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

   1 # encoding: utf-8
   2
   3 from __future__ import unicode_literals
   4
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     clean_html,
  10     ExtractorError,
  11 )
  12
  13
  14 class RTLnowIE(InfoExtractor):
  15     """Information Extractor for RTL NOW, RTL2 NOW, RTL NITRO, SUPER RTL NOW, VOX NOW and n-tv NOW"""
  16     _VALID_URL = r'(?:http://)?(?P<url>(?P<domain>rtl-now\.rtl\.de|rtl2now\.rtl2\.de|(?:www\.)?voxnow\.de|(?:www\.)?rtlnitronow\.de|(?:www\.)?superrtlnow\.de|(?:www\.)?n-tvnow\.de)/+[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P<video_id>[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)'
  17     _TESTS = [{
  18         'url': 'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1',
  19         'file': '90419.flv',
  20         'info_dict': {
  21             'upload_date': '20070416',
  22             'title': 'Ahornallee - Folge 1 - Der Einzug',
  23             'description': 'Folge 1 - Der Einzug',
  24         },
  25         'params': {
  26             'skip_download': True,
  27         },
  28         'skip': 'Only works from Germany',
  29     },
  30     {
  31         'url': 'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5',
  32         'file': '69756.flv',
  33         'info_dict': {
  34             'upload_date': '20120519',
  35             'title': 'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit...',
  36             'description': 'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.',
  37             'thumbnail': 'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg',
  38         },
  39         'params': {
  40             'skip_download': True,
  41         },
  42         'skip': 'Only works from Germany',
  43     },
  44     {
  45         'url': 'http://www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17',
  46         'file': '13883.flv',
  47         'info_dict': {
  48             'upload_date': '20090627',
  49             'title': 'Voxtours - Südafrika-Reporter II',
  50             'description': 'Südafrika-Reporter II',
  51         },
  52         'params': {
  53             'skip_download': True,
  54         },
  55     },
  56     {
  57         'url': 'http://superrtlnow.de/medicopter-117/angst.php?film_id=99205&player=1',
  58         'file': '99205.flv',
  59         'info_dict': {
  60             'upload_date': '20080928',
  61             'title': 'Medicopter 117 - Angst!',
  62             'description': 'Angst!',
  63             'thumbnail': 'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg'
  64         },
  65         'params': {
  66             'skip_download': True,
  67         },
  68     },
  69     {
  70         'url': 'http://www.n-tvnow.de/top-gear/episode-1-2013-01-01-00-00-00.php?film_id=124903&player=1&season=10',
  71         'file': '124903.flv',
  72         'info_dict': {
  73             'upload_date': '20130101',
  74             'title': 'Top Gear vom 01.01.2013',
  75             'description': 'Episode 1',
  76         },
  77         'params': {
  78             'skip_download': True,
  79         },
  80         'skip': 'Only works from Germany',
  81     }]
  82
  83     def _real_extract(self, url):
  84         mobj = re.match(self._VALID_URL, url)
  85
  86         webpage_url = 'http://' + mobj.group('url')
  87         video_page_url = 'http://' + mobj.group('domain') + '/'
  88         video_id = mobj.group('video_id')
  89
  90         webpage = self._download_webpage(webpage_url, video_id)
  91
  92         note_m = re.search(r'''(?sx)
  93             <div[ ]style="margin-left:[ ]20px;[ ]font-size:[ ]13px;">(.*?)
  94             <div[ ]id="playerteaser">''', webpage)
  95         if note_m:
  96             msg = clean_html(note_m.group(1))
  97             raise ExtractorError(msg)
  98
  99         video_title = self._html_search_regex(
 100             r'<title>(?P<title>[^<]+?)( \| [^<]*)?</title>',
 101             webpage, 'title')
 102         playerdata_url = self._html_search_regex(
 103             r'\'playerdata\': \'(?P<playerdata_url>[^\']+)\'',
 104             webpage, 'playerdata_url')
 105
 106         playerdata = self._download_webpage(playerdata_url, video_id)
 107         mobj = re.search(r'<title><!\[CDATA\[(?P<description>.+?)(?:\s+- (?:Sendung )?vom (?P<upload_date_d>[0-9]{2})\.(?P<upload_date_m>[0-9]{2})\.(?:(?P<upload_date_Y>[0-9]{4})|(?P<upload_date_y>[0-9]{2})) [0-9]{2}:[0-9]{2} Uhr)?\]\]></title>', playerdata)
 108         if mobj:
 109             video_description = mobj.group('description')
 110             if mobj.group('upload_date_Y'):
 111                 video_upload_date = mobj.group('upload_date_Y')
 112             elif mobj.group('upload_date_y'):
 113                 video_upload_date = '20' + mobj.group('upload_date_y')
 114             else:
 115                 video_upload_date = None
 116             if video_upload_date:
 117                 video_upload_date += mobj.group('upload_date_m') + mobj.group('upload_date_d')
 118         else:
 119             video_description = None
 120             video_upload_date = None
 121             self._downloader.report_warning('Unable to extract description and upload date')
 122
 123         # Thumbnail: not every video has an thumbnail
 124         mobj = re.search(r'<meta property="og:image" content="(?P<thumbnail>[^"]+)">', webpage)
 125         if mobj:
 126             video_thumbnail = mobj.group('thumbnail')
 127         else:
 128             video_thumbnail = None
 129
 130         mobj = re.search(r'<filename [^>]+><!\[CDATA\[(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>[^\]]+)\]\]></filename>', playerdata)
 131         if mobj is None:
 132             raise ExtractorError('Unable to extract media URL')
 133         video_url = mobj.group('url')
 134         video_play_path = 'mp4:' + mobj.group('play_path')
 135         video_player_url = video_page_url + 'includes/vodplayer.swf'
 136
 137         return {
 138             'id': video_id,
 139             'url': video_url,
 140             'play_path': video_play_path,
 141             'page_url': video_page_url,
 142             'player_url': video_player_url,
 143             'ext': 'flv',
 144             'title': video_title,
 145             'description': video_description,
 146             'upload_date': video_upload_date,
 147             'thumbnail': video_thumbnail,
 148         }