Cartoon: Apple Tablet: Now With Barometer and Bird Call Generator"
   :feed: http://www.readwriteweb.com/rss.xml
+  :feeds:
+    - http://www.readwriteweb.com/rss.xml
+    - http://www.readwriteweb.com/archives/2010/01/cartoon_apple_tablet_now_with_barometer_and_bird_c.xml  
 :briancray: 
   :title: 5 great examples of popular blog posts that you should know
   :feed: http://feeds.feedburner.com/briancray/blog
@@ -9,23 +12,37 @@
 :huffington:
   :title: Afghans Losing Hope After 8 Years Of War
   :author: TODD PITMAN
+  :authors:
+    - TODD PITMAN
+    - AP
   :feed: http://feeds.huffingtonpost.com/huffingtonpost/raw_feed
   :lede: "KABUL - The man on the motorcycle was going the wrong way down a one-way street, gesturing indignantly for the phalanx of traffic-clogged cars in front of him to move."
 :bbcnews:
   :title: Gay Muslims made homeless by family violence
+  :titles:
+    - Gay Muslims made homeless by family violence
   :author: Poonam Taneja
+  :authors:
+    - Poonam Taneja
   :description: A charity is dealing with more gay Muslims made homeless after fleeing forced marriages and so-called "honour" violence.
   :lede: A UK charity is dealing with an increasing number of young gay Muslims becoming homeless after fleeing forced marriages and so-called honour violence.
   :feed: http://newsrss.bbc.co.uk/rss/newsonline_uk_edition/england/rss.xml
 :factor:
   :title: Factor's bootstrap process explained
   :lede: "Separation of concerns between Factor VM and library codeThe Factor VM implements an abstract machine consisting of a data heap of objects, a code heap of machine code blocks, and a set of stacks. The VM loads an image file on startup, which becomes the data and code heap. "
+  :ledes:
+    - "Separation of concerns between Factor VM and library codeThe Factor VM implements an abstract machine consisting of a data heap of objects, a code heap of machine code blocks, and a set of stacks. The VM loads an image file on startup, which becomes the data and code heap. "
+    - Slava Pestov's weblog, primarily about Factor.  
 :youtube:
   :title: YMO - Rydeen (Official Video)
   :author: ymo1965
+  :authors:
+    - ymo1965
 :spolsky:
   :title: The Absolute Minimum Every Software Developer Absolutely, Positively Must Know About Unicode and Character Sets (No Excuses!)
   :description: Haven't mastered the basics of Unicode and character sets? Please don't write another line of code until you've read this article.
+  :ledes:
+    - Ever wonder about that mysterious Content-Type tag? You know, the one you're supposed to put in HTML and you never quite know what it should be?
   :author: Joel Spolsky
   :favicon: /favicon.ico
   :feed: http://www.joelonsoftware.com/rss.xml

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: pismo
 version: !ruby/object:Gem::Version 
-  version: 0.2.3
+  version: 0.4.0
 platform: ruby
 authors: 
 - Peter Cooper
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-05-03 00:00:00 +01:00
+date: 2010-05-15 00:00:00 +01:00
 default_executable: pismo
 dependencies: 
 - !ruby/object:Gem::Dependency