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         # Quality: Large, from iframe
  18         {
  19             'url': 'http://player.vimple.ru/iframe/b132bdfd71b546d3972f9ab9a25f201c',
  20             'info_dict': {
  21                 'id': 'b132bdfd71b546d3972f9ab9a25f201c',
  22                 'title': 'great-escape-minecraft.flv',
  23                 'ext': 'mp4',
  24                 'duration': 352,
  25                 'webpage_url': 'http://vimple.ru/b132bdfd71b546d3972f9ab9a25f201c',
  26             },
  27         },
  28         # Quality: Medium, from mainpage
  29         {
  30             'url': 'http://vimple.ru/a15950562888453b8e6f9572dc8600cd',
  31             'info_dict': {
  32                 'id': 'a15950562888453b8e6f9572dc8600cd',
  33                 'title': 'DB 01',
  34                 'ext': 'flv',
  35                 'duration': 1484,
  36                 'webpage_url': 'http://vimple.ru/a15950562888453b8e6f9572dc8600cd',
  37             }
  38         },
  39     ]
  40
  41     def _real_extract(self, url):
  42         mobj = re.match(self._VALID_URL, url)
  43         video_id = mobj.group('id')
  44
  45         iframe_url = 'http://player.vimple.ru/iframe/%s' % video_id
  46
  47         iframe = self._download_webpage(
  48             iframe_url, video_id,
  49             note='Downloading iframe', errnote='unable to fetch iframe')
  50         player_url = self._html_search_regex(
  51             r'"(http://player.vimple.ru/flash/.+?)"', iframe, 'player url')
  52
  53         player = self._request_webpage(
  54             player_url, video_id, note='Downloading swf player').read()
  55
  56         player = zlib.decompress(player[8:])
  57
  58         xml_pieces = re.findall(b'([a-zA-Z0-9 =+/]{500})', player)
  59         xml_pieces = [piece[1:-1] for piece in xml_pieces]
  60
  61         xml_data = b''.join(xml_pieces)
  62         xml_data = base64.b64decode(xml_data)
  63
  64         xml_data = xml.etree.ElementTree.fromstring(xml_data)
  65
  66         video = xml_data.find('Video')
  67         quality = video.get('quality')
  68         q_tag = video.find(quality.capitalize())
  69
  70         formats = [
  71             {
  72                 'url': q_tag.get('url'),
  73                 'tbr': int(q_tag.get('bitrate')),
  74                 'filesize': int(q_tag.get('filesize')),
  75                 'format_id': quality,
  76             },
  77         ]
  78
  79         return {
  80             'id': video_id,
  81             'title': video.find('Title').text,
  82             'formats': formats,
  83             'thumbnail': video.find('Poster').get('url'),
  84             'duration': int_or_none(video.get('duration')),
  85             'webpage_url': video.find('Share').get('videoPageUrl'),
  86         }