yt-dlp/youtube_dl/extractor/wistia.py

63 lines
1.7 KiB
Python
Raw Normal View History

2014-06-24 08:34:39 -04:00
from __future__ import unicode_literals
2013-12-06 03:15:04 -05:00
import json
import re
from .common import InfoExtractor
class WistiaIE(InfoExtractor):
2014-06-24 08:34:39 -04:00
_VALID_URL = r'https?://(?:fast\.)?wistia\.net/embed/iframe/(?P<id>[a-z0-9]+)'
2013-12-06 03:15:04 -05:00
_TEST = {
2014-06-24 08:34:39 -04:00
'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt',
'md5': 'cafeb56ec0c53c18c97405eecb3133df',
'info_dict': {
'id': 'sh7fpupwlt',
'ext': 'mov',
'title': 'Being Resourceful',
'duration': 117,
2013-12-06 03:15:04 -05:00
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
data_json = self._html_search_regex(
2014-06-24 08:34:39 -04:00
r'Wistia\.iframeInit\((.*?), {}\);', webpage, 'video data')
2013-12-06 03:15:04 -05:00
data = json.loads(data_json)
formats = []
thumbnails = []
for atype, a in data['assets'].items():
if atype == 'still':
thumbnails.append({
'url': a['url'],
'resolution': '%dx%d' % (a['width'], a['height']),
})
continue
if atype == 'preview':
continue
formats.append({
'format_id': atype,
'url': a['url'],
'width': a['width'],
'height': a['height'],
'filesize': a['size'],
'ext': a['ext'],
'preference': 1 if atype == 'original' else None,
2013-12-06 03:15:04 -05:00
})
2013-12-25 09:20:14 -05:00
self._sort_formats(formats)
2013-12-06 03:15:04 -05:00
return {
'id': video_id,
'title': data['name'],
'formats': formats,
'thumbnails': thumbnails,
2014-06-24 08:34:39 -04:00
'duration': data.get('duration'),
2013-12-06 03:15:04 -05:00
}