mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-11-25 19:52:11 +00:00
cea2582df2
URL does a redirect from dsc.discovery.com to www.discovery.com This commit fixes the correct URL.
47 lines
1.7 KiB
Python
47 lines
1.7 KiB
Python
from __future__ import unicode_literals
|
|
|
|
import re
|
|
import json
|
|
|
|
from .common import InfoExtractor
|
|
|
|
|
|
class DiscoveryIE(InfoExtractor):
|
|
_VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?'
|
|
_TEST = {
|
|
'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
|
|
'md5': 'e12614f9ee303a6ccef415cb0793eba2',
|
|
'info_dict': {
|
|
'id': '614784',
|
|
'ext': 'mp4',
|
|
'title': 'MythBusters: Mission Impossible Outtakes',
|
|
'description': ('Watch Jamie Hyneman and Adam Savage practice being'
|
|
' each other -- to the point of confusing Jamie\'s dog -- and '
|
|
'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s'
|
|
' back.'),
|
|
'duration': 156,
|
|
},
|
|
}
|
|
|
|
def _real_extract(self, url):
|
|
mobj = re.match(self._VALID_URL, url)
|
|
video_id = mobj.group('id')
|
|
webpage = self._download_webpage(url, video_id)
|
|
|
|
video_list_json = self._search_regex(r'var videoListJSON = ({.*?});',
|
|
webpage, 'video list', flags=re.DOTALL)
|
|
video_list = json.loads(video_list_json)
|
|
info = video_list['clips'][0]
|
|
formats = []
|
|
for f in info['mp4']:
|
|
formats.append(
|
|
{'url': f['src'], 'ext': 'mp4', 'tbr': int(f['bitrate'][:-1])})
|
|
|
|
return {
|
|
'id': info['contentId'],
|
|
'title': video_list['name'],
|
|
'formats': formats,
|
|
'description': info['videoCaption'],
|
|
'thumbnail': info.get('videoStillURL') or info.get('thumbnailURL'),
|
|
'duration': info['duration'],
|
|
}
|