youtube-dl/youtube_dl/extractor/vimple.py

76 lines
2.3 KiB
Python
Raw Normal View History

2014-06-12 07:27:23 +00:00
# coding: utf-8
from __future__ import unicode_literals
2014-06-13 03:08:06 +00:00
import base64
2014-07-11 09:11:09 +00:00
import re
2014-06-13 03:08:06 +00:00
import xml.etree.ElementTree
2014-07-11 09:11:09 +00:00
import zlib
2014-06-12 07:27:23 +00:00
from .common import InfoExtractor
from ..utils import int_or_none
2014-06-12 07:27:23 +00:00
2014-06-13 03:08:06 +00:00
2014-06-12 07:27:23 +00:00
class VimpleIE(InfoExtractor):
IE_DESC = 'Vimple.ru'
2014-06-13 03:08:06 +00:00
_VALID_URL = r'https?://(player.vimple.ru/iframe|vimple.ru)/(?P<id>[a-f0-9]{10,})'
2014-06-12 07:27:23 +00:00
_TESTS = [
{
'url': 'http://vimple.ru/c0f6b1687dcd4000a97ebe70068039cf',
'md5': '2e750a330ed211d3fd41821c6ad9a279',
2014-06-12 07:27:23 +00:00
'info_dict': {
'id': 'c0f6b1687dcd4000a97ebe70068039cf',
2014-06-13 03:08:06 +00:00
'ext': 'mp4',
'title': 'Sunset',
'duration': 20,
'thumbnail': 're:https?://.*?\.jpg',
2014-06-13 03:08:06 +00:00
},
},
2014-06-12 07:27:23 +00:00
]
2014-06-13 03:08:06 +00:00
2014-06-12 07:27:23 +00:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
2014-06-13 03:08:06 +00:00
2014-06-12 07:27:23 +00:00
iframe_url = 'http://player.vimple.ru/iframe/%s' % video_id
2014-07-11 09:11:09 +00:00
iframe = self._download_webpage(
iframe_url, video_id,
note='Downloading iframe', errnote='unable to fetch iframe')
player_url = self._html_search_regex(
r'"(http://player.vimple.ru/flash/.+?)"', iframe, 'player url')
2014-06-13 03:08:06 +00:00
2014-07-11 09:11:09 +00:00
player = self._request_webpage(
player_url, video_id, note='Downloading swf player').read()
2014-06-12 07:27:23 +00:00
player = zlib.decompress(player[8:])
2014-06-13 02:33:50 +00:00
xml_pieces = re.findall(b'([a-zA-Z0-9 =+/]{500})', player)
2014-06-12 07:27:23 +00:00
xml_pieces = [piece[1:-1] for piece in xml_pieces]
2014-06-13 03:08:06 +00:00
2014-06-12 07:27:23 +00:00
xml_data = b''.join(xml_pieces)
xml_data = base64.b64decode(xml_data)
2014-06-13 03:08:06 +00:00
2014-06-12 07:27:23 +00:00
xml_data = xml.etree.ElementTree.fromstring(xml_data)
2014-06-13 03:08:06 +00:00
2014-06-12 07:27:23 +00:00
video = xml_data.find('Video')
quality = video.get('quality')
q_tag = video.find(quality.capitalize())
formats = [
{
'url': q_tag.get('url'),
'tbr': int(q_tag.get('bitrate')),
'filesize': int(q_tag.get('filesize')),
'format_id': quality,
},
]
return {
'id': video_id,
'title': video.find('Title').text,
'formats': formats,
'thumbnail': video.find('Poster').get('url'),
'duration': int_or_none(video.get('duration')),
2014-06-12 07:27:23 +00:00
'webpage_url': video.find('Share').get('videoPageUrl'),
}