_ Git - youtube-dl/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         'md5': 'bfcc179030535b08dc2b36b469b5adc7',
  13         'info_dict': {
  14             'id': 'folge-203-0',
  15             'ext': 'f4v',
  16             'title': 'GRIP sucht den Sommerkönig',
  17             'description': 'Matthias, Det und Helge treten gegeneinander an.'
  18         },
  19         'params': {
  20             # rtmp download
  21             'skip_download': True,
  22         },
  23     }, {
  24         'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/',
  25         'md5': 'ffcd517d2805b57ce11a58a2980c2b02',
  26         'info_dict': {
  27             'id': '21040-anna-erwischt-alex',
  28             'ext': 'mp4',
  29             'title': 'Anna erwischt Alex!',
  30             'description': 'Anna ist Alex\' Tochter bei Köln 50667.'
  31         },
  32         'params': {
  33             # rtmp download
  34             'skip_download': True,
  35         },
  36     }]
  37
  38     def _real_extract(self, url):
  39         # Some rtl2 urls have no slash at the end, so append it.
  40         if not url.endswith('/'):
  41             url += '/'
  42
  43         video_id = self._match_id(url)
  44         webpage = self._download_webpage(url, video_id)
  45
  46         mobj = re.search(
  47             r'<div[^>]+data-collection="(?P<vico_id>\d+)"[^>]+data-video="(?P<vivi_id>\d+)"',
  48             webpage)
  49         if mobj:
  50             vico_id = mobj.group('vico_id')
  51             vivi_id = mobj.group('vivi_id')
  52         else:
  53             vico_id = self._html_search_regex(
  54                 r'vico_id\s*:\s*([0-9]+)', webpage, 'vico_id')
  55             vivi_id = self._html_search_regex(
  56                 r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id')
  57         info_url = 'http://www.rtl2.de/video/php/get_video.php?vico_id=' + vico_id + '&vivi_id=' + vivi_id
  58
  59         info = self._download_json(info_url, video_id)
  60         video_info = info['video']
  61         title = video_info['titel']
  62         description = video_info.get('beschreibung')
  63         thumbnail = video_info.get('image')
  64
  65         download_url = video_info['streamurl']
  66         download_url = download_url.replace('\\', '')
  67         stream_url = 'mp4:' + self._html_search_regex(r'ondemand/(.*)', download_url, 'stream URL')
  68         rtmp_conn = ["S:connect", "O:1", "NS:pageUrl:" + url, "NB:fpad:0", "NN:videoFunction:1", "O:0"]
  69
  70         formats = [{
  71             'url': download_url,
  72             'play_path': stream_url,
  73             'player_url': 'http://www.rtl2.de/flashplayer/vipo_player.swf',
  74             'page_url': url,
  75             'flash_version': 'LNX 11,2,202,429',
  76             'rtmp_conn': rtmp_conn,
  77             'no_resume': True,
  78         }]
  79         self._sort_formats(formats)
  80
  81         return {
  82             'id': video_id,
  83             'title': title,
  84             'thumbnail': thumbnail,
  85             'description': description,
  86             'formats': formats,
  87         }