Raphaël G. Git Repositories - youtubedl/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     int_or_none,
  12 )
  13
  14
  15 class RTLnowIE(InfoExtractor):
  16     """Information Extractor for RTL NOW, RTL2 NOW, RTL NITRO, SUPER RTL NOW, VOX NOW and n-tv NOW"""
  17     _VALID_URL = r'''(?x)
  18                         (?:https?://)?
  19                         (?P<url>
  20                             (?P<domain>
  21                                 rtl-now\.rtl\.de|
  22                                 rtl2now\.rtl2\.de|
  23                                 (?:www\.)?voxnow\.de|
  24                                 (?:www\.)?rtlnitronow\.de|
  25                                 (?:www\.)?superrtlnow\.de|
  26                                 (?:www\.)?n-tvnow\.de)
  27                             /+[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?
  28                             (?:container_id|film_id)=(?P<video_id>[0-9]+)&
  29                             player=1(?:&season=[0-9]+)?(?:&.*)?
  30                         )'''
  31
  32     _TESTS = [
  33         {
  34             'url': 'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1',
  35             'info_dict': {
  36                 'id': '90419',
  37                 'ext': 'flv',
  38                 'title': 'Ahornallee - Folge 1 - Der Einzug',
  39                 'description': 'md5:ce843b6b5901d9a7f7d04d1bbcdb12de',
  40                 'upload_date': '20070416',
  41                 'duration': 1685,
  42             },
  43             'params': {
  44                 'skip_download': True,
  45             },
  46             'skip': 'Only works from Germany',
  47         },
  48         {
  49             'url': 'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5',
  50             'info_dict': {
  51                 'id': '69756',
  52                 'ext': 'flv',
  53                 'title': 'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.',
  54                 'description': 'md5:3fb247005ed21a935ffc82b7dfa70cf0',
  55                 'thumbnail': 'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg',
  56                 'upload_date': '20120519',
  57                 'duration': 1245,
  58             },
  59             'params': {
  60                 'skip_download': True,
  61             },
  62             'skip': 'Only works from Germany',
  63         },
  64         {
  65             'url': 'http://www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17',
  66             'info_dict': {
  67                 'id': '13883',
  68                 'ext': 'flv',
  69                 'title': 'Voxtours - Südafrika-Reporter II',
  70                 'description': 'md5:de7f8d56be6fd4fed10f10f57786db00',
  71                 'upload_date': '20090627',
  72                 'duration': 1800,
  73             },
  74             'params': {
  75                 'skip_download': True,
  76             },
  77         },
  78         {
  79             'url': 'http://superrtlnow.de/medicopter-117/angst.php?film_id=99205&player=1',
  80             'info_dict': {
  81                 'id': '99205',
  82                 'ext': 'flv',
  83                 'title': 'Medicopter 117 - Angst!',
  84                 'description': 're:^Im Therapiezentrum \'Sonnalm\' kommen durch eine Unachtsamkeit die für die B.handlung mit Phobikern gehaltenen Voglespinnen frei\. Eine Ausreißerin',
  85                 'thumbnail': 'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg',
  86                 'upload_date': '20080928',
  87                 'duration': 2691,
  88             },
  89             'params': {
  90                 'skip_download': True,
  91             },
  92         },
  93         {
  94             'url': 'http://rtl-now.rtl.de/der-bachelor/folge-4.php?film_id=188729&player=1&season=5',
  95             'info_dict': {
  96                 'id': '188729',
  97                 'ext': 'flv',
  98                 'upload_date': '20150204',
  99                 'description': 'md5:5e1ce23095e61a79c166d134b683cecc',
 100                 'title': 'Der Bachelor - Folge 4',
 101             }
 102         }, {
 103             'url': 'http://www.n-tvnow.de/deluxe-alles-was-spass-macht/thema-ua-luxushotel-fuer-vierbeiner.php?container_id=153819&player=1&season=0',
 104             'only_matching': True,
 105         },
 106     ]
 107
 108     def _real_extract(self, url):
 109         mobj = re.match(self._VALID_URL, url)
 110         video_page_url = 'http://%s/' % mobj.group('domain')
 111         video_id = mobj.group('video_id')
 112
 113         webpage = self._download_webpage('http://' + mobj.group('url'), video_id)
 114
 115         mobj = re.search(r'(?s)<div style="margin-left: 20px; font-size: 13px;">(.*?)<div id="playerteaser">', webpage)
 116         if mobj:
 117             raise ExtractorError(clean_html(mobj.group(1)), expected=True)
 118
 119         title = self._og_search_title(webpage)
 120         description = self._og_search_description(webpage)
 121         thumbnail = self._og_search_thumbnail(webpage, default=None)
 122
 123         upload_date = unified_strdate(self._html_search_meta('uploadDate', webpage, 'upload date'))
 124
 125         mobj = re.search(r'<meta itemprop="duration" content="PT(?P<seconds>\d+)S" />', webpage)
 126         duration = int(mobj.group('seconds')) if mobj else None
 127
 128         playerdata_url = self._html_search_regex(
 129             r"'playerdata': '(?P<playerdata_url>[^']+)'", webpage, 'playerdata_url')
 130
 131         playerdata = self._download_xml(playerdata_url, video_id, 'Downloading player data XML')
 132
 133         videoinfo = playerdata.find('./playlist/videoinfo')
 134
 135         formats = []
 136         for filename in videoinfo.findall('filename'):
 137             mobj = re.search(r'(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>.+)', filename.text)
 138             if mobj:
 139                 fmt = {
 140                     'url': mobj.group('url'),
 141                     'play_path': 'mp4:' + mobj.group('play_path'),
 142                     'page_url': video_page_url,
 143                     'player_url': video_page_url + 'includes/vodplayer.swf',
 144                 }
 145             else:
 146                 mobj = re.search(r'.*/(?P<hoster>[^/]+)/videos/(?P<play_path>.+)\.f4m', filename.text)
 147                 if mobj:
 148                     fmt = {
 149                         'url': 'rtmpe://fms.rtl.de/' + mobj.group('hoster'),
 150                         'play_path': 'mp4:' + mobj.group('play_path'),
 151                         'page_url': url,
 152                         'player_url': video_page_url + 'includes/vodplayer.swf',
 153                     }
 154                 else:
 155                     fmt = {
 156                         'url': filename.text,
 157                     }
 158             fmt.update({
 159                 'width': int_or_none(filename.get('width')),
 160                 'height': int_or_none(filename.get('height')),
 161                 'vbr': int_or_none(filename.get('bitrate')),
 162                 'ext': 'flv',
 163             })
 164             formats.append(fmt)
 165
 166         return {
 167             'id': video_id,
 168             'title': title,
 169             'description': description,
 170             'thumbnail': thumbnail,
 171             'upload_date': upload_date,
 172             'duration': duration,
 173             'formats': formats,
 174         }