youtubesearchresultscraper 0.0.1

data/CHANGELOG

@@ -0,0 +1,3 @@
+*0.1.0*
+
+* First public release

data/MIT-LICENSE

@@ -0,0 +1,20 @@
+Copyright (C) 2006 by in3c.org                                                                               
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README

@@ -0,0 +1,13 @@
+YouTubeの検索結果のHTMLをスクレイピングして、YouTube Developer APIのyoutube.videos.list_by_tagと同様な形式のXMLを返すライブラリです。
+
+使用例: 
+8< - - - - 8< - - - - 8< - - - - 8< - - - - 
+require "youtube/searchresultscraper"
+
+scraper = Youtube::SearchResultScraper.new(keyword, page)
+scraper.open
+scraper.scrape
+puts scraper.get_xml
+8< - - - - 8< - - - - 8< - - - - 8< - - - - 
+
+参考) http://www.ark-web.jp/sandbox/wiki/183.html

data/lib/youtube/searchresultscraper.rb

@@ -0,0 +1,137 @@
+# Copyright (C) 2006 by in3c.org                                                                               
+#
+# Permission is hereby granted, free of charge, to any person obtaining
+# a copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of the Software, and to
+# permit persons to whom the Software is furnished to do so, subject to
+# the following conditions:
+#
+# The above copyright notice and this permission notice shall be
+# included in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+# LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+# OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+# WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+require 'open-uri'
+require 'cgi'
+require 'rubygems'
+require 'hpricot'
+require 'youtube/video'
+
+module Youtube
+  class SearchResultScraper
+
+    attr_accessor :keyword
+    attr_accessor :page
+
+    @@youtube_search_base_url = "http://www.youtube.com/results?search_query="
+
+    def initialize keyword, page=nil
+      @keyword = keyword
+      @page    = page if not page == nil
+    end
+
+    def open
+      url = @@youtube_search_base_url + CGI.escape(@keyword)
+      url += "&page=#{@page}" if not @page == nil
+      @html = Kernel.open(url).read
+      replace_document_write_javascript
+      @search_result = Hpricot.parse(@html)
+    end
+
+    def scrape
+      @videos = []
+
+      @search_result.search("//div[@class='vEntry']").each do |video_html|
+        video = Youtube::Video.new
+        video.id             = scrape_id(video_html)
+        video.author         = scrape_author(video_html)
+        video.title          = scrape_title(video_html)
+        video.length_seconds = scrape_length_seconds(video_html)
+        video.rating_avg     = scrape_rating_avg(video_html)
+        video.rating_count   = scrape_rating_count(video_html)
+        video.description    = scrape_description(video_html)
+        video.view_count     = scrape_view_count(video_html)
+        video.thumbnail_url  = scrape_thumbnail_url(video_html)
+        video.tags           = scrape_tags(video_html)
+        video.url            = scrape_url(video_html)
+        @videos << video
+      end
+    end
+
+    def get_xml
+      xml = "<ut_response status=\"ok\"><video_list>\n"
+      @videos.each do |video|
+        xml += video.to_xml
+      end
+      xml += "</video_list></ut_response>"
+    end
+
+    private
+
+    def replace_document_write_javascript
+      @html.gsub!(%r{<script language="javascript" type="text/javascript">.*?document.write\('(.*?)'\).*?</script>}m, '\1')
+    end
+
+    def scrape_id video_html
+      scrape_thumbnail_url(video_html).sub(%r{.*/([^/]+)/[^/]+.jpg}, '\1')
+    end
+
+    def scrape_author video_html
+      video_html.search("div[@class='vfacets']").inner_html.sub(/.*From:<\/span> <a.*?>(.*?)<\/a>.*/m, '\1')
+    end
+
+
+    def scrape_title video_html
+      video_html.search("div[@class='vtitle']/a").inner_html
+    end
+
+    def scrape_length_seconds video_html
+      length_seconds = video_html.search("span[@class='runtime']").inner_html
+      length_seconds =~ /(\d\d):(\d\d)/
+      $1.to_i * 60 + $2.to_i
+    end
+
+    def scrape_rating_avg video_html
+      video_html.search("img[@src='/img/star_sm.gif']").size +
+        video_html.search("img[@src='/img/star_sm_half.gif']").size * 0.5
+    end
+
+    def scrape_rating_count video_html
+      video_html.search("div[@class='rating']").inner_html.sub(/(\d+) rating/, '\1').to_i
+    end
+
+    def scrape_description video_html
+      description = video_html.search("div[@class='vdesc']/span").inner_html.sub(/^\n\t(.*?)\n\t$/m, '\1')
+    end
+
+    def scrape_view_count video_html
+      video_html.search("div[@class='vfacets']").inner_html.sub(/.*Views:<\/span> (\d+).*/m, '\1').to_i
+    end
+
+    def scrape_tags video_html
+      tags = []
+      video_html.search("div[@class='vtagValue']/a").each do |tag|
+        tags << tag.inner_html
+      end
+      tags.join(" ")
+    end
+
+    def scrape_thumbnail_url video_html
+      video_html.search("img[@class='vimg120']").to_html.sub(/.*src="(.*?)".*/, '\1')
+    end
+
+    def scrape_url video_html
+      "http://www.youtube.com" +
+        video_html.search("div[@class='vtitle']/a").to_html.sub(/.*href="(.*?)".*/m, '\1')
+    end
+  end
+
+end

