Created
February 14, 2015 14:49
-
-
Save RX14/929ea1016152ddda4b43 to your computer and use it in GitHub Desktop.
This file contains hidden or 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 "bundler" | |
require "open-uri" | |
require "json" | |
require "benchmark" | |
Bundler.require | |
def parse_link_xml(link_xml) | |
link = {} | |
link[:type] = link_xml.text | |
link[:link] = link_xml["href"] | |
link | |
end | |
def parse_resolution_xml(res_xml) | |
res = {} | |
res[:resolution] = res_xml.at_css('a[href="#"] > text()').text | |
res[:filename] = res_xml.at_css("span.dl-label").text | |
res[:links] = res_xml.css("span.ind-link > a").map(&method(:parse_link_xml)) | |
res | |
end | |
def parse_episode(episode_xml) | |
episode = {} | |
match = /^\(.+?\) (.*) - (\d*)$/.match(episode_xml.at_css("text()").text) | |
episode[:show] = match[1] | |
episode[:ep_num] = match[2].to_i | |
episode[:id] = episode_xml["id"] | |
episode[:resolutions] = episode_xml.css("div.resolution-block.linkful").map(&method(:parse_resolution_xml)) | |
episode | |
end | |
doc = Nokogiri::HTML(open("http://horriblesubs.info/lib/latest.php")) | |
episodes = doc.css("div.episode").map(&method(:parse_episode)) | |
puts JSON.pretty_generate(episodes) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment