scrapeit/scrapeit/mininova.py

49 lines
1.4 KiB
Python

# -*- Mode: Python; -*-
# -*- coding: utf-8 -*-
# vi:si:et:sw=2:sts=2:ts=2
import re
import socket
from urllib import quote
from BeautifulSoup import BeautifulSoup
from utils import read_url, read_url_utf8
from btutils import torrentsWeLike
socket.setdefaulttimeout(10.0)
def search(query, filterResult = False):
'''search for torrents on mininova
'''
torrents = []
url = "http://www.mininova.org/search/%s/seeds" % quote(query)
page = read_url(url)
soup = BeautifulSoup(page)
for row in soup('tr'):
links = row('a', {'href':re.compile('/tor')})
if links:
torrent_url = "http://www.mininova.org%s" % links[0].get('href').replace('/tor', '/get')
if filterResult:
if torrentsWeLike(links[0]):
torrents.append(torrent_url)
else:
torrents.append(torrent_url)
return torrents
def searchByImdb(imdb):
'''search for torrents on mininova by imdb
'''
torrents = []
page = read_url("http://www.mininova.org/imdb/?imdb=%s" % imdb)
soup = BeautifulSoup(page)
for row in soup('tr'):
#filter private trackers
private_tracker = row('a', {'href':re.compile('/faq/#pt')})
links = row('a', {'href':re.compile('/tor')})
if not private_tracker and links:
torrent = links[0]
if torrentsWeLike(unicode(torrent.contents[0])):
torrent_url = "http://www.mininova.org%s" % torrent.get('href').replace('/tor', '/get')
torrents.append(torrent_url)
return torrents