2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..compat import compat_urllib_request
15 class TwitterCardIE(InfoExtractor):
16 IE_NAME = 'twitter:card'
17 _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/cards/tfw/v1/(?P<id>\d+)'
20 'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889',
21 'md5': '7d2f6b4d2eb841a7ccc893d479bfceb4',
23 'id': '560070183650213889',
25 'title': 'TwitterCard',
26 'thumbnail': 're:^https?://.*\.jpg$',
31 'url': 'https://twitter.com/i/cards/tfw/v1/623160978427936768',
32 'md5': '7ee2a553b63d1bccba97fbed97d9e1c8',
34 'id': '623160978427936768',
36 'title': 'TwitterCard',
37 'thumbnail': 're:^https?://.*\.jpg',
43 def _real_extract(self, url):
44 video_id = self._match_id(url)
46 # Different formats served for different User-Agents
48 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/20.0 (Chrome)', # mp4
49 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0', # webm
54 for user_agent in USER_AGENTS:
55 request = compat_urllib_request.Request(url)
56 request.add_header('User-Agent', user_agent)
57 webpage = self._download_webpage(request, video_id)
59 config = self._parse_json(
60 unescapeHTML(self._search_regex(
61 r'data-player-config="([^"]+)"', webpage, 'data player config')),
63 if 'playlist' not in config:
64 if 'vmapUrl' in config:
65 vmap_data = self._download_xml(config['vmapUrl'], video_id)
66 video_url = xpath_text(vmap_data, './/MediaFile').strip()
70 break # same video regardless of UA
73 video_url = config['playlist'][0]['source']
79 m = re.search(r'/(?P<width>\d+)x(?P<height>\d+)/', video_url)
82 'width': int(m.group('width')),
83 'height': int(m.group('height')),
86 self._sort_formats(formats)
88 thumbnail = config.get('posterImageUrl')
89 duration = float_or_none(config.get('duration'))
93 'title': 'TwitterCard',
94 'thumbnail': thumbnail,
100 class TwitterIE(InfoExtractor):
102 _VALID_URL = r'https?://(?:www|m|mobile)?\.?twitter\.com/(?P<id>[^/]+/status/\d+)'
105 'url': 'https://twitter.com/freethenipple/status/643211948184596480',
106 'md5': '31cd83a116fc41f99ae3d909d4caf6a0',
108 'id': '643211948184596480',
110 'title': 'freethenipple - FTN supporters on Hollywood Blvd today!',
111 'thumbnail': 're:^https?://.*\.jpg',
113 'description': 'FREE THE NIPPLE on Twitter: "FTN supporters on Hollywood Blvd today! http://t.co/c7jHH749xJ"',
114 'uploader': 'FREE THE NIPPLE',
115 'uploader_id': 'freethenipple',
119 def _real_extract(self, url):
120 id = self._match_id(url)
121 username, twid = re.match(r'([^/]+)/status/(\d+)', id).groups()
123 url = re.sub(r'https?://(m|mobile)\.', 'https://', url)
124 webpage = self._download_webpage(url, 'tweet: ' + url)
125 description = self._html_search_regex('<title>\s*(.+?)\s*</title>', webpage, 'title')
126 title = description.replace('\n', ' ')
127 splitdesc = re.match(r'^(.+?)\s*on Twitter:\s* "(.+?)"$', title)
129 name, title = splitdesc.groups()
130 title = re.sub(r'\s*https?://[^ ]+', '', title) # strip 'https -_t.co_BJYgOjSeGA' junk from filenames
131 card_id = self._search_regex(r'["\']/i/cards/tfw/v1/(\d+)', webpage, '/i/card/...')
132 card_url = 'https://twitter.com/i/cards/tfw/v1/' + card_id
134 '_type': 'url_transparent',
135 'ie_key': 'TwitterCard',
136 'uploader_id': username,
140 'description': description,
141 'title': username + ' - ' + title,