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