support repositories to manage backends (closes #747)
This commit is contained in:
Romain Bignon
parent
ef16a5b726
commit
14a7a1d362
410 changed files with 1079 additions and 297 deletions
0
modules/youporn/pages/__init__.py
Normal file
0
modules/youporn/pages/__init__.py
Normal file
37
modules/youporn/pages/base.py
Normal file
37
modules/youporn/pages/base.py
Normal file
|
|
@ -0,0 +1,37 @@
|
|||
# -*- 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/>.
|
||||
|
||||
from weboob.tools.mech import ClientForm
|
||||
ControlNotFoundError = ClientForm.ControlNotFoundError
|
||||
|
||||
from mechanize import FormNotFoundError
|
||||
from weboob.tools.browser import BasePage
|
||||
|
||||
|
||||
__all__ = ['PornPage']
|
||||
|
||||
|
||||
class PornPage(BasePage):
|
||||
def on_loaded(self):
|
||||
try:
|
||||
self.browser.select_form(nr=0)
|
||||
self.browser.submit(name='user_choice')
|
||||
return False
|
||||
except (ControlNotFoundError, FormNotFoundError):
|
||||
return True
|
||||
75
modules/youporn/pages/index.py
Normal file
75
modules/youporn/pages/index.py
Normal file
|
|
@ -0,0 +1,75 @@
|
|||
# -*- 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
|
||||
|
||||
from .base import PornPage
|
||||
from ..video import YoupornVideo
|
||||
|
||||
|
||||
__all__ = ['IndexPage']
|
||||
|
||||
|
||||
class IndexPage(PornPage):
|
||||
def iter_videos(self):
|
||||
uls = self.document.getroot().cssselect("ul[class=clearfix]")
|
||||
if not uls:
|
||||
return
|
||||
|
||||
for ul in uls:
|
||||
for li in ul.findall('li'):
|
||||
a = li.find('a')
|
||||
if a is None or a.find('img') is None:
|
||||
continue
|
||||
|
||||
thumbnail_url = a.find('img').attrib['src']
|
||||
|
||||
h1 = li.find('h1')
|
||||
a = h1.find('a')
|
||||
if a is None:
|
||||
continue
|
||||
|
||||
url = a.attrib['href']
|
||||
_id = url[len('/watch/'):]
|
||||
_id = _id[:_id.find('/')]
|
||||
title = a.text.strip()
|
||||
|
||||
minutes = seconds = 0
|
||||
div = li.cssselect('div[class=duration_views]')
|
||||
if div:
|
||||
h2 = div[0].find('h2')
|
||||
minutes = int(h2.text.strip())
|
||||
seconds = int(h2.find('span').tail.strip())
|
||||
|
||||
rating = 0
|
||||
rating_max = 0
|
||||
div = li.cssselect('div[class=rating]')
|
||||
if div:
|
||||
p = div[0].find('p')
|
||||
rating = float(p.text.strip())
|
||||
rating_max = float(p.find('span').text.strip()[2:])
|
||||
|
||||
yield YoupornVideo(int(_id),
|
||||
title=title,
|
||||
rating=rating,
|
||||
rating_max=rating_max,
|
||||
duration=datetime.timedelta(minutes=minutes, seconds=seconds),
|
||||
thumbnail_url=thumbnail_url,
|
||||
)
|
||||
94
modules/youporn/pages/video.py
Normal file
94
modules/youporn/pages/video.py
Normal file
|
|
@ -0,0 +1,94 @@
|
|||
# -*- 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 re
|
||||
import datetime
|
||||
|
||||
|
||||
|
||||
from .base import PornPage
|
||||
from ..video import YoupornVideo
|
||||
|
||||
|
||||
class VideoPage(PornPage):
|
||||
def get_video(self, video=None):
|
||||
if not PornPage.on_loaded(self):
|
||||
return
|
||||
if video is None:
|
||||
video = YoupornVideo(self.group_dict['id'])
|
||||
video.title = self.get_title()
|
||||
video.url, video.ext = self.get_url()
|
||||
self.set_details(video)
|
||||
return video
|
||||
|
||||
def get_url(self):
|
||||
download_div = self.parser.select(self.document.getroot(), '#download', 1)
|
||||
a = self.parser.select(download_div, 'a', 1)
|
||||
m = re.match('^(\w+) - .*', a.text)
|
||||
if m:
|
||||
ext = m.group(1).lower()
|
||||
else:
|
||||
ext = 'flv'
|
||||
return a.attrib['href'], ext
|
||||
|
||||
def get_title(self):
|
||||
element = self.parser.select(self.document.getroot(), '#videoArea h1', 1)
|
||||
return unicode(element.getchildren()[0].tail).strip()
|
||||
|
||||
DATE_REGEXP = re.compile("\w+ (\w+) (\d+) (\d+):(\d+):(\d+) (\d+)")
|
||||
MONTH2I = ['', 'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']
|
||||
|
||||
def set_details(self, v):
|
||||
details_div = self.parser.select(self.document.getroot(), '#details', 1)
|
||||
for li in details_div.getiterator('li'):
|
||||
span = li.find('span')
|
||||
name = span.text.strip()
|
||||
value = span.tail.strip()
|
||||
|
||||
if name == 'Duration:':
|
||||
seconds = minutes = 0
|
||||
for word in value.split():
|
||||
if word.endswith('min'):
|
||||
minutes = int(word[:word.find('min')])
|
||||
elif word.endswith('sec'):
|
||||
seconds = int(word[:word.find('sec')])
|
||||
v.duration = datetime.timedelta(minutes=minutes, seconds=seconds)
|
||||
elif name == 'Submitted:':
|
||||
author = li.find('i')
|
||||
if author is None:
|
||||
author = li.find('a')
|
||||
if author is None:
|
||||
v.author = value
|
||||
else:
|
||||
v.author = author.text
|
||||
elif name == 'Rating:':
|
||||
r = value.split()
|
||||
v.rating = float(r[0])
|
||||
v.rating_max = float(r[2])
|
||||
elif name == 'Date:':
|
||||
m = self.DATE_REGEXP.match(value)
|
||||
if m:
|
||||
month = self.MONTH2I.index(m.group(1))
|
||||
day = int(m.group(2))
|
||||
hour = int(m.group(3))
|
||||
minute = int(m.group(4))
|
||||
second = int(m.group(5))
|
||||
year = int(m.group(6))
|
||||
v.date = datetime.datetime(year, month, day, hour, minute, second)
|
||||
Loading…
Add table
Add a link
Reference in a new issue