1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-12-05 06:37:54 +01:00
youtube-dl/youtube_dl/extractor/charlierose.py

55 lines
1.8 KiB
Python
Raw Normal View History

2016-08-19 12:53:34 +02:00
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import remove_end
class CharlieRoseIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?charlierose\.com/(?:video|episode)(?:s|/player)/(?P<id>\d+)'
2016-08-21 20:06:47 +02:00
_TESTS = [{
2016-08-19 12:53:34 +02:00
'url': 'https://charlierose.com/videos/27996',
2016-08-21 20:06:47 +02:00
'md5': 'fda41d49e67d4ce7c2411fd2c4702e09',
2016-08-19 12:53:34 +02:00
'info_dict': {
'id': '27996',
'ext': 'mp4',
'title': 'Remembering Zaha Hadid',
'thumbnail': r're:^https?://.*\.jpg\?\d+',
2016-08-19 12:53:34 +02:00
'description': 'We revisit past conversations with Zaha Hadid, in memory of the world renowned Iraqi architect.',
2016-08-21 20:06:47 +02:00
'subtitles': {
'en': [{
'ext': 'vtt',
}],
},
2016-08-19 12:53:34 +02:00
},
2016-08-21 20:06:47 +02:00
}, {
'url': 'https://charlierose.com/videos/27996',
'only_matching': True,
}, {
'url': 'https://charlierose.com/episodes/30887?autoplay=true',
'only_matching': True,
2016-08-21 20:06:47 +02:00
}]
2016-08-19 12:53:34 +02:00
_PLAYER_BASE = 'https://charlierose.com/video/player/%s'
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(self._PLAYER_BASE % video_id, video_id)
title = remove_end(self._og_search_title(webpage), ' - Charlie Rose')
2016-08-21 20:06:47 +02:00
info_dict = self._parse_html5_media_entries(
self._PLAYER_BASE % video_id, webpage, video_id,
m3u8_entry_protocol='m3u8_native')[0]
2016-08-19 12:53:34 +02:00
2016-08-21 20:06:47 +02:00
self._sort_formats(info_dict['formats'])
self._remove_duplicate_formats(info_dict['formats'])
2016-08-19 12:53:34 +02:00
2016-08-21 20:06:47 +02:00
info_dict.update({
2016-08-19 12:53:34 +02:00
'id': video_id,
'title': title,
'thumbnail': self._og_search_thumbnail(webpage),
'description': self._og_search_description(webpage),
2016-08-21 20:06:47 +02:00
})
return info_dict