[teachingchannel] fix extraction

This commit is contained in:
Remita Amine 2019-11-30 23:49:45 +01:00
parent ddfe50195b
commit 3765284476

View file

@ -1,35 +1,33 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .ooyala import OoyalaIE
class TeachingChannelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?teachingchannel\.org/videos/(?P<title>.+)'
_VALID_URL = r'https?://(?:www\.)?teachingchannel\.org/videos?/(?P<id>[^/?&#]+)'
_TEST = {
'url': 'https://www.teachingchannel.org/videos/teacher-teaming-evolution',
'md5': '3d6361864d7cac20b57c8784da17166f',
'info_dict': {
'id': 'F3bnlzbToeI6pLEfRyrlfooIILUjz4nM',
'id': '3swwlzkT',
'ext': 'mp4',
'title': 'A History of Teaming',
'description': 'md5:2a9033db8da81f2edffa4c99888140b3',
'duration': 422.255,
'duration': 422,
'upload_date': '20170316',
'timestamp': 1489691297,
},
'params': {
'skip_download': True,
},
'add_ie': ['Ooyala'],
'add_ie': ['JWPlatform'],
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
title = mobj.group('title')
webpage = self._download_webpage(url, title)
ooyala_code = self._search_regex(
r'data-embed-code=\'(.+?)\'', webpage, 'ooyala code')
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
mid = self._search_regex(
r'(?:data-mid=["\']|id=["\']jw-video-player-)([a-zA-Z0-9]{8})',
webpage, 'media id')
return OoyalaIE._build_url_result(ooyala_code)
return self.url_result('jwplatform:' + mid, 'JWPlatform', mid)