yt_dlp/extractor/tagesschau.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     js_to_json,
   6     extract_attributes,
   7     try_get,
   8     int_or_none,
   9 )
  10
  11
  12 class TagesschauIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/(?P<path>[^/]+/(?:[^/]+/)*?(?P<id>[^/#?]+?(?:-?[0-9]+)?))(?:~_?[^/#?]+?)?\.html'
  14
  15     _TESTS = [{
  16         'url': 'http://www.tagesschau.de/multimedia/video/video-102143.html',
  17         'md5': '7a7287612fa881a1ae1d087df45c2fd6',
  18         'info_dict': {
  19             'id': 'video-102143-1',
  20             'ext': 'mp4',
  21             'title': 'Regierungsumbildung in Athen: Neue Minister in Griechenland vereidigt',
  22         },
  23     }, {
  24         'url': 'http://www.tagesschau.de/multimedia/sendung/ts-5727.html',
  25         'md5': '3c54c1f6243d279b706bde660ceec633',
  26         'info_dict': {
  27             'id': 'ts-5727-1',
  28             'ext': 'mp4',
  29             'title': 'Ganze Sendung',
  30         },
  31     }, {
  32         # exclusive audio
  33         'url': 'http://www.tagesschau.de/multimedia/audio/audio-29417.html',
  34         'md5': '4cf22023c285f35e99c24d290ba58cc9',
  35         'info_dict': {
  36             'id': 'audio-29417-1',
  37             'ext': 'mp3',
  38             'title': 'Brasilianischer Präsident Bolsonaro unter Druck: Corona-Bericht wird vorgestellt',
  39         },
  40     }, {
  41         'url': 'http://www.tagesschau.de/inland/bnd-303.html',
  42         'md5': '12cfb212d9325b5ba0d52b625f1aa61c',
  43         'info_dict': {
  44             'id': 'bnd-303-1',
  45             'ext': 'mp4',
  46             'title': 'SPD-Gruppenbild mit Bärbel Bas nach der Fraktionssitzung | dpa',
  47         },
  48     }, {
  49         'url': 'http://www.tagesschau.de/inland/afd-parteitag-135.html',
  50         'info_dict': {
  51             'id': 'afd-parteitag-135',
  52             'title': 'AfD',
  53         },
  54         'playlist_count': 20,
  55     }, {
  56         'url': 'https://www.tagesschau.de/multimedia/audio/audio-29417~player.html',
  57         'info_dict': {
  58             'id': 'audio-29417-1',
  59             'ext': 'mp3',
  60             'title': 'Brasilianischer Präsident Bolsonaro unter Druck: Corona-Bericht wird vorgestellt',
  61         },
  62     }, {
  63         'url': 'http://www.tagesschau.de/multimedia/sendung/tsg-3771.html',
  64         'only_matching': True,
  65     }, {
  66         'url': 'http://www.tagesschau.de/multimedia/sendung/tt-3827.html',
  67         'only_matching': True,
  68     }, {
  69         'url': 'http://www.tagesschau.de/multimedia/sendung/nm-3475.html',
  70         'only_matching': True,
  71     }, {
  72         'url': 'http://www.tagesschau.de/multimedia/sendung/weltspiegel-3167.html',
  73         'only_matching': True,
  74     }, {
  75         'url': 'http://www.tagesschau.de/multimedia/tsvorzwanzig-959.html',
  76         'only_matching': True,
  77     }, {
  78         'url': 'http://www.tagesschau.de/multimedia/sendung/bab/bab-3299~_bab-sendung-209.html',
  79         'only_matching': True,
  80     }, {
  81         'url': 'http://www.tagesschau.de/multimedia/video/video-102303~_bab-sendung-211.html',
  82         'only_matching': True,
  83     }, {
  84         'url': 'http://www.tagesschau.de/100sekunden/index.html',
  85         'only_matching': True,
  86     }, {
  87         # playlist article with collapsing sections
  88         'url': 'http://www.tagesschau.de/wirtschaft/faq-freihandelszone-eu-usa-101.html',
  89         'only_matching': True,
  90     }]
  91
  92     def _real_extract(self, url):
  93         mobj = self._match_valid_url(url)
  94         video_id = mobj.group('id') or mobj.group('path')
  95         display_id = video_id.lstrip('-')
  96
  97         webpage = self._download_webpage(url, display_id)
  98
  99         title = self._html_search_regex(
 100             r'<span[^>]*class="headline"[^>]*>(.+?)</span>',
 101             webpage, 'title', default=None) or self._og_search_title(webpage, fatal=False)
 102
 103         entries = []
 104         videos = re.findall(r'<div[^>]+>', webpage)
 105         num = 0
 106         for video in videos:
 107             video = extract_attributes(video).get('data-config')
 108             if not video:
 109                 continue
 110             video = self._parse_json(video, video_id, transform_source=js_to_json, fatal=False)
 111             video_formats = try_get(video, lambda x: x['mc']['_mediaArray'][0]['_mediaStreamArray'])
 112             if not video_formats:
 113                 continue
 114             num += 1
 115             for video_format in video_formats:
 116                 media_url = video_format.get('_stream') or ''
 117                 formats = []
 118                 if media_url.endswith('master.m3u8'):
 119                     formats = self._extract_m3u8_formats(media_url, video_id, 'mp4', m3u8_id='hls')
 120                 elif media_url.endswith('.hi.mp3') and media_url.startswith('https://download'):
 121                     formats = [{
 122                         'url': media_url,
 123                         'vcodec': 'none',
 124                     }]
 125                 if not formats:
 126                     continue
 127                 entries.append({
 128                     'id': '%s-%d' % (display_id, num),
 129                     'title': try_get(video, lambda x: x['mc']['_title']),
 130                     'duration': int_or_none(try_get(video, lambda x: x['mc']['_duration'])),
 131                     'formats': formats
 132                 })
 133         if len(entries) > 1:
 134             return self.playlist_result(entries, display_id, title)
 135         formats = entries[0]['formats']
 136         video_info = self._search_json_ld(webpage, video_id)
 137         description = video_info.get('description')
 138         thumbnail = self._og_search_thumbnail(webpage) or video_info.get('thumbnail')
 139         timestamp = video_info.get('timestamp')
 140         title = title or video_info.get('description')
 141
 142         return {
 143             'id': display_id,
 144             'title': title,
 145             'thumbnail': thumbnail,
 146             'formats': formats,
 147             'timestamp': timestamp,
 148             'description': description,
 149         }