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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class RTL2IE(InfoExtractor):
   8     _VALID_URL = r'http?://(?:www\.)?rtl2\.de/[^?#]*?/(?P<id>[^?#/]*?)(?:$|/(?:$|[?#]))'
   9     _TESTS = [{
  10         'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0',
  11         'md5': 'bfcc179030535b08dc2b36b469b5adc7',
  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     }, {
  19         'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/',
  20         'md5': 'ffcd517d2805b57ce11a58a2980c2b02',
  21         'info_dict': {
  22             'id': '21040-anna-erwischt-alex',
  23             'ext': 'mp4',
  24             'title': 'Anna erwischt Alex!',
  25             'description': 'Anna ist Alex\' Tochter bei Köln 50667.'
  26         },
  27     }]
  28
  29     def _real_extract(self, url):
  30         # Some rtl2 urls have no slash at the end, so append it.
  31         if not url.endswith('/'):
  32             url += '/'
  33
  34         video_id = self._match_id(url)
  35         webpage = self._download_webpage(url, video_id)
  36
  37         vico_id = self._html_search_regex(
  38             r'vico_id\s*:\s*([0-9]+)', webpage, 'vico_id')
  39         vivi_id = self._html_search_regex(
  40             r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id')
  41         info_url = 'http://www.rtl2.de/video/php/get_video.php?vico_id=' + vico_id + '&vivi_id=' + vivi_id
  42         webpage = self._download_webpage(info_url, '')
  43
  44         info = self._download_json(info_url, video_id)
  45         video_info = info['video']
  46         title = video_info['titel']
  47         description = video_info.get('beschreibung')
  48         thumbnail = video_info.get('image')
  49
  50         download_url = video_info['streamurl']
  51         download_url = download_url.replace('\\', '')
  52         stream_url = 'mp4:' + self._html_search_regex(r'ondemand/(.*)', download_url, 'stream URL')
  53         rtmp_conn = ["S:connect", "O:1", "NS:pageUrl:" + url, "NB:fpad:0", "NN:videoFunction:1", "O:0"]
  54
  55         formats = [{
  56             'url': download_url,
  57             'play_path': stream_url,
  58             'player_url': 'http://www.rtl2.de/flashplayer/vipo_player.swf',
  59             'page_url': url,
  60             'flash_version': 'LNX 11,2,202,429',
  61             'rtmp_conn': rtmp_conn,
  62             'no_resume': True,
  63         }]
  64         self._sort_formats(formats)
  65
  66         return {
  67             'id': video_id,
  68             'title': title,
  69             'thumbnail': thumbnail,
  70             'description': description,
  71             'formats': formats,
  72         }