youtubescraper 0.0.8 → 0.0.9

data/CHANGELOG

@@ -25,3 +25,7 @@
 
 0.0.8 2007-03-29
   Description is not required.
+
+0.0.9 2007-03-30
+  Add sort function for Youtube::SearchResultScraper
+  Scrape upload_time from search result page

data/lib/youtube/searchresultscraper.rb

@@ -61,10 +61,16 @@ module Youtube #:nodoc:
 
     attr_accessor :keyword
     attr_accessor :page
+    attr_accessor :sort
     attr_reader   :video_count
     attr_reader   :video_from
     attr_reader   :video_to
 
+    Relevance   = 'relevance'
+    DateAdded   = 'video_date_uploaded'
+    ViewCount   = 'video_view_count'
+    Rating      = 'video_avg_rating'
+
     @@youtube_search_base_url = "http://www.youtube.com/results?search_query="
 
     # Create Youtube::SearchResultScraper object specifying keyword and number of page.
@@ -75,16 +81,19 @@ module Youtube #:nodoc:
     # * keyword - specify keyword that you want to search on YouTube.
     #   You must specify keyword encoded by UTF-8.
     # * page    - specify number of page
+    # * sort    - specify sort rule
 
-    def initialize keyword, page=nil
+    def initialize keyword, page=nil, sort=nil
       @keyword = keyword
       @page    = page if not page == nil
+      @sort    = sort if not sort == nil
     end
 
     # Get search result from youtube by specified keyword.
     def open
       @url = @@youtube_search_base_url + CGI.escape(@keyword)
       @url += "&page=#{@page}" if not @page == nil
+      @url += "&search_sort=#{@sort}" if not @sort == nil
       @html = Kernel.open(@url).read
       replace_document_write_javascript
       @search_result = Hpricot.parse(@html)
@@ -106,6 +115,7 @@ module Youtube #:nodoc:
         video.view_count     = scrape_view_count(video_html)
         video.thumbnail_url  = scrape_thumbnail_url(video_html)
         video.tags           = scrape_tags(video_html)
+        video.upload_time    = scrape_upload_time(video_html)
         video.url            = scrape_url(video_html)
 
         check_video video
@@ -189,6 +199,22 @@ module Youtube #:nodoc:
       tags.join(" ")
     end
 
+    def scrape_upload_time video_html
+      if   video_html.search("div[@class='vfacets']").inner_html =~ /.*Added:<\/span>\s*(\d+)\s*(hour|day|week|month|year).*/m
+        if $2 == "hour"
+          Time.now - $1.to_i * 60 * 60
+        elsif $2 == "day"
+          Time.now - $1.to_i * 60 * 60 * 24
+        elsif $2 == "week"
+          Time.now - $1.to_i * 60 * 60 * 24 * 7
+        elsif $2 == "month"
+          Time.now - $1.to_i * 60 * 60 * 24 * 30
+        elsif $2 == "year"
+          Time.now - $1.to_i * 60 * 60 * 24 * 30 * 12
+        end
+      end
+    end
+
     def scrape_thumbnail_url video_html
       video_html.search("img[@class='vimg120']").to_html.sub(/.*src="(.*?)".*/, '\1')
     end

data/lib/youtube/video.rb

@@ -1,6 +1,6 @@
 #--
-# Copyright (C) 2006 by in3c.org                                                                               
-# http://in3c.org/ 
+# Copyright (C) 2006 by in3c.org
+# http://in3c.org/
 #
 # Permission is hereby granted, free of charge, to any person obtaining
 # a copy of this software and associated documentation files (the
@@ -36,13 +36,14 @@ module Youtube
     attr_accessor :upload_time
     attr_accessor :comment_count
     attr_accessor :tags
+    attr_accessor :upload_time
     attr_accessor :url
     attr_accessor :thumbnail_url
 
