1 from __future__ import unicode_literals
5 from .common import InfoExtractor
6 from ..compat import compat_urllib_request
13 class TwitterCardIE(InfoExtractor):
14 _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/cards/tfw/v1/(?P<id>\d+)'
16 'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889',
17 'md5': 'a74f50b310c83170319ba16de6955192',
19 'id': '560070183650213889',
21 'title': 'TwitterCard',
22 'thumbnail': 're:^https?://.*\.jpg$',
27 def _real_extract(self, url):
28 video_id = self._match_id(url)
30 # Different formats served for different User-Agents
32 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/20.0 (Chrome)', # mp4
33 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0', # webm
38 for user_agent in USER_AGENTS:
39 request = compat_urllib_request.Request(url)
40 request.add_header('User-Agent', user_agent)
41 webpage = self._download_webpage(request, video_id)
43 config = self._parse_json(
44 unescapeHTML(self._search_regex(
45 r'data-player-config="([^"]+)"', webpage, 'data player config')),
48 video_url = config['playlist'][0]['source']
54 m = re.search(r'/(?P<width>\d+)x(?P<height>\d+)/', video_url)
57 'width': int(m.group('width')),
58 'height': int(m.group('height')),
61 self._sort_formats(formats)
63 thumbnail = config.get('posterImageUrl')
64 duration = float_or_none(config.get('duration'))
68 'title': 'TwitterCard',
69 'thumbnail': thumbnail,