data/lib/youtube/video.rb

@@ -0,0 +1,59 @@
+# 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
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of the Software, and to
+# permit persons to whom the Software is furnished to do so, subject to
+# the following conditions:
+#
+# The above copyright notice and this permission notice shall be
+# included in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+# LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+# OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+# WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+module Youtube
+
+  class Video
+    attr_accessor :author
+    attr_accessor :id
+    attr_accessor :title
+    attr_accessor :length_seconds
+    attr_accessor :rating_avg
+    attr_accessor :rating_count
+    attr_accessor :description
+    attr_accessor :view_count
+    attr_accessor :upload_time
+    attr_accessor :comment_count
+    attr_accessor :tags
+    attr_accessor :url
+    attr_accessor :thumbnail_url
+
+    def to_xml
+      xml = "<video>\n"
+      instance_variables.each do |attr| 
+        value = instance_variable_get(attr).to_s
+        value.gsub!(/<br \/>/, "\n")
+        value.gsub!(/<.*?>/m, '')
+        value.gsub!(/&/m, '&amp;')
+        value.gsub!(/'/m, '&apos;')
+        value.gsub!(/"/m, '&quot;')
+        value.gsub!(/</m, '&lt;')
+        value.gsub!(/>/m, '&gt;')
+        attr.sub!(/@/, '')
+        xml += "<#{attr}>#{value}</#{attr}>\n"
+      end
+      xml += "</video>\n"
+    end
+  end
+
+end
+

metadata

@@ -0,0 +1,61 @@
+--- !ruby/object:Gem::Specification 
+rubygems_version: 0.9.0
+specification_version: 1
+name: youtubesearchresultscraper
+version: !ruby/object:Gem::Version 
+  version: 0.0.1
+date: 2006-11-26 00:00:00 +09:00
+summary: This gem provide function to scrape html of search result on youtube
+require_paths: 
+- lib
+email: 
+homepage: 
+rubyforge_project: 
+description: 
+autorequire: youtube/searchresultscraper
+default_executable: 
+bindir: bin
+has_rdoc: false
+required_ruby_version: !ruby/object:Gem::Version::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: 1.8.1
+  version: 
+platform: ruby
+signing_key: 
+cert_chain: 
+post_install_message: 
+authors: 
+- Yuki SHIDA
+files: 
+- lib/youtube
+- lib/youtube/video.rb
+- lib/youtube/searchresultscraper.rb
+- CHANGELOG
+- MIT-LICENSE
+- README
+test_files: []
+
+rdoc_options: []
+
+extra_rdoc_files: 
+- CHANGELOG
+- MIT-LICENSE
+- README
+executables: []
+
+extensions: []
+
+requirements: 
+- hpricot rubygem
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: hpricot
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Version::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0.4"
+    version: