weboob-devel/modules/youjizz/pages/video.py
2014-03-13 21:27:59 +01:00

69 lines
2.5 KiB
Python

# -*- coding: utf-8 -*-
# Copyright(C) 2010-2014 Roger Philibert
#
# This file is part of weboob.
#
# weboob is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# weboob is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
import datetime
import re
from weboob.tools.browser2 import HTMLPage
from weboob.tools.browser2.page import method, ItemElement
from weboob.tools.browser2.filters import CleanText, Env
from weboob.capabilities.base import NotAvailable
from weboob.capabilities.video import BaseVideo
from weboob.tools.misc import to_unicode
__all__ = ['VideoPage']
class VideoPage(HTMLPage):
@method
class get_video(ItemElement):
klass = BaseVideo
obj_id = Env('id')
obj_title = CleanText('//title')
obj_nsfw = True
obj_ext = u'flv'
def obj_duration(self):
# youjizz HTML is crap, we must parse it with regexps
m = re.search(r'<strong>.*?Runtime.*?</strong> (.+?)</div>', self.page.response.text)
if m:
txt = m.group(1).strip()
if txt == 'Unknown':
return NotAvailable
else:
minutes, seconds = (int(v) for v in to_unicode(txt).split(':'))
return datetime.timedelta(minutes=minutes, seconds=seconds)
else:
raise ValueError('Unable to retrieve video duration')
def obj_url(self):
real_id = int(self.env['id'].split('-')[-1])
response = self.page.browser.open('http://www.youjizz.com/videos/embed/%s' % real_id)
data = response.text
video_file_urls = re.findall(r'"(http://[^",]+\.youjizz\.com[^",]+\.flv(?:\?[^"]*)?)"', data)
if len(video_file_urls) == 0:
raise ValueError('Video URL not found')
elif len(video_file_urls) > 1:
raise ValueError('Many video file URL found')
else:
return to_unicode(video_file_urls[0])