yt_dlp/extractor/hrfensehen.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import re
   6
   7 from ..utils import int_or_none, unified_timestamp, unescapeHTML
   8 from .common import InfoExtractor
   9
  10
  11 class HRFernsehenIE(InfoExtractor):
  12     IE_NAME = 'hrfernsehen'
  13     _VALID_URL = r'^https?://www\.(?:hr-fernsehen|hessenschau)\.de/.*,video-(?P<id>[0-9]{6})\.html'
  14
  15     _TESTS = [{
  16         'url': 'https://www.hessenschau.de/tv-sendung/hessenschau-vom-26082020,video-130546.html',
  17         'md5': '5c4e0ba94677c516a2f65a84110fc536',
  18         'info_dict': {
  19             'id': '130546',
  20             'ext': 'mp4',
  21             'description': 'Sturmtief Kirsten fegt über Hessen / Die Corona-Pandemie – eine Chronologie / '
  22                            'Sterbehilfe: Die Lage in Hessen / Miss Hessen leitet zwei eigene Unternehmen / '
  23                            'Pop-Up Museum zeigt Schwarze Unterhaltung und Black Music',
  24             'subtitles': {'de': [{
  25                 'url': 'https://hr-a.akamaihd.net/video/as/hessenschau/2020_08/hrLogo_200826200407_L385592_512x288-25p-500kbit.vtt'
  26             }]},
  27             'timestamp': 1598470200,
  28             'upload_date': '20200826',
  29             'thumbnail': 'https://www.hessenschau.de/tv-sendung/hs_ganz-1554~_t-1598465545029_v-16to9__medium.jpg',
  30             'title': 'hessenschau vom 26.08.2020'
  31         }
  32     }, {
  33         'url': 'https://www.hr-fernsehen.de/sendungen-a-z/mex/sendungen/fair-und-gut---was-hinter-aldis-eigenem-guetesiegel-steckt,video-130544.html',
  34         'only_matching': True
  35     }]
  36
  37     _GEO_COUNTRIES = ['DE']
  38
  39     def extract_airdate(self, loader_data):
  40         airdate_str = loader_data.get('mediaMetadata', {}).get('agf', {}).get('airdate')
  41
  42         if airdate_str is None:
  43             return None
  44
  45         return unified_timestamp(airdate_str)
  46
  47     def extract_formats(self, loader_data):
  48         stream_formats = []
  49         for stream_obj in loader_data["videoResolutionLevels"]:
  50             stream_format = {
  51                 'format_id': str(stream_obj['verticalResolution']) + "p",
  52                 'height': stream_obj['verticalResolution'],
  53                 'url': stream_obj['url'],
  54             }
  55
  56             quality_information = re.search(r'([0-9]{3,4})x([0-9]{3,4})-([0-9]{2})p-([0-9]{3,4})kbit',
  57                                             stream_obj['url'])
  58             if quality_information:
  59                 stream_format['width'] = int_or_none(quality_information.group(1))
  60                 stream_format['height'] = int_or_none(quality_information.group(2))
  61                 stream_format['fps'] = int_or_none(quality_information.group(3))
  62                 stream_format['tbr'] = int_or_none(quality_information.group(4))
  63
  64             stream_formats.append(stream_format)
  65
  66         self._sort_formats(stream_formats)
  67         return stream_formats
  68
  69     def _real_extract(self, url):
  70         video_id = self._match_id(url)
  71         webpage = self._download_webpage(url, video_id)
  72
  73         title = self._html_search_meta(
  74             ['og:title', 'twitter:title', 'name'], webpage)
  75         description = self._html_search_meta(
  76             ['description'], webpage)
  77
  78         loader_str = unescapeHTML(self._search_regex(r"data-new-hr-mediaplayer-loader='([^']*)'", webpage, "ardloader"))
  79         loader_data = json.loads(loader_str)
  80
  81         info = {
  82             'id': video_id,
  83             'title': title,
  84             'description': description,
  85             'formats': self.extract_formats(loader_data),
  86             'timestamp': self.extract_airdate(loader_data)
  87         }
  88
  89         if "subtitle" in loader_data:
  90             info["subtitles"] = {"de": [{"url": loader_data["subtitle"]}]}
  91
  92         thumbnails = list(set([t for t in loader_data.get("previewImageUrl", {}).values()]))
  93         if len(thumbnails) > 0:
  94             info["thumbnails"] = [{"url": t} for t in thumbnails]
  95
  96         return info