Last active
October 14, 2016 10:29
-
-
Save affix/da98f6f72c2abaddd6add8aa99f33be4 to your computer and use it in GitHub Desktop.
A simple Pirate Bay Scraper that only scrapes a single page
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
#!/usr/bin/env ruby | |
# Simple Pirate Bay Parser | |
# Checks the results page and lists torrents and info | |
# Also gives Magnet link | |
# (c) 2016 Keiran Smith | |
# Licensed under gnu/gplv3 | |
require 'nokogiri' | |
require 'open-uri' | |
root_url = "https://piratebaymirror.eu" | |
html = open("#{root_url}/recent") | |
doc = Nokogiri::HTML(html) | |
doc.encoding = 'utf-8' | |
rows = doc.xpath('//table[@id="searchResult"]/tr') | |
def sanitize(data) | |
data.gsub("Details for ", "") | |
end | |
start = 0 | |
rows.each do |row| | |
dataset = row.xpath('//tr/td/div[@class="detName"]') | |
dataset.each do | data | | |
link = data.css('a').first | |
if link | |
puts "#{link.content} :: #{link["href"]}" | |
page = nil | |
begin | |
page = open("#{root_url}#{link["href"]}") | |
rescue URI::InvalidURIError | |
# URI Had an invalid char, Trying alternate, slow method | |
split = link["href"].split('/') | |
link = "/#{split[1]}/#{split[2]}" | |
page = open("#{root_url}#{link}") | |
end | |
pdoc = Nokogiri::HTML(page) | |
pdoc.encoding = 'utf-8' | |
c1 = pdoc.xpath('//dl[@class="col1"]/dd') | |
puts "Category : #{c1[0].content}" | |
puts "Size : #{c1[2].content}" | |
nfo = pdoc.xpath('//div[@class="nfo"]/pre') | |
puts nfo.first.content | |
magnet = pdoc.xpath('//div[@class="download"]') | |
mlink = magnet.css('a').first | |
puts "Magnet Link : #{mlink["href"]}" | |
puts "--" | |
start += 3 | |
end | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment