b55d83e6ab
A resubmit of the previous one, this time with understandable name. Copied the original submission text. This is a simple backend for btdigg.org. This site is especially interesting because it is not an indexer where uploaders add their torrents; it crawls the DHT and listens to all infohashes being exchanged by the nodes. Because of this, btdigg.org provides no description and no torrent files, only magnets. Moreover, there are no seeders and leechers (although there is the number of peers in the swarms) Note that there is no icon. Signed-off-by: Matthieu Rakotojaona <matthieu.rakotojaona@gmail.com> Signed-off-by: Romain Bignon <romain@symlink.me>
102 lines
3.3 KiB
Python
102 lines
3.3 KiB
Python
# -*- coding: utf-8 -*-
|
|
|
|
from datetime import datetime, timedelta
|
|
from urlparse import urlparse, parse_qs
|
|
|
|
from weboob.tools.browser import BasePage,BrokenPageError
|
|
from weboob.capabilities.torrent import Torrent, MagnetOnly
|
|
from weboob.capabilities.base import NotAvailable
|
|
|
|
__all__ = ['TorrentsPage', 'TorrentPage']
|
|
|
|
def fullsize(n, u):
|
|
m = {'B': 1,
|
|
'KB': 1024,
|
|
'MB': 1024 * 1024,
|
|
'GB': 1024 * 1024 * 1024,
|
|
'TB': 1024 * 1024 * 1024 * 1024,
|
|
}
|
|
return float(n * m[u])
|
|
|
|
class TorrentsPage(BasePage):
|
|
|
|
def iter_torrents(self):
|
|
try:
|
|
table = self.document.getroot().cssselect('table.torrent_name_tbl')
|
|
except BrokenPageError:
|
|
return
|
|
for i in range(0, len(table), 2):
|
|
# Title
|
|
title = table[i].cssselect('td.torrent_name a')[0]
|
|
name = unicode(title.text)
|
|
url = unicode(title.attrib['href'])
|
|
|
|
# Other elems
|
|
elems = table[i+1].cssselect('td')
|
|
|
|
magnet = unicode(elems[0].cssselect('a')[0].attrib['href'])
|
|
|
|
query = urlparse(magnet).query # xt=urn:btih:<...>&dn=<...>
|
|
btih = parse_qs(query)['xt'][0] # urn:btih:<...>
|
|
ih = btih.split(':')[-1]
|
|
|
|
value, unit = elems[2].cssselect('span.attr_val')[0].text.split()
|
|
|
|
valueago, valueunit, _ = elems[5].cssselect('span.attr_val')[0].text.split()
|
|
delta = timedelta(**{valueunit: float(valueago)})
|
|
date = datetime.now() - delta
|
|
|
|
url = unicode('https://btdigg.org/search?info_hash=%s' % ih)
|
|
|
|
torrent = Torrent(ih, name)
|
|
torrent.url = url
|
|
torrent.size = fullsize(float(value), unit)
|
|
torrent.magnet = magnet
|
|
torrent.seeders = NotAvailable
|
|
torrent.leechers = NotAvailable
|
|
torrent.description = NotAvailable
|
|
torrent.files = NotAvailable
|
|
torrent.date = date
|
|
yield torrent
|
|
|
|
class TorrentPage(BasePage):
|
|
def get_torrent(self, id):
|
|
trs = self.document.getroot().cssselect('table.torrent_info_tbl tr')
|
|
|
|
# magnet
|
|
download = trs[2].cssselect('td a')[0]
|
|
if download.attrib['href'].startswith('magnet:'):
|
|
magnet = unicode(download.attrib['href'])
|
|
|
|
query = urlparse(magnet).query # xt=urn:btih:<...>&dn=<...>
|
|
btih = parse_qs(query)['xt'][0] # urn:btih:<...>
|
|
ih = btih.split(':')[-1]
|
|
|
|
name = unicode(trs[3].cssselect('td')[1].text)
|
|
|
|
value, unit = trs[5].cssselect('td')[1].text.split()
|
|
|
|
valueago, valueunit, _ = trs[6].cssselect('td')[1].text.split()
|
|
delta = timedelta(**{valueunit: float(valueago)})
|
|
date = datetime.now() - delta
|
|
|
|
|
|
files = []
|
|
for tr in trs[15:]:
|
|
files.append(unicode(tr.cssselect('td')[1].text))
|
|
|
|
torrent = Torrent(ih, name)
|
|
torrent.url = unicode(self.url)
|
|
torrent.size = fullsize(float(value), unit)
|
|
torrent.magnet = magnet
|
|
torrent.seeders = NotAvailable
|
|
torrent.leechers = NotAvailable
|
|
torrent.description = NotAvailable
|
|
torrent.files = files
|
|
torrent.filename = NotAvailable
|
|
torrent.date = date
|
|
|
|
return torrent
|
|
|
|
def get_torrent_file(self, id):
|
|
raise MagnetOnly(self.get_torrent(id).magnet)
|