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

[isohunt] corrected (closes #529), the site doesn't provide seed information on info page anymore

Browse source
This commit is contained in:
Julien Veyssier 2011-02-26 12:24:41 +01:00 • committed by Romain Bignon
commit ac7274cafd
2 changed files with 17 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

4
weboob/backends/isohunt/browser.py
View file

@ -30,7 +30,7 @@ class IsohuntBrowser(BaseBrowser):
ENCODING = 'utf-8' ENCODING = 'utf-8'
USER_AGENT = BaseBrowser.USER_AGENTS['wget'] USER_AGENT = BaseBrowser.USER_AGENTS['wget']
PAGES = { PAGES = {
'https://isohunt.com/torrents/.*iht=-1&ihp=1&ihs1=2&iho1=d' : TorrentsPage, 'https://isohunt.com/torrents/.*iht=-1&ihp=1&ihs1=1&iho1=d' : TorrentsPage,
'https://isohunt.com/torrent_details.*tab=summary' : TorrentPage, 'https://isohunt.com/torrent_details.*tab=summary' : TorrentPage,
} }
@ -38,7 +38,7 @@ class IsohuntBrowser(BaseBrowser):
return self.location('https://isohunt.com') return self.location('https://isohunt.com')
def iter_torrents(self, pattern): def iter_torrents(self, pattern):
self.location('https://isohunt.com/torrents/%s?iht=-1&ihp=1&ihs1=2&iho1=d' % pattern) self.location('https://isohunt.com/torrents/%s?iht=-1&ihp=1&ihs1=1&iho1=d' % pattern)
assert self.is_on_page(TorrentsPage) assert self.is_on_page(TorrentsPage)
return self.page.iter_torrents() return self.page.iter_torrents()

29
weboob/backends/isohunt/pages/torrents.py
View file

@ -63,23 +63,23 @@ class TorrentPage(BasePage):
for a in self.document.getiterator('a'): for a in self.document.getiterator('a'):
if 'Search more torrents of' in a.attrib.get('title', ''): if 'Search more torrents of' in a.attrib.get('title', ''):
title = a.tail title = a.tail
seed = -1
leech = -1
tip_id = "none"
for span in self.document.getiterator('span'): for span in self.document.getiterator('span'):
if span.attrib.get('style', '') == 'color:green;' and ('ShowTip' in span.attrib.get('onmouseover', '')): if span.attrib.get('style', '') == 'color:green;' and ('ShowTip' in span.attrib.get('onmouseover', '')):
seed = span.tail.split(' ')[1] seed = span.tail.split(' ')[1]
tip_id = span.attrib.get('onmouseover', '').split("'")[1] tip_id = span.attrib.get('onmouseover', '').split("'")[1]
for div in self.document.getiterator('div'): for div in self.document.getiterator('div'):
# find the corresponding super tip which appears on super mouse hover! # find the corresponding super tip which appears on super mouse hover!
if div.attrib.get('class', '') == 'dirs ydsf' and tip_id in div.attrib.get('id', ''): if div.attrib.get('class', '') == 'dirs ydsf' and tip_id in div.attrib.get('id', ''):
leech = div.getchildren()[0].getchildren()[1].tail.split(' ')[2] leech = div.getchildren()[0].getchildren()[1].tail.split(' ')[2]
# the <b> with the size in it doesn't have a distinction # the <b> with the size in it doesn't have a distinction
# have to get it by higher # have to get it by higher
elif div.attrib.get('id', '') == 'torrent_details': elif div.attrib.get('id', '') == 'torrent_details':
size = div.getchildren()[6].getchildren()[0].getchildren()[0].text size = div.getchildren()[6].getchildren()[0].getchildren()[0].text
u = size[-2:] u = size[-2:]
size = float(size[:-3]) size = float(size[:-3])
# all the thing we get in that loop are unique, no need to go on looping
break
# files and description (uploader's comment) # files and description (uploader's comment)
description = 'No description' description = 'No description'
@ -89,7 +89,8 @@ class TorrentPage(BasePage):
if p.attrib.get('style', '') == 'line-height:1.2em;margin-top:1.8em': if p.attrib.get('style', '') == 'line-height:1.2em;margin-top:1.8em':
count_p_found += 1 count_p_found += 1
if count_p_found == 1: if count_p_found == 1:
description = p.getchildren()[1].tail if p.getchildren()[1].tail != None:
description = p.getchildren()[1].tail
if count_p_found == 2: if count_p_found == 2:
if p.getchildren()[0].text == 'Directory:': if p.getchildren()[0].text == 'Directory:':
files.append(p.getchildren()[0].tail.strip()+'/') files.append(p.getchildren()[0].tail.strip()+'/')