0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-05 04:17:27 +00:00
yt-dlp/yt_dlp/extractor/historicfilms.py
sepro add96eb9f8
[cleanup] Add more ruff rules (#10149)
Authored by: seproDev

Reviewed-by: bashonly <88596187+bashonly@users.noreply.github.com>
Reviewed-by: Simon Sawicki <contact@grub4k.xyz>
2024-06-12 01:09:58 +02:00

45 lines
1.5 KiB
Python

from .common import InfoExtractor
from ..utils import parse_duration
class HistoricFilmsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?historicfilms\.com/(?:tapes/|play)(?P<id>\d+)'
_TEST = {
'url': 'http://www.historicfilms.com/tapes/4728',
'md5': 'd4a437aec45d8d796a38a215db064e9a',
'info_dict': {
'id': '4728',
'ext': 'mov',
'title': 'Historic Films: GP-7',
'description': 'md5:1a86a0f3ac54024e419aba97210d959a',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 2096,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
tape_id = self._search_regex(
[r'class="tapeId"[^>]*>([^<]+)<', r'tapeId\s*:\s*"([^"]+)"'],
webpage, 'tape id')
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
thumbnail = self._html_search_meta(
'thumbnailUrl', webpage, 'thumbnails') or self._og_search_thumbnail(webpage)
duration = parse_duration(self._html_search_meta(
'duration', webpage, 'duration'))
video_url = f'http://www.historicfilms.com/video/{tape_id}_{video_id}_web.mov'
return {
'id': video_id,
'url': video_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
}