Last active
July 1, 2022 15:07
-
-
Save agarie/5386009 to your computer and use it in GitHub Desktop.
Utility to download torrent files from tokyotosho.info. It uses a similar heuristic to my own when looking for torrents, but could use some improvements.
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
#!/usr/bin/env ruby -w | |
require 'open-uri' | |
require 'uri' | |
require 'nokogiri' | |
DEFAULT_DIR = "/Users/carlosagarie/torrents" | |
CATEGORY = 1 # Anime. | |
# Regular expressions and constants for extraction. | |
RELEVANT_ENTRIES = "table.listing > tr.category_#{CATEGORY}" | |
MIME_TYPE = "application/x-bittorrent" | |
SIZE_RE = /Size:\s*([\d.]+)(?:K|M|G)B/ | |
STATS_RE = /^S:\s*(\d+)\s*L:\s*(\d+).*/ | |
# Class used to hold torrents. | |
Torrent = Struct.new(:name, :link, :size, :seeds, :leechers) do | |
# Similar to the heuristics I use when looking for a torrent. | |
def <=>(other) | |
if self.seeds > 10 || other.seeds > 10 | |
other.seeds <=> self.seeds | |
else | |
other.leechers <=> self.leechers | |
end | |
end | |
def to_s | |
puts name | |
puts "Size: #{size} | Seeds: #{seeds} | Leechers: #{leechers}" | |
puts link | |
end | |
end | |
def address(terms, type = CATEGORY) | |
base_url = "http://tokyotosho.info/search.php?size_min=&size_max=&username=" | |
"#{base_url}&terms=#{terms.split(' ').join('+')}&type=#{type}" | |
end | |
url = address(ARGV[0]) | |
page = Nokogiri::HTML(open(url)) | |
# Get the torrent URLs from the main page. Yeah, tokyotosho.info HTML sucks. | |
results = [] | |
page.css(RELEVANT_ENTRIES).each_slice(2) do |e| | |
torrent = Torrent.new | |
links = e[0].css('a').select { |l| l["type"] == MIME_TYPE } | |
torrent.name = links[0].content | |
torrent.link = links[0]["href"] | |
torrent.size = e[1].css('td.desc-bot')[0].content.match(SIZE_RE)[1] | |
e[1].css('td.stats')[0].content.match(STATS_RE) do |m| | |
torrent.seeds = m[1].to_i | |
torrent.leechers = m[2].to_i | |
end | |
results << torrent | |
end | |
# Download the "best" torrent. | |
torrent = results.sort.shift | |
filename = File.join(DEFAULT_DIR, torrent.name + '.torrent') | |
File.open(filename, 'wb') do |f| | |
f << open(torrent.link).read | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment