yt_dlp/extractor/tagesschau.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     UnsupportedError,
   6     extract_attributes,
   7     int_or_none,
   8     js_to_json,
   9     parse_iso8601,
  10     try_get,
  11 )
  12
  13
  14 class TagesschauIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/(?P<path>[^/]+/(?:[^/]+/)*?(?P<id>[^/#?]+?(?:-?[0-9]+)?))(?:~_?[^/#?]+?)?\.html'
  16
  17     _TESTS = [{
  18         'url': 'http://www.tagesschau.de/multimedia/video/video-102143.html',
  19         'md5': 'ccb9359bf8c4795836e43759f3408a93',
  20         'info_dict': {
  21             'id': 'video-102143-1',
  22             'ext': 'mp4',
  23             'title': 'Regierungsumbildung in Athen: Neue Minister in Griechenland vereidigt',
  24             'duration': 138,
  25         },
  26     }, {
  27         'url': 'http://www.tagesschau.de/multimedia/sendung/ts-5727.html',
  28         'md5': '5c15e8f3da049e48829ec9786d835536',
  29         'info_dict': {
  30             'id': 'ts-5727-1',
  31             'ext': 'mp4',
  32             'title': 'Ganze Sendung',
  33             'duration': 932,
  34         },
  35     }, {
  36         # exclusive audio
  37         'url': 'http://www.tagesschau.de/multimedia/audio/audio-29417.html',
  38         'md5': '4bff8f23504df56a0d86ed312d654182',
  39         'info_dict': {
  40             'id': 'audio-29417-1',
  41             'ext': 'mp3',
  42             'title': 'EU-Gipfel: Im Verbrennerstreit hat Deutschland maximalen Schaden angerichtet',
  43         },
  44     }, {
  45         'url': 'http://www.tagesschau.de/inland/bnd-303.html',
  46         'md5': 'f049fa1698d7564e9ca4c3325108f034',
  47         'info_dict': {
  48             'id': 'bnd-303-1',
  49             'ext': 'mp3',
  50             'title': 'Das Siegel des Bundesnachrichtendienstes | dpa',
  51         },
  52     }, {
  53         'url': 'http://www.tagesschau.de/inland/afd-parteitag-135.html',
  54         'info_dict': {
  55             'id': 'afd-parteitag-135',
  56             'title': 'AfD',
  57         },
  58         'playlist_mincount': 15,
  59     }, {
  60         'url': 'https://www.tagesschau.de/multimedia/audio/audio-29417~player.html',
  61         'info_dict': {
  62             'id': 'audio-29417-1',
  63             'ext': 'mp3',
  64             'title': 'EU-Gipfel: Im Verbrennerstreit hat Deutschland maximalen Schaden angerichtet',
  65         },
  66     }, {
  67         'url': 'https://www.tagesschau.de/multimedia/audio/podcast-11km-327.html',
  68         'info_dict': {
  69             'id': 'podcast-11km-327',
  70             'ext': 'mp3',
  71             'title': 'Gewalt in der Kita – Wenn Erzieher:innen schweigen',
  72             'upload_date': '20230322',
  73             'timestamp': 1679482808,
  74             'thumbnail': 'https://www.tagesschau.de/multimedia/audio/podcast-11km-329~_v-original.jpg',
  75             'description': 'md5:dad059931fe4b3693e3656e93a249848',
  76         },
  77     }, {
  78         'url': 'http://www.tagesschau.de/multimedia/sendung/tsg-3771.html',
  79         'only_matching': True,
  80     }, {
  81         'url': 'http://www.tagesschau.de/multimedia/sendung/tt-3827.html',
  82         'only_matching': True,
  83     }, {
  84         'url': 'http://www.tagesschau.de/multimedia/sendung/nm-3475.html',
  85         'only_matching': True,
  86     }, {
  87         'url': 'http://www.tagesschau.de/multimedia/sendung/weltspiegel-3167.html',
  88         'only_matching': True,
  89     }, {
  90         'url': 'http://www.tagesschau.de/multimedia/tsvorzwanzig-959.html',
  91         'only_matching': True,
  92     }, {
  93         'url': 'http://www.tagesschau.de/multimedia/sendung/bab/bab-3299~_bab-sendung-209.html',
  94         'only_matching': True,
  95     }, {
  96         'url': 'http://www.tagesschau.de/multimedia/video/video-102303~_bab-sendung-211.html',
  97         'only_matching': True,
  98     }, {
  99         'url': 'http://www.tagesschau.de/100sekunden/index.html',
 100         'only_matching': True,
 101     }, {
 102         # playlist article with collapsing sections
 103         'url': 'http://www.tagesschau.de/wirtschaft/faq-freihandelszone-eu-usa-101.html',
 104         'only_matching': True,
 105     }]
 106
 107     def _real_extract(self, url):
 108         mobj = self._match_valid_url(url)
 109         video_id = mobj.group('id') or mobj.group('path')
 110         display_id = video_id.lstrip('-')
 111
 112         webpage = self._download_webpage(url, display_id)
 113
 114         title = self._html_search_regex(
 115             r'<span[^>]*class="headline"[^>]*>(.+?)</span>',
 116             webpage, 'title', default=None) or self._og_search_title(webpage, fatal=False)
 117
 118         entries = []
 119         videos = re.findall(r'<div[^>]+>', webpage)
 120         num = 0
 121         for video in videos:
 122             video = extract_attributes(video).get('data-config')
 123             if not video:
 124                 continue
 125             video = self._parse_json(video, video_id, transform_source=js_to_json, fatal=False)
 126             video_formats = try_get(video, lambda x: x['mc']['_mediaArray'][0]['_mediaStreamArray'])
 127             if not video_formats:
 128                 continue
 129             num += 1
 130             for video_format in video_formats:
 131                 media_url = video_format.get('_stream') or ''
 132                 formats = []
 133                 if media_url.endswith('master.m3u8'):
 134                     formats = self._extract_m3u8_formats(media_url, video_id, 'mp4', m3u8_id='hls')
 135                 elif media_url.endswith('.mp3'):
 136                     formats = [{
 137                         'url': media_url,
 138                         'vcodec': 'none',
 139                     }]
 140                 if not formats:
 141                     continue
 142                 entries.append({
 143                     'id': '%s-%d' % (display_id, num),
 144                     'title': try_get(video, lambda x: x['mc']['_title']),
 145                     'duration': int_or_none(try_get(video, lambda x: x['mc']['_duration'])),
 146                     'formats': formats
 147                 })
 148
 149         if not entries:
 150             raise UnsupportedError(url)
 151
 152         if len(entries) > 1:
 153             return self.playlist_result(entries, display_id, title)
 154
 155         return {
 156             'id': display_id,
 157             'title': title,
 158             'thumbnail': self._og_search_thumbnail(webpage),
 159             'formats': entries[0]['formats'],
 160             'timestamp': parse_iso8601(self._html_search_meta('date', webpage)),
 161             'description': self._og_search_description(webpage),
 162             'duration': entries[0]['duration'],
 163         }