logo

youtube-dl

[mirror] Download/Watch videos from video hostersgit clone https://hacktivis.me/git/mirror/youtube-dl.git

hrfernsehen.py (3877B)

    

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