yt_dlp/extractor/phoenix.py

   1 import re
   2
   3 from .youtube import YoutubeIE
   4 from .zdf import ZDFBaseIE
   5 from ..compat import compat_str
   6 from ..utils import (
   7     int_or_none,
   8     merge_dicts,
   9     try_get,
  10     unified_timestamp,
  11     urljoin,
  12 )
  13
  14
  15 class PhoenixIE(ZDFBaseIE):
  16     IE_NAME = 'phoenix.de'
  17     _VALID_URL = r'https?://(?:www\.)?phoenix\.de/(?:[^/]+/)*[^/?#&]*-a-(?P<id>\d+)\.html'
  18     _TESTS = [{
  19         # Same as https://www.zdf.de/politik/phoenix-sendungen/wohin-fuehrt-der-protest-in-der-pandemie-100.html
  20         'url': 'https://www.phoenix.de/sendungen/ereignisse/corona-nachgehakt/wohin-fuehrt-der-protest-in-der-pandemie-a-2050630.html',
  21         'md5': '34ec321e7eb34231fd88616c65c92db0',
  22         'info_dict': {
  23             'id': '210222_phx_nachgehakt_corona_protest',
  24             'ext': 'mp4',
  25             'title': 'Wohin führt der Protest in der Pandemie?',
  26             'description': 'md5:7d643fe7f565e53a24aac036b2122fbd',
  27             'duration': 1691,
  28             'timestamp': 1613902500,
  29             'upload_date': '20210221',
  30             'uploader': 'Phoenix',
  31             'series': 'corona nachgehakt',
  32             'episode': 'Wohin führt der Protest in der Pandemie?',
  33         },
  34     }, {
  35         # Youtube embed
  36         'url': 'https://www.phoenix.de/sendungen/gespraeche/phoenix-streitgut-brennglas-corona-a-1965505.html',
  37         'info_dict': {
  38             'id': 'hMQtqFYjomk',
  39             'ext': 'mp4',
  40             'title': 'phoenix streitgut: Brennglas Corona - Wie gerecht ist unsere Gesellschaft?',
  41             'description': 'md5:ac7a02e2eb3cb17600bc372e4ab28fdd',
  42             'duration': 3509,
  43             'upload_date': '20201219',
  44             'uploader': 'phoenix',
  45             'uploader_id': 'phoenix',
  46         },
  47         'params': {
  48             'skip_download': True,
  49         },
  50     }, {
  51         'url': 'https://www.phoenix.de/entwicklungen-in-russland-a-2044720.html',
  52         'only_matching': True,
  53     }, {
  54         # no media
  55         'url': 'https://www.phoenix.de/sendungen/dokumentationen/mit-dem-jumbo-durch-die-nacht-a-89625.html',
  56         'only_matching': True,
  57     }, {
  58         # Same as https://www.zdf.de/politik/phoenix-sendungen/die-gesten-der-maechtigen-100.html
  59         'url': 'https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche',
  60         'only_matching': True,
  61     }]
  62
  63     def _real_extract(self, url):
  64         article_id = self._match_id(url)
  65
  66         article = self._download_json(
  67             'https://www.phoenix.de/response/id/%s' % article_id, article_id,
  68             'Downloading article JSON')
  69
  70         video = article['absaetze'][0]
  71         title = video.get('titel') or article.get('subtitel')
  72
  73         if video.get('typ') == 'video-youtube':
  74             video_id = video['id']
  75             return self.url_result(
  76                 video_id, ie=YoutubeIE.ie_key(), video_id=video_id,
  77                 video_title=title)
  78
  79         video_id = compat_str(video.get('basename') or video.get('content'))
  80
  81         details = self._download_json(
  82             'https://www.phoenix.de/php/mediaplayer/data/beitrags_details.php',
  83             video_id, 'Downloading details JSON', query={
  84                 'ak': 'web',
  85                 'ptmd': 'true',
  86                 'id': video_id,
  87                 'profile': 'player2',
  88             })
  89
  90         title = title or details['title']
  91         content_id = details['tracking']['nielsen']['content']['assetid']
  92
  93         info = self._extract_ptmd(
  94             'https://tmd.phoenix.de/tmd/2/ngplayer_2_3/vod/ptmd/phoenix/%s' % content_id,
  95             content_id, None, url)
  96
  97         duration = int_or_none(try_get(
  98             details, lambda x: x['tracking']['nielsen']['content']['length']))
  99         timestamp = unified_timestamp(details.get('editorialDate'))
 100         series = try_get(
 101             details, lambda x: x['tracking']['nielsen']['content']['program'],
 102             compat_str)
 103         episode = title if details.get('contentType') == 'episode' else None
 104
 105         thumbnails = []
 106         teaser_images = try_get(details, lambda x: x['teaserImageRef']['layouts'], dict) or {}
 107         for thumbnail_key, thumbnail_url in teaser_images.items():
 108             thumbnail_url = urljoin(url, thumbnail_url)
 109             if not thumbnail_url:
 110                 continue
 111             thumbnail = {
 112                 'url': thumbnail_url,
 113             }
 114             m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
 115             if m:
 116                 thumbnail['width'] = int(m.group(1))
 117                 thumbnail['height'] = int(m.group(2))
 118             thumbnails.append(thumbnail)
 119
 120         return merge_dicts(info, {
 121             'id': content_id,
 122             'title': title,
 123             'description': details.get('leadParagraph'),
 124             'duration': duration,
 125             'thumbnails': thumbnails,
 126             'timestamp': timestamp,
 127             'uploader': details.get('tvService'),
 128             'series': series,
 129             'episode': episode,
 130         })