yt-dlp/youtube_dl/extractor/thescene.py

69 lines
2.1 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urlparse
2017-02-24 14:22:29 +00:00
from ..utils import (
int_or_none,
qualities,
)
class TheSceneIE(InfoExtractor):
2016-09-08 11:29:05 +00:00
_VALID_URL = r'https?://thescene\.com/watch/[^/]+/(?P<id>[^/#?]+)'
_TEST = {
'url': 'https://thescene.com/watch/vogue/narciso-rodriguez-spring-2013-ready-to-wear',
'info_dict': {
'id': '520e8faac2b4c00e3c6e5f43',
'ext': 'mp4',
'title': 'Narciso Rodriguez: Spring 2013 Ready-to-Wear',
'display_id': 'narciso-rodriguez-spring-2013-ready-to-wear',
2017-02-24 14:22:29 +00:00
'duration': 127,
'series': 'Style.com Fashion Shows',
'season': 'Ready To Wear Spring 2013',
'tags': list,
'categories': list,
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
player_url = compat_urlparse.urljoin(
url,
self._html_search_regex(
r'id=\'js-player-script\'[^>]+src=\'(.+?)\'', webpage, 'player url'))
player = self._download_webpage(player_url, display_id)
info = self._parse_json(
self._search_regex(
r'(?m)video\s*:\s*({.+?}),$', player, 'info json'),
display_id)
2017-02-24 14:22:29 +00:00
video_id = info['id']
title = info['title']
qualities_order = qualities(('low', 'high'))
formats = [{
'format_id': '{0}-{1}'.format(f['type'].split('/')[0], f['quality']),
'url': f['src'],
'quality': qualities_order(f['quality']),
} for f in info['sources']]
self._sort_formats(formats)
return {
2017-02-24 14:22:29 +00:00
'id': video_id,
'display_id': display_id,
2017-02-24 14:22:29 +00:00
'title': title,
'formats': formats,
'thumbnail': info.get('poster_frame'),
2017-02-24 14:22:29 +00:00
'duration': int_or_none(info.get('duration')),
'series': info.get('series_title'),
'season': info.get('season_title'),
'tags': info.get('tags'),
'categories': info.get('categories'),
}