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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import int_or_none
   8
   9
  10 class RTL2IE(InfoExtractor):
  11     _VALID_URL = r'http?://(?:www\.)?rtl2\.de/[^?#]*?/(?P<id>[^?#/]*?)(?:$|/(?:$|[?#]))'
  12     _TESTS = [{
  13         'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0',
  14         'info_dict': {
  15             'id': 'folge-203-0',
  16             'ext': 'f4v',
  17             'title': 'GRIP sucht den Sommerkönig',
  18             'description': 'md5:e3adbb940fd3c6e76fa341b8748b562f'
  19         },
  20         'params': {
  21             # rtmp download
  22             'skip_download': True,
  23         },
  24     }, {
  25         'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/',
  26         'info_dict': {
  27             'id': '21040-anna-erwischt-alex',
  28             'ext': 'mp4',
  29             'title': 'Anna erwischt Alex!',
  30             'description': 'Anna nimmt ihrem Vater nicht ab, dass er nicht spielt. Und tatsächlich erwischt sie ihn auf frischer Tat.'
  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
  58         info = self._download_json(
  59             'http://www.rtl2.de/sites/default/modules/rtl2/mediathek/php/get_video_jw.php',
  60             video_id, query={
  61                 'vico_id': vico_id,
  62                 'vivi_id': vivi_id,
  63             })
  64         video_info = info['video']
  65         title = video_info['titel']
  66
  67         formats = []
  68
  69         rtmp_url = video_info.get('streamurl')
  70         if rtmp_url:
  71             rtmp_url = rtmp_url.replace('\\', '')
  72             stream_url = 'mp4:' + self._html_search_regex(r'/ondemand/(.+)', rtmp_url, 'stream URL')
  73             rtmp_conn = ['S:connect', 'O:1', 'NS:pageUrl:' + url, 'NB:fpad:0', 'NN:videoFunction:1', 'O:0']
  74
  75             formats.append({
  76                 'format_id': 'rtmp',
  77                 'url': rtmp_url,
  78                 'play_path': stream_url,
  79                 'player_url': 'http://www.rtl2.de/flashplayer/vipo_player.swf',
  80                 'page_url': url,
  81                 'flash_version': 'LNX 11,2,202,429',
  82                 'rtmp_conn': rtmp_conn,
  83                 'no_resume': True,
  84                 'preference': 1,
  85             })
  86
  87         m3u8_url = video_info.get('streamurl_hls')
  88         if m3u8_url:
  89             formats.extend(self._extract_akamai_formats(m3u8_url, video_id))
  90
  91         self._sort_formats(formats)
  92
  93         return {
  94             'id': video_id,
  95             'title': title,
  96             'thumbnail': video_info.get('image'),
  97             'description': video_info.get('beschreibung'),
  98             'duration': int_or_none(video_info.get('duration')),
  99             'formats': formats,
 100         }