Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vimple.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import base64
   5 import re
   6 import xml.etree.ElementTree
   7 import zlib
   8
   9 from .common import InfoExtractor
  10 from ..utils import int_or_none
  11
  12
  13 class VimpleIE(InfoExtractor):
  14     IE_DESC = 'Vimple.ru'
  15     _VALID_URL = r'https?://(player.vimple.ru/iframe|vimple.ru)/(?P<id>[a-f0-9]{10,})'
  16     _TESTS = [
  17         {
  18             'url': 'http://vimple.ru/c0f6b1687dcd4000a97ebe70068039cf',
  19             'md5': '2e750a330ed211d3fd41821c6ad9a279',
  20             'info_dict': {
  21                 'id': 'c0f6b1687dcd4000a97ebe70068039cf',
  22                 'ext': 'mp4',
  23                 'title': 'Sunset',
  24                 'duration': 20,
  25                 'thumbnail': 're:https?://.*?\.jpg',
  26             },
  27         },
  28     ]
  29
  30     def _real_extract(self, url):
  31         mobj = re.match(self._VALID_URL, url)
  32         video_id = mobj.group('id')
  33
  34         iframe_url = 'http://player.vimple.ru/iframe/%s' % video_id
  35
  36         iframe = self._download_webpage(
  37             iframe_url, video_id,
  38             note='Downloading iframe', errnote='unable to fetch iframe')
  39         player_url = self._html_search_regex(
  40             r'"(http://player.vimple.ru/flash/.+?)"', iframe, 'player url')
  41
  42         player = self._request_webpage(
  43             player_url, video_id, note='Downloading swf player').read()
  44
  45         player = zlib.decompress(player[8:])
  46
  47         xml_pieces = re.findall(b'([a-zA-Z0-9 =+/]{500})', player)
  48         xml_pieces = [piece[1:-1] for piece in xml_pieces]
  49
  50         xml_data = b''.join(xml_pieces)
  51         xml_data = base64.b64decode(xml_data)
  52
  53         xml_data = xml.etree.ElementTree.fromstring(xml_data)
  54
  55         video = xml_data.find('Video')
  56         quality = video.get('quality')
  57         q_tag = video.find(quality.capitalize())
  58
  59         formats = [
  60             {
  61                 'url': q_tag.get('url'),
  62                 'tbr': int(q_tag.get('bitrate')),
  63                 'filesize': int(q_tag.get('filesize')),
  64                 'format_id': quality,
  65             },
  66         ]
  67
  68         return {
  69             'id': video_id,
  70             'title': video.find('Title').text,
  71             'formats': formats,
  72             'thumbnail': video.find('Poster').get('url'),
  73             'duration': int_or_none(video.get('duration')),
  74             'webpage_url': video.find('Share').get('videoPageUrl'),
  75         }