Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/rtl2.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 from .common import InfoExtractor
   6
   7
   8 class RTL2IE(InfoExtractor):
   9     _VALID_URL = r'http?://(?:www\.)?rtl2\.de/[^?#]*?/(?P<id>[^?#/]*?)(?:$|/(?:$|[?#]))'
  10     _TESTS = [{
  11         'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0',
  12         'info_dict': {
  13             'id': 'folge-203-0',
  14             'ext': 'f4v',
  15             'title': 'GRIP sucht den Sommerkönig',
  16             'description': 'Matthias, Det und Helge treten gegeneinander an.'
  17         },
  18         'params': {
  19             # rtmp download
  20             'skip_download': True,
  21         },
  22     }, {
  23         'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/',
  24         'info_dict': {
  25             'id': '21040-anna-erwischt-alex',
  26             'ext': 'mp4',
  27             'title': 'Anna erwischt Alex!',
  28             'description': 'Anna ist Alex\' Tochter bei Köln 50667.'
  29         },
  30         'params': {
  31             # rtmp download
  32             'skip_download': True,
  33         },
  34     }]
  35
  36     def _real_extract(self, url):
  37         # Some rtl2 urls have no slash at the end, so append it.
  38         if not url.endswith('/'):
  39             url += '/'
  40
  41         video_id = self._match_id(url)
  42         webpage = self._download_webpage(url, video_id)
  43
  44         mobj = re.search(
  45             r'<div[^>]+data-collection="(?P<vico_id>\d+)"[^>]+data-video="(?P<vivi_id>\d+)"',
  46             webpage)
  47         if mobj:
  48             vico_id = mobj.group('vico_id')
  49             vivi_id = mobj.group('vivi_id')
  50         else:
  51             vico_id = self._html_search_regex(
  52                 r'vico_id\s*:\s*([0-9]+)', webpage, 'vico_id')
  53             vivi_id = self._html_search_regex(
  54                 r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id')
  55         info_url = 'http://www.rtl2.de/video/php/get_video.php?vico_id=' + vico_id + '&vivi_id=' + vivi_id
  56
  57         info = self._download_json(info_url, video_id)
  58         video_info = info['video']
  59         title = video_info['titel']
  60         description = video_info.get('beschreibung')
  61         thumbnail = video_info.get('image')
  62
  63         download_url = video_info['streamurl']
  64         download_url = download_url.replace('\\', '')
  65         stream_url = 'mp4:' + self._html_search_regex(r'ondemand/(.*)', download_url, 'stream URL')
  66         rtmp_conn = ['S:connect', 'O:1', 'NS:pageUrl:' + url, 'NB:fpad:0', 'NN:videoFunction:1', 'O:0']
  67
  68         formats = [{
  69             'url': download_url,
  70             'play_path': stream_url,
  71             'player_url': 'http://www.rtl2.de/flashplayer/vipo_player.swf',
  72             'page_url': url,
  73             'flash_version': 'LNX 11,2,202,429',
  74             'rtmp_conn': rtmp_conn,
  75             'no_resume': True,
  76         }]
  77         self._sort_formats(formats)
  78
  79         return {
  80             'id': video_id,
  81             'title': title,
  82             'thumbnail': thumbnail,
  83             'description': description,
  84             'formats': formats,
  85         }