support repositories to manage backends (closes #747)
This commit is contained in:
parent
ef16a5b726
commit
14a7a1d362
410 changed files with 1079 additions and 297 deletions
65
modules/ina/pages/search.py
Normal file
65
modules/ina/pages/search.py
Normal file
|
|
@ -0,0 +1,65 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright(C) 2010-2011 Romain Bignon
|
||||
#
|
||||
# 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.browser import BasePage
|
||||
from weboob.tools.browser import BrokenPageError
|
||||
|
||||
from ..video import InaVideo
|
||||
|
||||
|
||||
__all__ = ['SearchPage']
|
||||
|
||||
|
||||
class SearchPage(BasePage):
|
||||
URL_REGEXP = re.compile(r'/video/(.+)\.html')
|
||||
|
||||
def iter_videos(self):
|
||||
try:
|
||||
ul = self.parser.select(self.document.getroot(), 'div.container-videos ul', 1)
|
||||
except BrokenPageError:
|
||||
# It means there are no results.
|
||||
return
|
||||
for li in ul.findall('li'):
|
||||
id = re.sub(self.URL_REGEXP, r'\1', li.find('a').attrib['href'])
|
||||
|
||||
thumbnail = 'http://boutique.ina.fr%s' % li.find('a').find('img').attrib['src']
|
||||
|
||||
title = self.parser.select(li, 'p.titre', 1).text
|
||||
|
||||
date = self.parser.select(li, 'p.date', 1).text
|
||||
day, month, year = [int(s) for s in date.split('/')]
|
||||
date = datetime.datetime(year, month, day)
|
||||
|
||||
duration = self.parser.select(li, 'p.duree', 1).text
|
||||
m = re.match(r'((\d+)h)?((\d+)min)?(\d+)s', duration)
|
||||
if m:
|
||||
duration = datetime.timedelta(hours=int(m.group(2) or 0), minutes=int(m.group(4) or 0), seconds=int(m.group(5)))
|
||||
else:
|
||||
raise BrokenPageError('Unable to match duration (%r)' % duration)
|
||||
|
||||
yield InaVideo('boutique.%s' % id,
|
||||
title=title,
|
||||
date=date,
|
||||
duration=duration,
|
||||
thumbnail_url=thumbnail,
|
||||
)
|
||||
Loading…
Add table
Add a link
Reference in a new issue