1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-25 02:07:44 +00:00
youtube-dl/youtube_dl/extractor/wistia.py
2014-06-24 19:34:39 +07:00

62 lines
1.7 KiB
Python

from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
class WistiaIE(InfoExtractor):
_VALID_URL = r'https?://(?:fast\.)?wistia\.net/embed/iframe/(?P<id>[a-z0-9]+)'
_TEST = {
'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt',
'md5': 'cafeb56ec0c53c18c97405eecb3133df',
'info_dict': {
'id': 'sh7fpupwlt',
'ext': 'mov',
'title': 'Being Resourceful',
'duration': 117,
},
}
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(
r'Wistia\.iframeInit\((.*?), {}\);', webpage, 'video data')
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,
})
self._sort_formats(formats)
return {
'id': video_id,
'title': data['name'],
'formats': formats,
'thumbnails': thumbnails,
'duration': data.get('duration'),
}