_ Git - youtube-dl/blob - youtube_dl/extractor/rtl2.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import json
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     ExtractorError,
  10     clean_html,
  11     unified_strdate,
  12     int_or_none,
  13 )
  14
  15
  16 class RTL2IE(InfoExtractor):
  17     """Information Extractor for RTL NOW, RTL2 NOW, RTL NITRO, SUPER RTL NOW, VOX NOW and n-tv NOW"""
  18     _VALID_URL = r'http?://(?P<url>(?P<domain>(www\.)?rtl2\.de)/.*/(?P<video_id>.*))'
  19     _TESTS = [{
  20             'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0',
  21             'info_dict': {
  22                 'id': 'folge-203-0',
  23                 'ext': 'f4v',
  24                 'title': 'GRIP sucht den Sommerk\xf6nig',
  25                 'description' : 'Matthias, Det und Helge treten gegeneinander an.'
  26             },
  27             'params': {
  28                 # rtmp download
  29                 #'skip_download': True,
  30             },
  31         },
  32         {
  33             'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/',
  34             'info_dict': {
  35                 'id': '21040-anna-erwischt-alex',
  36                 'ext': 'f4v',
  37                 'title': 'GRIP sucht den Sommerk\xf6nig',
  38                 'description' : 'Matthias, Det und Helge treten gegeneinander an.'
  39             },
  40             'params': {
  41                 # rtmp download
  42                 #'skip_download': True,
  43             },
  44         },
  45     ]
  46
  47     def _real_extract(self, url):
  48         mobj = re.match(self._VALID_URL, url)
  49         video_page_url = 'http://%s/' % mobj.group('domain')
  50         video_id = mobj.group('video_id')
  51
  52         webpage = self._download_webpage('http://' + mobj.group('url'), video_id)
  53
  54         vico_id = self._html_search_regex(r'vico_id\s*:\s*([0-9]+)', webpage, '%s');
  55         vivi_id = self._html_search_regex(r'vivi_id\s*:\s*([0-9]+)', webpage, '%s');
  56
  57         info_url = 'http://www.rtl2.de/video/php/get_video.php?vico_id=' + vico_id + '&vivi_id=' + vivi_id
  58         webpage = self._download_webpage(info_url, '')
  59
  60         video_info = json.loads(webpage)
  61
  62         download_url = video_info["video"]["streamurl"] # self._html_search_regex(r'streamurl\":\"(.*?)\"', webpage, '%s');
  63         title = video_info["video"]["titel"] # self._html_search_regex(r'titel\":\"(.*?)\"', webpage, '%s');
  64         description = video_info["video"]["beschreibung"] # self._html_search_regex(r'beschreibung\":\"(.*?)\"', webpage, '%s');
  65         #ext = self._html_search_regex(r'streamurl\":\".*?(\..{2,4})\"', webpage, '%s');
  66
  67         thumbnail = video_info["video"]["image"]
  68
  69         download_url = download_url.replace("\\", "")
  70
  71         stream_url = 'mp4:' + self._html_search_regex(r'ondemand/(.*)', download_url, '%s')
  72
  73         #print(download_url)
  74         #print(stream_url)
  75         #print(title)
  76         #print(description)
  77         #print(video_id)
  78
  79         formats = []
  80
  81         fmt = {
  82             'url' : download_url,
  83                 #'app': 'ondemand?_fcs_vhost=cp108781.edgefcs.net',
  84                 'play_path': stream_url,
  85                 'player_url': 'http://www.rtl2.de/flashplayer/vipo_player.swf',
  86                 'page_url': url,
  87                 'flash_version' : "LNX 11,2,202,429",
  88                 'rtmp_conn' : ["S:connect", "O:1", "NS:pageUrl:" + url, "NB:fpad:0", "NN:videoFunction:1", "O:0"],
  89                 'no_resume' : 1,
  90         }
  91
  92         formats.append(fmt)
  93
  94         return {
  95             'id': video_id,
  96             'title': title,
  97             'thumbnail' : thumbnail,
  98             'description' : description,
  99             'formats': formats,
 100         }