0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-23 02:25:11 +00:00
yt-dlp/yt_dlp/extractor/hrfensehen.py
bashonly c6387abc1a
[cleanup] Misc (#10807)
Closes #10751, Closes #10769, Closes #10791
Authored by: bashonly, Codenade, pzhlkj6612, seproDev, coletdjnz, grqz, Grub4K

Co-authored-by: Codenade <amadeus.dorian04@gmail.com>
Co-authored-by: Mozi <29089388+pzhlkj6612@users.noreply.github.com>
Co-authored-by: sepro <4618135+seproDev@users.noreply.github.com>
Co-authored-by: coletdjnz <coletdjnz@protonmail.com>
Co-authored-by: N/Ame <173015200+grqz@users.noreply.github.com>
Co-authored-by: Simon Sawicki <contact@grub4k.xyz>
2024-09-27 22:46:22 +00:00

88 lines
3.7 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import json
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
traverse_obj,
try_call,
unescapeHTML,
unified_timestamp,
)
class HRFernsehenIE(InfoExtractor):
IE_NAME = 'hrfernsehen'
_VALID_URL = r'https?://www\.(?:hr-fernsehen|hessenschau)\.de/.*,video-(?P<id>[0-9]{6})\.html'
_TESTS = [{
'url': 'https://www.hessenschau.de/tv-sendung/hessenschau-vom-26082020,video-130546.html',
'md5': '5c4e0ba94677c516a2f65a84110fc536',
'info_dict': {
'id': '130546',
'ext': 'mp4',
'description': 'Sturmtief Kirsten fegt über Hessen / Die Corona-Pandemie eine Chronologie / '
'Sterbehilfe: Die Lage in Hessen / Miss Hessen leitet zwei eigene Unternehmen / '
'Pop-Up Museum zeigt Schwarze Unterhaltung und Black Music',
'subtitles': {'de': [{
'url': 'https://hr-a.akamaihd.net/video/as/hessenschau/2020_08/hrLogo_200826200407_L385592_512x288-25p-500kbit.vtt',
}]},
'timestamp': 1598400000,
'upload_date': '20200826',
'thumbnail': 'https://www.hessenschau.de/tv-sendung/hs_ganz-1554~_t-1598465545029_v-16to9.jpg',
'title': 'hessenschau vom 26.08.2020',
'duration': 1654,
},
}, {
'url': 'https://www.hr-fernsehen.de/sendungen-a-z/mex/sendungen/fair-und-gut---was-hinter-aldis-eigenem-guetesiegel-steckt,video-130544.html',
'only_matching': True,
}]
_GEO_COUNTRIES = ['DE']
def extract_formats(self, loader_data):
stream_formats = []
data = loader_data['mediaCollection']['streams'][0]['media']
for inner in data[1:]:
stream_format = {
'format_id': try_call(lambda: f'{inner["maxHResolutionPx"]}p'),
'height': inner.get('maxHResolutionPx'),
'url': inner['url'],
}
quality_information = re.search(r'([0-9]{3,4})x([0-9]{3,4})-([0-9]{2})p-([0-9]{3,4})kbit',
inner['url'])
if quality_information:
stream_format['width'] = int_or_none(quality_information.group(1))
stream_format['height'] = int_or_none(quality_information.group(2))
stream_format['fps'] = int_or_none(quality_information.group(3))
stream_format['tbr'] = int_or_none(quality_information.group(4))
stream_formats.append(stream_format)
return stream_formats
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_meta(
['og:title', 'twitter:title', 'name'], webpage)
description = self._html_search_meta(
['description'], webpage)
loader_str = unescapeHTML(self._search_regex(r"data-(?:new-)?hr-mediaplayer-loader='([^']*)'", webpage, 'ardloader'))
loader_data = json.loads(loader_str)
subtitle = traverse_obj(loader_data, ('mediaCollection', 'subTitles', 0, 'sources', 0, 'url'))
return {
'id': video_id,
'title': title,
'description': description,
'formats': self.extract_formats(loader_data),
'subtitles': {'de': [{'url': subtitle}]},
'timestamp': unified_timestamp(self._search_regex(
r'<time\sdatetime="(\d{4}\W\d{1,2}\W\d{1,2})', webpage, 'datetime', fatal=False)),
'duration': int_or_none(traverse_obj(
loader_data, ('playerConfig', 'pluginData', 'trackingAti@all', 'richMedia', 'duration'))),
'thumbnail': self._search_regex(r'thumbnailUrl\W*([^"]+)', webpage, 'thumbnail', default=None),
}