nojhan/weboob-devel
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[piratebay] ok without descriptions

Browse source
This commit is contained in:
Julien Veyssier 2010-11-27 00:22:44 +01:00
commit 0fef303764
2 changed files with 17 additions and 74 deletions
Download patch file Download diff file Expand all files Collapse all files

1
weboob/backends/piratebay/browser.py
View file

@ -66,7 +66,6 @@ class PiratebayBrowser(BaseBrowser):
return self.page.iter_torrents() return self.page.iter_torrents()
def get_torrent(self, id): def get_torrent(self, id):
print 'goto:'+id
self.location('https://thepiratebay.org/torrent/%s/' % id) self.location('https://thepiratebay.org/torrent/%s/' % id)
assert self.is_on_page(TorrentPage) assert self.is_on_page(TorrentPage)

90
weboob/backends/piratebay/pages/torrents.py
View file

@ -58,9 +58,7 @@ class TorrentsPage(BasePage):
size = td.find('font').text.split(',')[1] size = td.find('font').text.split(',')[1]
size = size.split(' ')[2] size = size.split(' ')[2]
u = size[-3:].replace('i','') u = size[-3:].replace('i','')
print "u:"+u
size = size[:-3] size = size[:-3]
print 'size:'+size
seed = tr.getchildren()[2].text seed = tr.getchildren()[2].text
leech = tr.getchildren()[3].text leech = tr.getchildren()[3].text
@ -75,77 +73,23 @@ class TorrentsPage(BasePage):
class TorrentPage(BasePage): class TorrentPage(BasePage):
def get_torrent(self, id): def get_torrent(self, id):
table = self.document.getroot().cssselect('div.thin') for div in self.document.getiterator('div'):
if not table: if div.attrib.get('id','') == 'title':
warning('No div.thin found') title = div.text
return None elif div.attrib.get('class','') == 'download':
url = div.getchildren()[0].attrib.get('href','')
h2 = table[0].find('h2') elif div.attrib.get('id','') == 'details':
title = h2.text or '' size = float(div.getchildren()[0].getchildren()[5].text.split('(')[1].split('Bytes')[0])
if h2.find('a') != None: seed = div.getchildren()[0].getchildren()[24].text
title += h2.find('a').text + h2.find('a').tail leech = div.getchildren()[0].getchildren()[26].text
elif div.attrib.get('class','') == 'nfo':
description = div.getchildren()[0].text
torrent = Torrent(id, title) torrent = Torrent(id, title)
table = self.document.getroot().cssselect('table.torrent_table') torrent.url = url
if not table: torrent.size = size
warning('No table found') torrent.seeders = int(seed)
return None torrent.leechers = int(leech)
torrent.description = description
for tr in table[0].findall('tr'): torrent.files = ['NYI']
if tr.attrib.get('class', '').startswith('group_torrent'):
tds = tr.findall('td')
if not len(tds) == 5:
continue
url = tds[0].find('span').find('a').attrib['href']
id = self.TORRENTID_REGEXP.match(url)
if not id:
warning('ID not found')
continue
id = id.group(1)
if id != torrent.id:
continue
torrent.url = self.format_url(url)
torrent.size = self.unit(*tds[1].text.split())
torrent.seeders = int(tds[3].text)
torrent.leechers = int(tds[4].text)
break
if not torrent.url:
warning('Torrent %d not found in list' % torrent.id)
return None
div = self.document.getroot().cssselect('div.main_column')
if not div:
warning('WTF')
return None
for box in div[0].cssselect('div.box'):
title = None
body = None
title_t = box.cssselect('div.head')
if title_t:
title = title_t[0].find('strong').text.strip()
body_t = box.cssselect('div.body')
if body_t:
body = html2text(self.browser.parser.tostring(body_t[0])).strip()
if title and body:
if torrent.description is NotLoaded:
torrent.description = u''
torrent.description += u'%s\n\n%s\n' % (title, body)
div = self.document.getroot().cssselect('div#files_%s' % torrent.id)
if div:
torrent.files = []
for tr in div[0].find('table'):
if tr.attrib.get('class', None) != 'colhead_dark':
torrent.files.append(tr.find('td').text)
return torrent return torrent