     # Return self information as XML format.
     def to_xml
       xml = "<video>\n"
-      instance_variables.each do |attr| 
+      instance_variables.each do |attr|
         value = instance_variable_get(attr).to_s
         value.gsub!(/<br \/>/, "\n")
         value.gsub!(/<.*?>/m, '')

metadata

@@ -3,8 +3,8 @@ rubygems_version: 0.9.0
 specification_version: 1
 name: youtubescraper
 version: !ruby/object:Gem::Version 
-  version: 0.0.8
-date: 2007-03-29 00:00:00 +09:00
+  version: 0.0.9
+date: 2007-03-30 00:00:00 +09:00
 summary: This gem provide function to scrape html of search result on youtube
 require_paths: 
 - lib
@@ -35,7 +35,6 @@ files:
 - lib/youtube/searchresultscraper.rb
 - test/youtube_scraper_test.rb
 - test/html
-- test/youtube_scraper_test.rb~
 - test/html/scraping_error.html
 - test/html/dataY_noMsgY.htm
 - test/html/dataN_noMsgN.htm

data/test/youtube_scraper_test.rb~

@@ -1,92 +0,0 @@
-#!/usr/bin/ruby
-
-#require "runit/testcase"
-#require "runit/cui/testrunner"
-require 'test/unit'
-
-
-require "rubygems"
-require 'hpricot'
-require "youtube/searchresultscraper"
-
-class SearchResultScraperTest < Test::Unit::TestCase
-#class SearchResultScraperTest < RUNIT::TestCase
-
-  def test_scrape
-
-    #
-    #�����
-    #
-    #������̤�����
-    open_and_scrape("http://www.youtube.com/results?search_query=", "doraemon", 2)
-    #������̤��ʤ�
-    open_and_scrape("http://www.youtube.com/results?search_query=", "aeudyr jahafudfhadf ahf", 2) 
-
-    #
-    #�۾��
-    #
-    #������̤����뤬��Not Found��������
-    begin 
-      open_local_file_and_scrape("html/dataY_noMsgY.htm")
-      assert_fail("������٤����顼��ȯ�����Ƥ��ʤ�")
-    rescue RuntimeError =>e
-      #puts e
-    end
-    #������̤��ʤ���Not Found��ʤ����
-    begin
-      open_local_file_and_scrape("html/dataN_noMsgN.htm")
-      assert_fail("������٤����顼��ȯ�����Ƥ��ʤ�")
-    rescue RuntimeError
-      #puts e
-    end
- 
-    #�����ι��ܤ��������Ǥ��Ƥ��ʤ����
-    begin
-      open_local_file_and_scrape("html/scraping_error.html")
-      assert_fail("������٤����顼��ȯ�����Ƥ��ʤ�")
-    rescue RuntimeError => e
-     # puts e
-    end
-  end
-
-  def test_scrape_video_count
-    
-    scraper = open_and_scrape("http://www.youtube.com/results?search_query=", "doraemon", 2)
-    puts scraper.video_count
-    assert( scraper.video_count > 0 )
-    
-    scraper = open_and_scrape("http://www.youtube.com/results?search_query=", "doraemonifdadfa", 2)
-    puts scraper.video_count
-    assert( scraper.video_count == 0 )
-  end
-
-  def open_and_scrape url, keyword=nil, page=nil
-    scraper = MySearchResultScraper.new(url, keyword, page)
-    scraper.open
-    scraper.scrape
-    scraper
-  end
-
-  def open_local_file_and_scrape url
-    scraper = MySearchResultScraper.new(url)
-    scraper.open_local_file
-    scraper.scrape
-  end
-
-end
-
-class MySearchResultScraper  < Youtube::SearchResultScraper
-   @@youtube_search_base_url = "http://www.youtube.com/results?search_query="
-
-  def initialize url, keyword=nil, page=nil
-    @@youtube_search_base_url = url
-    @keyword = keyword
-    @page    = page if not page == nil
-  end
-
-  def open_local_file
-    @html = Kernel.open(@@youtube_search_base_url).read
-    replace_document_write_javascript
-    @search_result = Hpricot.parse(@html)
-  end
-end