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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     clean_html,
  10     unified_strdate,
  11     parse_duration,
  12     int_or_none,
  13 )
  14
  15
  16 class RTLnowIE(InfoExtractor):
  17     """Information Extractor for RTL NOW, RTL2 NOW, RTL NITRO, SUPER RTL NOW, VOX NOW and n-tv NOW"""
  18     _VALID_URL = r'''(?x)
  19                         (?:https?://)?
  20                         (?P<url>
  21                             (?P<domain>
  22                                 rtl-now\.rtl\.de|
  23                                 rtl2now\.rtl2\.de|
  24                                 (?:www\.)?voxnow\.de|
  25                                 (?:www\.)?rtlnitronow\.de|
  26                                 (?:www\.)?superrtlnow\.de|
  27                                 (?:www\.)?n-tvnow\.de)
  28                             /+[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?
  29                             (?:container_id|film_id)=(?P<video_id>[0-9]+)&
  30                             player=1(?:&season=[0-9]+)?(?:&.*)?
  31                         )'''
  32
  33     _TESTS = [
  34         {
  35             'url': 'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1',
  36             'info_dict': {
  37                 'id': '90419',
  38                 'ext': 'flv',
  39                 'title': 'Ahornallee - Folge 1 - Der Einzug',
  40                 'description': 'md5:ce843b6b5901d9a7f7d04d1bbcdb12de',
  41                 'upload_date': '20070416',
  42                 'duration': 1685,
  43             },
  44             'params': {
  45                 'skip_download': True,
  46             },
  47             'skip': 'Only works from Germany',
  48         },
  49         {
  50             'url': 'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5',
  51             'info_dict': {
  52                 'id': '69756',
  53                 'ext': 'flv',
  54                 'title': 'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.',
  55                 'description': 'md5:3fb247005ed21a935ffc82b7dfa70cf0',
  56                 'thumbnail': 'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg',
  57                 'upload_date': '20120519',
  58                 'duration': 1245,
  59             },
  60             'params': {
  61                 'skip_download': True,
  62             },
  63             'skip': 'Only works from Germany',
  64         },
  65         {
  66             'url': 'http://www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17',
  67             'info_dict': {
  68                 'id': '13883',
  69                 'ext': 'flv',
  70                 'title': 'Voxtours - Südafrika-Reporter II',
  71                 'description': 'md5:de7f8d56be6fd4fed10f10f57786db00',
  72                 'upload_date': '20090627',
  73                 'duration': 1800,
  74             },
  75             'params': {
  76                 'skip_download': True,
  77             },
  78         },
  79         {
  80             'url': 'http://superrtlnow.de/medicopter-117/angst.php?film_id=99205&player=1',
  81             'info_dict': {
  82                 'id': '99205',
  83                 'ext': 'flv',
  84                 'title': 'Medicopter 117 - Angst!',
  85                 'description': 'md5:895b1df01639b5f61a04fc305a5cb94d',
  86                 'thumbnail': 'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg',
  87                 'upload_date': '20080928',
  88                 'duration': 2691,
  89             },
  90             'params': {
  91                 'skip_download': True,
  92             },
  93         },
  94         {
  95             'url': 'http://www.n-tvnow.de/deluxe-alles-was-spass-macht/thema-ua-luxushotel-fuer-vierbeiner.php?container_id=153819&player=1&season=0',
  96             'info_dict': {
  97                 'id': '153819',
  98                 'ext': 'flv',
  99                 'title': 'Deluxe - Alles was Spaß macht - Thema u.a.: Luxushotel für Vierbeiner',
 100                 'description': 'md5:c3705e1bb32e1a5b2bcd634fc065c631',
 101                 'thumbnail': 'http://autoimg.static-fra.de/ntvnow/383157/1500x1500/image2.jpg',
 102                 'upload_date': '20140221',
 103                 'duration': 2429,
 104             },
 105             'skip': 'Only works from Germany',
 106         },
 107     ]
 108
 109     def _real_extract(self, url):
 110         mobj = re.match(self._VALID_URL, url)
 111         video_page_url = 'http://%s/' % mobj.group('domain')
 112         video_id = mobj.group('video_id')
 113
 114         webpage = self._download_webpage('http://' + mobj.group('url'), video_id)
 115
 116         mobj = re.search(r'(?s)<div style="margin-left: 20px; font-size: 13px;">(.*?)<div id="playerteaser">', webpage)
 117         if mobj:
 118             raise ExtractorError(clean_html(mobj.group(1)), expected=True)
 119
 120         title = self._og_search_title(webpage)
 121         description = self._og_search_description(webpage)
 122         thumbnail = self._og_search_thumbnail(webpage, default=None)
 123
 124         upload_date = unified_strdate(self._html_search_meta('uploadDate', webpage, 'upload date'))
 125
 126         mobj = re.search(r'<meta itemprop="duration" content="PT(?P<seconds>\d+)S" />', webpage)
 127         duration = int(mobj.group('seconds')) if mobj else None
 128
 129         playerdata_url = self._html_search_regex(
 130             r"'playerdata': '(?P<playerdata_url>[^']+)'", webpage, 'playerdata_url')
 131
 132         playerdata = self._download_xml(playerdata_url, video_id, 'Downloading player data XML')
 133
 134         videoinfo = playerdata.find('./playlist/videoinfo')
 135
 136         formats = []
 137         for filename in videoinfo.findall('filename'):
 138             mobj = re.search(r'(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>.+)', filename.text)
 139             if mobj:
 140                 fmt = {
 141                     'url': mobj.group('url'),
 142                     'play_path': 'mp4:' + mobj.group('play_path'),
 143                     'page_url': video_page_url,
 144                     'player_url': video_page_url + 'includes/vodplayer.swf',
 145                 }
 146             else:
 147                 fmt = {
 148                     'url': filename.text,
 149                 }
 150             fmt.update({
 151                 'width': int_or_none(filename.get('width')),
 152                 'height': int_or_none(filename.get('height')),
 153                 'vbr': int_or_none(filename.get('bitrate')),
 154                 'ext': 'flv',
 155             })
 156             formats.append(fmt)
 157
 158         return {
 159             'id': video_id,
 160             'title': title,
 161             'description': description,
 162             'thumbnail': thumbnail,
 163             'upload_date': upload_date,
 164             'duration': duration,
 165             'formats': formats,
 166         }