0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-30 02:01:05 +00:00
yt-dlp/yt_dlp/extractor/fivetv.py
2022-10-31 17:41:48 +05:30

85 lines
3 KiB
Python
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

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.

from .common import InfoExtractor
from ..utils import int_or_none
class FiveTVIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:www\.)?5-tv\.ru/
(?:
(?:[^/]+/)+(?P<id>\d+)|
(?P<path>[^/?#]+)(?:[/?#])?
)
'''
_TESTS = [{
'url': 'http://5-tv.ru/news/96814/',
'md5': 'bbff554ad415ecf5416a2f48c22d9283',
'info_dict': {
'id': '96814',
'ext': 'mp4',
'title': 'Россияне выбрали имя для общенациональной платежной системы',
'description': 'md5:a8aa13e2b7ad36789e9f77a74b6de660',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 180,
},
}, {
'url': 'http://5-tv.ru/video/1021729/',
'info_dict': {
'id': '1021729',
'ext': 'mp4',
'title': '3D принтер',
'description': 'md5:d76c736d29ef7ec5c0cf7d7c65ffcb41',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 180,
},
}, {
# redirect to https://www.5-tv.ru/projects/1000095/izvestia-glavnoe/
'url': 'http://www.5-tv.ru/glavnoe/#itemDetails',
'info_dict': {
'id': 'glavnoe',
'ext': 'mp4',
'title': r're:^Итоги недели с \d+ по \d+ \w+ \d{4} года$',
'thumbnail': r're:^https?://.*\.jpg$',
},
'skip': 'redirect to «Известия. Главное» project page',
}, {
'url': 'http://www.5-tv.ru/glavnoe/broadcasts/508645/',
'only_matching': True,
}, {
'url': 'http://5-tv.ru/films/1507502/',
'only_matching': True,
}, {
'url': 'http://5-tv.ru/programs/broadcast/508713/',
'only_matching': True,
}, {
'url': 'http://5-tv.ru/angel/',
'only_matching': True,
}, {
'url': 'http://www.5-tv.ru/schedule/?iframe=true&width=900&height=450',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id = mobj.group('id') or mobj.group('path')
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
[r'<div[^>]+?class="(?:flow)?player[^>]+?data-href="([^"]+)"',
r'<a[^>]+?href="([^"]+)"[^>]+?class="videoplayer"'],
webpage, 'video url')
title = self._generic_title('', webpage)
duration = int_or_none(self._og_search_property(
'video:duration', webpage, 'duration', default=None))
return {
'id': video_id,
'url': video_url,
'title': title,
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'duration': duration,
}