yt-dlp/youtube_dl/extractor/byutv.py

52 lines
1.7 KiB
Python
Raw Normal View History

2014-03-24 17:12:15 +01:00
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
2014-04-10 14:37:55 +02:00
from ..utils import ExtractorError
2014-03-24 17:12:15 +01:00
class BYUtvIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<video_id>[^/?#]+)'
_TEST = {
2014-11-05 15:43:53 +01:00
'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5',
'md5': '05850eb8c749e2ee05ad5a1c34668493',
2014-03-24 17:12:15 +01:00
'info_dict': {
2014-11-05 15:43:53 +01:00
'id': 'studio-c-season-5-episode-5',
2014-03-24 17:12:15 +01:00
'ext': 'mp4',
'description': 'md5:e07269172baff037f8e8bf9956bc9747',
2014-11-05 15:43:53 +01:00
'title': 'Season 5 Episode 5',
'thumbnail': 're:^https?://.*\.jpg$',
2015-12-04 16:18:02 +01:00
'duration': 1486.486,
2014-03-24 17:12:15 +01:00
},
2016-05-24 17:42:22 +02:00
'params': {
'skip_download': True,
},
'add_ie': ['Ooyala'],
2014-03-24 17:12:15 +01:00
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('video_id')
webpage = self._download_webpage(url, video_id)
episode_code = self._search_regex(
r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information')
episode_json = re.sub(
r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', episode_code)
ep = json.loads(episode_json)
if ep['providerType'] == 'Ooyala':
return {
'_type': 'url_transparent',
'ie_key': 'Ooyala',
'url': 'ooyala:%s' % ep['providerId'],
'id': video_id,
'title': ep['title'],
'description': ep.get('description'),
'thumbnail': ep.get('imageThumbnail'),
}
else:
raise ExtractorError('Unsupported provider %s' % ep['provider'])