youtube_dl/extractor/rtlnow.py

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