youtube_dl/extractor/phoenix.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .youtube import YoutubeIE
   7 from .zdf import ZDFBaseIE
   8 from ..compat import compat_str
   9 from ..utils import (
  10     int_or_none,
  11     merge_dicts,
  12     try_get,
  13     unified_timestamp,
  14     urljoin,
  15 )
  16
  17
  18 class PhoenixIE(ZDFBaseIE):
  19     IE_NAME = 'phoenix.de'
  20     _VALID_URL = r'https?://(?:www\.)?phoenix\.de/(?:[^/]+/)*[^/?#&]*-a-(?P<id>\d+)\.html'
  21     _TESTS = [{
  22         # Same as https://www.zdf.de/politik/phoenix-sendungen/wohin-fuehrt-der-protest-in-der-pandemie-100.html
  23         'url': 'https://www.phoenix.de/sendungen/ereignisse/corona-nachgehakt/wohin-fuehrt-der-protest-in-der-pandemie-a-2050630.html',
  24         'md5': '34ec321e7eb34231fd88616c65c92db0',
  25         'info_dict': {
  26             'id': '210222_phx_nachgehakt_corona_protest',
  27             'ext': 'mp4',
  28             'title': 'Wohin führt der Protest in der Pandemie?',
  29             'description': 'md5:7d643fe7f565e53a24aac036b2122fbd',
  30             'duration': 1691,
  31             'timestamp': 1613902500,
  32             'upload_date': '20210221',
  33             'uploader': 'Phoenix',
  34             'series': 'corona nachgehakt',
  35             'episode': 'Wohin führt der Protest in der Pandemie?',
  36         },
  37     }, {
  38         # Youtube embed
  39         'url': 'https://www.phoenix.de/sendungen/gespraeche/phoenix-streitgut-brennglas-corona-a-1965505.html',
  40         'info_dict': {
  41             'id': 'hMQtqFYjomk',
  42             'ext': 'mp4',
  43             'title': 'phoenix streitgut: Brennglas Corona - Wie gerecht ist unsere Gesellschaft?',
  44             'description': 'md5:ac7a02e2eb3cb17600bc372e4ab28fdd',
  45             'duration': 3509,
  46             'upload_date': '20201219',
  47             'uploader': 'phoenix',
  48             'uploader_id': 'phoenix',
  49         },
  50         'params': {
  51             'skip_download': True,
  52         },
  53     }, {
  54         'url': 'https://www.phoenix.de/entwicklungen-in-russland-a-2044720.html',
  55         'only_matching': True,
  56     }, {
  57         # no media
  58         'url': 'https://www.phoenix.de/sendungen/dokumentationen/mit-dem-jumbo-durch-die-nacht-a-89625.html',
  59         'only_matching': True,
  60     }, {
  61         # Same as https://www.zdf.de/politik/phoenix-sendungen/die-gesten-der-maechtigen-100.html
  62         'url': 'https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche',
  63         'only_matching': True,
  64     }]
  65
  66     def _real_extract(self, url):
  67         article_id = self._match_id(url)
  68
  69         article = self._download_json(
  70             'https://www.phoenix.de/response/id/%s' % article_id, article_id,
  71             'Downloading article JSON')
  72
  73         video = article['absaetze'][0]
  74         title = video.get('titel') or article.get('subtitel')
  75
  76         if video.get('typ') == 'video-youtube':
  77             video_id = video['id']
  78             return self.url_result(
  79                 video_id, ie=YoutubeIE.ie_key(), video_id=video_id,
  80                 video_title=title)
  81
  82         video_id = compat_str(video.get('basename') or video.get('content'))
  83
  84         details = self._download_json(
  85             'https://www.phoenix.de/php/mediaplayer/data/beitrags_details.php',
  86             video_id, 'Downloading details JSON', query={
  87                 'ak': 'web',
  88                 'ptmd': 'true',
  89                 'id': video_id,
  90                 'profile': 'player2',
  91             })
  92
  93         title = title or details['title']
  94         content_id = details['tracking']['nielsen']['content']['assetid']
  95
  96         info = self._extract_ptmd(
  97             'https://tmd.phoenix.de/tmd/2/ngplayer_2_3/vod/ptmd/phoenix/%s' % content_id,
  98             content_id, None, url)
  99
 100         duration = int_or_none(try_get(
 101             details, lambda x: x['tracking']['nielsen']['content']['length']))
 102         timestamp = unified_timestamp(details.get('editorialDate'))
 103         series = try_get(
 104             details, lambda x: x['tracking']['nielsen']['content']['program'],
 105             compat_str)
 106         episode = title if details.get('contentType') == 'episode' else None
 107
 108         thumbnails = []
 109         teaser_images = try_get(details, lambda x: x['teaserImageRef']['layouts'], dict) or {}
 110         for thumbnail_key, thumbnail_url in teaser_images.items():
 111             thumbnail_url = urljoin(url, thumbnail_url)
 112             if not thumbnail_url:
 113                 continue
 114             thumbnail = {
 115                 'url': thumbnail_url,
 116             }
 117             m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
 118             if m:
 119                 thumbnail['width'] = int(m.group(1))
 120                 thumbnail['height'] = int(m.group(2))
 121             thumbnails.append(thumbnail)
 122
 123         return merge_dicts(info, {
 124             'id': content_id,
 125             'title': title,
 126             'description': details.get('leadParagraph'),
 127             'duration': duration,
 128             'thumbnails': thumbnails,
 129             'timestamp': timestamp,
 130             'uploader': details.get('tvService'),
 131             'series': series,
 132             'episode': episode,
 133         })