Created
June 12, 2011 13:13
-
-
Save serghost/1021539 to your computer and use it in GitHub Desktop.
wikiheroes
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require 'nokogiri' | |
require 'open-uri' | |
i = 0 | |
heroes = [] | |
descriptions = [] | |
image_urls = [] | |
puts "Parsing..." | |
while i+=1 | |
@doc = Nokogiri::HTML.parse(open("http://www.topnews.ru/photo_id_5341_#{i}.html")) | |
name = (@doc/"p"/"b").find_all {|name| name.text[/^\d+\..*\)$/]}.map {|name| name.text.match(/^\d+\.\s+([^\s]+\s[^\s]+)/)[1]} | |
description = (@doc/"div.pvtElement"/"p._ga1_on_").map {|desc| desc.text}.join("\n") | |
descriptions << description | |
image_url = (@doc.xpath('//*[(@class = "pvtPic")]//img')).map {|img| img['src']}.join("\n") | |
image_urls << image_url | |
unless name.empty? | |
heroes += name | |
puts "find: #{name.join(", ")}" | |
end | |
if (@doc/"a.pvtNext").length == 0 | |
puts "\nLast page: #{i}" | |
break | |
end | |
end | |
puts "\nHeroes: #{heroes.compact.uniq.join(", ")}" | |
puts "\nDescriptions: #{descriptions.join(", ")}" | |
puts "\nImages: #{image_urls.join(", ")}" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment