yt_dlp/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     unified_timestamp,
  13     xpath_text,
  14 )
  15
  16
  17 class PhoenixIE(ZDFBaseIE):
  18     IE_NAME = 'phoenix.de'
  19     _VALID_URL = r'https?://(?:www\.)?phoenix\.de/(?:[^/]+/)*[^/?#&]*-a-(?P<id>\d+)\.html'
  20     _TESTS = [{
  21         # Same as https://www.zdf.de/politik/phoenix-sendungen/wohin-fuehrt-der-protest-in-der-pandemie-100.html
  22         'url': 'https://www.phoenix.de/sendungen/ereignisse/corona-nachgehakt/wohin-fuehrt-der-protest-in-der-pandemie-a-2050630.html',
  23         'md5': '34ec321e7eb34231fd88616c65c92db0',
  24         'info_dict': {
  25             'id': '210222_phx_nachgehakt_corona_protest',
  26             'ext': 'mp4',
  27             'title': 'Wohin führt der Protest in der Pandemie?',
  28             'description': 'md5:7d643fe7f565e53a24aac036b2122fbd',
  29             'duration': 1691,
  30             'timestamp': 1613906100,
  31             'upload_date': '20210221',
  32             'uploader': 'Phoenix',
  33             'channel': 'corona nachgehakt',
  34         },
  35     }, {
  36         # Youtube embed
  37         'url': 'https://www.phoenix.de/sendungen/gespraeche/phoenix-streitgut-brennglas-corona-a-1965505.html',
  38         'info_dict': {
  39             'id': 'hMQtqFYjomk',
  40             'ext': 'mp4',
  41             'title': 'phoenix streitgut: Brennglas Corona - Wie gerecht ist unsere Gesellschaft?',
  42             'description': 'md5:ac7a02e2eb3cb17600bc372e4ab28fdd',
  43             'duration': 3509,
  44             'upload_date': '20201219',
  45             'uploader': 'phoenix',
  46             'uploader_id': 'phoenix',
  47         },
  48         'params': {
  49             'skip_download': True,
  50         },
  51     }, {
  52         'url': 'https://www.phoenix.de/entwicklungen-in-russland-a-2044720.html',
  53         'only_matching': True,
  54     }, {
  55         # no media
  56         'url': 'https://www.phoenix.de/sendungen/dokumentationen/mit-dem-jumbo-durch-die-nacht-a-89625.html',
  57         'only_matching': True,
  58     }, {
  59         # Same as https://www.zdf.de/politik/phoenix-sendungen/die-gesten-der-maechtigen-100.html
  60         'url': 'https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche',
  61         'only_matching': True,
  62     }]
  63
  64     def _real_extract(self, url):
  65         article_id = self._match_id(url)
  66
  67         article = self._download_json(
  68             'https://www.phoenix.de/response/id/%s' % article_id, article_id,
  69             'Downloading article JSON')
  70
  71         video = article['absaetze'][0]
  72         title = video.get('titel') or article.get('subtitel')
  73
  74         if video.get('typ') == 'video-youtube':
  75             video_id = video['id']
  76             return self.url_result(
  77                 video_id, ie=YoutubeIE.ie_key(), video_id=video_id,
  78                 video_title=title)
  79
  80         video_id = compat_str(video.get('basename') or video.get('content'))
  81
  82         details = self._download_xml(
  83             'https://www.phoenix.de/php/mediaplayer/data/beitrags_details.php',
  84             video_id, 'Downloading details XML', query={
  85                 'ak': 'web',
  86                 'ptmd': 'true',
  87                 'id': video_id,
  88                 'profile': 'player2',
  89             })
  90
  91         title = title or xpath_text(
  92             details, './/information/title', 'title', fatal=True)
  93         content_id = xpath_text(
  94             details, './/video/details/basename', 'content id', fatal=True)
  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         timestamp = unified_timestamp(xpath_text(details, './/details/airtime'))
 101
 102         thumbnails = []
 103         for node in details.findall('.//teaserimages/teaserimage'):
 104             thumbnail_url = node.text
 105             if not thumbnail_url:
 106                 continue
 107             thumbnail = {
 108                 'url': thumbnail_url,
 109             }
 110             thumbnail_key = node.get('key')
 111             if thumbnail_key:
 112                 m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
 113                 if m:
 114                     thumbnail['width'] = int(m.group(1))
 115                     thumbnail['height'] = int(m.group(2))
 116             thumbnails.append(thumbnail)
 117
 118         return merge_dicts(info, {
 119             'id': content_id,
 120             'title': title,
 121             'description': xpath_text(details, './/information/detail'),
 122             'duration': int_or_none(xpath_text(details, './/details/lengthSec')),
 123             'thumbnails': thumbnails,
 124             'timestamp': timestamp,
 125             'uploader': xpath_text(details, './/details/channel'),
 126             'uploader_id': xpath_text(details, './/details/originChannelId'),
 127             'channel': xpath_text(details, './/details/originChannelTitle'),
 128         })