yt_dlp/extractor/phoenix.py

   1 import re
   2
   3 from .youtube import YoutubeIE
   4 from .zdf import ZDFBaseIE
   5 from ..utils import (
   6     int_or_none,
   7     merge_dicts,
   8     try_get,
   9     unified_timestamp,
  10     urljoin,
  11 )
  12
  13
  14 class PhoenixIE(ZDFBaseIE):
  15     IE_NAME = 'phoenix.de'
  16     _VALID_URL = r'https?://(?:www\.)?phoenix\.de/(?:[^/]+/)*[^/?#&]*-a-(?P<id>\d+)\.html'
  17     _TESTS = [{
  18         # Same as https://www.zdf.de/politik/phoenix-sendungen/wohin-fuehrt-der-protest-in-der-pandemie-100.html
  19         'url': 'https://www.phoenix.de/sendungen/ereignisse/corona-nachgehakt/wohin-fuehrt-der-protest-in-der-pandemie-a-2050630.html',
  20         'md5': '34ec321e7eb34231fd88616c65c92db0',
  21         'info_dict': {
  22             'id': '210222_phx_nachgehakt_corona_protest',
  23             'ext': 'mp4',
  24             'title': 'Wohin führt der Protest in der Pandemie?',
  25             'description': 'md5:7d643fe7f565e53a24aac036b2122fbd',
  26             'duration': 1691,
  27             'timestamp': 1613902500,
  28             'upload_date': '20210221',
  29             'uploader': 'Phoenix',
  30             'series': 'corona nachgehakt',
  31             'episode': 'Wohin führt der Protest in der Pandemie?',
  32         },
  33     }, {
  34         # Youtube embed
  35         'url': 'https://www.phoenix.de/sendungen/gespraeche/phoenix-streitgut-brennglas-corona-a-1965505.html',
  36         'info_dict': {
  37             'id': 'hMQtqFYjomk',
  38             'ext': 'mp4',
  39             'title': 'phoenix streitgut: Brennglas Corona - Wie gerecht ist unsere Gesellschaft?',
  40             'description': 'md5:ac7a02e2eb3cb17600bc372e4ab28fdd',
  41             'duration': 3509,
  42             'upload_date': '20201219',
  43             'uploader': 'phoenix',
  44             'uploader_id': 'phoenix',
  45         },
  46         'params': {
  47             'skip_download': True,
  48         },
  49     }, {
  50         'url': 'https://www.phoenix.de/entwicklungen-in-russland-a-2044720.html',
  51         'only_matching': True,
  52     }, {
  53         # no media
  54         'url': 'https://www.phoenix.de/sendungen/dokumentationen/mit-dem-jumbo-durch-die-nacht-a-89625.html',
  55         'only_matching': True,
  56     }, {
  57         # Same as https://www.zdf.de/politik/phoenix-sendungen/die-gesten-der-maechtigen-100.html
  58         'url': 'https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche',
  59         'only_matching': True,
  60     }]
  61
  62     def _real_extract(self, url):
  63         article_id = self._match_id(url)
  64
  65         article = self._download_json(
  66             f'https://www.phoenix.de/response/id/{article_id}', article_id,
  67             'Downloading article JSON')
  68
  69         video = article['absaetze'][0]
  70         title = video.get('titel') or article.get('subtitel')
  71
  72         if video.get('typ') == 'video-youtube':
  73             video_id = video['id']
  74             return self.url_result(
  75                 video_id, ie=YoutubeIE.ie_key(), video_id=video_id,
  76                 video_title=title)
  77
  78         video_id = str(video.get('basename') or video.get('content'))
  79
  80         details = self._download_json(
  81             'https://www.phoenix.de/php/mediaplayer/data/beitrags_details.php',
  82             video_id, 'Downloading details JSON', query={
  83                 'ak': 'web',
  84                 'ptmd': 'true',
  85                 'id': video_id,
  86                 'profile': 'player2',
  87             })
  88
  89         title = title or details['title']
  90         content_id = details['tracking']['nielsen']['content']['assetid']
  91
  92         info = self._extract_ptmd(
  93             f'https://tmd.phoenix.de/tmd/2/ngplayer_2_3/vod/ptmd/phoenix/{content_id}',
  94             content_id, None, url)
  95
  96         duration = int_or_none(try_get(
  97             details, lambda x: x['tracking']['nielsen']['content']['length']))
  98         timestamp = unified_timestamp(details.get('editorialDate'))
  99         series = try_get(
 100             details, lambda x: x['tracking']['nielsen']['content']['program'],
 101             str)
 102         episode = title if details.get('contentType') == 'episode' else None
 103
 104         thumbnails = []
 105         teaser_images = try_get(details, lambda x: x['teaserImageRef']['layouts'], dict) or {}
 106         for thumbnail_key, thumbnail_url in teaser_images.items():
 107             thumbnail_url = urljoin(url, thumbnail_url)
 108             if not thumbnail_url:
 109                 continue
 110             thumbnail = {
 111                 'url': thumbnail_url,
 112             }
 113             m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
 114             if m:
 115                 thumbnail['width'] = int(m.group(1))
 116                 thumbnail['height'] = int(m.group(2))
 117             thumbnails.append(thumbnail)
 118
 119         return merge_dicts(info, {
 120             'id': content_id,
 121             'title': title,
 122             'description': details.get('leadParagraph'),
 123             'duration': duration,
 124             'thumbnails': thumbnails,
 125             'timestamp': timestamp,
 126             'uploader': details.get('tvService'),
 127             'series': series,
 128             'episode': episode,
 129         })