2 from __future__ import unicode_literals
6 from .common import InfoExtractor
17 class TwitterBaseIE(InfoExtractor):
18 def _get_vmap_video_url(self, vmap_url, video_id):
19 vmap_data = self._download_xml(vmap_url, video_id)
20 return xpath_text(vmap_data, './/MediaFile').strip()
23 class TwitterCardIE(TwitterBaseIE):
24 IE_NAME = 'twitter:card'
25 _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/cards/tfw/v1/(?P<id>\d+)'
28 'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889',
29 'md5': '4fa26a35f9d1bf4b646590ba8e84be19',
31 'id': '560070183650213889',
33 'title': 'TwitterCard',
34 'thumbnail': 're:^https?://.*\.jpg$',
39 'url': 'https://twitter.com/i/cards/tfw/v1/623160978427936768',
40 'md5': '7ee2a553b63d1bccba97fbed97d9e1c8',
42 'id': '623160978427936768',
44 'title': 'TwitterCard',
45 'thumbnail': 're:^https?://.*\.jpg',
50 'url': 'https://twitter.com/i/cards/tfw/v1/654001591733886977',
51 'md5': 'b6f35e8b08a0bec6c8af77a2f4b3a814',
55 'title': 'Ubuntu 11.10 Overview',
56 'description': 'Take a quick peek at what\'s new and improved in Ubuntu 11.10.\n\nOnce installed take a look at 10 Things to Do After Installing: http://www.omgubuntu.co.uk/2011/10/10-things-to-do-after-installing-ubuntu-11-10/',
57 'upload_date': '20111013',
58 'uploader': 'OMG! Ubuntu!',
59 'uploader_id': 'omgubuntu',
61 'add_ie': ['Youtube'],
64 'url': 'https://twitter.com/i/cards/tfw/v1/665289828897005568',
65 'md5': 'ab2745d0b0ce53319a534fccaa986439',
69 'upload_date': '20151113',
70 'uploader_id': '1189339351084113920',
71 'uploader': '@ArsenalTerje',
72 'title': 'Vine by @ArsenalTerje',
78 def _real_extract(self, url):
79 video_id = self._match_id(url)
81 # Different formats served for different User-Agents
83 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/20.0 (Chrome)', # mp4
84 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0', # webm
89 for user_agent in USER_AGENTS:
90 request = sanitized_Request(url)
91 request.add_header('User-Agent', user_agent)
92 webpage = self._download_webpage(request, video_id)
94 iframe_url = self._html_search_regex(
95 r'<iframe[^>]+src="((?:https?:)?//(?:www.youtube.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"',
96 webpage, 'video iframe', default=None)
98 return self.url_result(iframe_url)
100 config = self._parse_json(self._html_search_regex(
101 r'data-player-config="([^"]+)"', webpage, 'data player config'),
103 if 'playlist' not in config:
104 if 'vmapUrl' in config:
106 'url': self._get_vmap_video_url(config['vmapUrl'], video_id),
108 break # same video regardless of UA
111 video_url = config['playlist'][0]['source']
117 m = re.search(r'/(?P<width>\d+)x(?P<height>\d+)/', video_url)
120 'width': int(m.group('width')),
121 'height': int(m.group('height')),
124 self._sort_formats(formats)
126 thumbnail = config.get('posterImageUrl')
127 duration = float_or_none(config.get('duration'))
131 'title': 'TwitterCard',
132 'thumbnail': thumbnail,
133 'duration': duration,
138 class TwitterIE(InfoExtractor):
140 _VALID_URL = r'https?://(?:www\.|m\.|mobile\.)?twitter\.com/(?P<user_id>[^/]+)/status/(?P<id>\d+)'
141 _TEMPLATE_URL = 'https://twitter.com/%s/status/%s'
144 'url': 'https://twitter.com/freethenipple/status/643211948184596480',
145 'md5': 'db6612ec5d03355953c3ca9250c97e5e',
147 'id': '643211948184596480',
149 'title': 'FREE THE NIPPLE - FTN supporters on Hollywood Blvd today!',
150 'thumbnail': 're:^https?://.*\.jpg',
152 'description': 'FREE THE NIPPLE on Twitter: "FTN supporters on Hollywood Blvd today! http://t.co/c7jHH749xJ"',
153 'uploader': 'FREE THE NIPPLE',
154 'uploader_id': 'freethenipple',
157 'url': 'https://twitter.com/giphz/status/657991469417025536/photo/1',
158 'md5': 'f36dcd5fb92bf7057f155e7d927eeb42',
160 'id': '657991469417025536',
162 'title': 'Gifs - tu vai cai tu vai cai tu nao eh capaz disso tu vai cai',
163 'description': 'Gifs on Twitter: "tu vai cai tu vai cai tu nao eh capaz disso tu vai cai https://t.co/tM46VHFlO5"',
164 'thumbnail': 're:^https?://.*\.png',
166 'uploader_id': 'giphz',
169 'url': 'https://twitter.com/starwars/status/665052190608723968',
170 'md5': '39b7199856dee6cd4432e72c74bc69d4',
172 'id': '665052190608723968',
174 'title': 'Star Wars - A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens.',
175 'description': 'Star Wars on Twitter: "A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens."',
176 'uploader_id': 'starwars',
177 'uploader': 'Star Wars',
181 def _real_extract(self, url):
182 mobj = re.match(self._VALID_URL, url)
183 user_id = mobj.group('user_id')
184 twid = mobj.group('id')
186 webpage = self._download_webpage(self._TEMPLATE_URL % (user_id, twid), twid)
188 username = remove_end(self._og_search_title(webpage), ' on Twitter')
190 title = description = self._og_search_description(webpage).strip('').replace('\n', ' ').strip('“”')
192 # strip 'https -_t.co_BJYgOjSeGA' junk from filenames
193 title = re.sub(r'\s+(https?://[^ ]+)', '', title)
196 'uploader_id': user_id,
197 'uploader': username,
199 'description': '%s on Twitter: "%s"' % (username, description),
200 'title': username + ' - ' + title,
203 card_id = self._search_regex(
204 r'["\']/i/cards/tfw/v1/(\d+)', webpage, 'twitter card url', default=None)
206 card_url = 'https://twitter.com/i/cards/tfw/v1/' + card_id
208 '_type': 'url_transparent',
209 'ie_key': 'TwitterCard',
214 mobj = re.search(r'''(?x)
215 <video[^>]+class="animated-gif"[^>]+
216 (?:data-height="(?P<height>\d+)")?[^>]+
217 (?:data-width="(?P<width>\d+)")?[^>]+
218 (?:poster="(?P<poster>[^"]+)")?[^>]*>\s*
219 <source[^>]+video-src="(?P<url>[^"]+)"
225 'url': mobj.group('url'),
226 'height': int_or_none(mobj.group('height')),
227 'width': int_or_none(mobj.group('width')),
228 'thumbnail': mobj.group('poster'),
232 raise ExtractorError('There\'s not video in this tweet.')
235 class TwitterAmplifyIE(TwitterBaseIE):
236 IE_NAME = 'twitter:amplify'
237 _VALID_URL = 'https?://amp\.twimg\.com/v/(?P<id>[0-9a-f\-]{36})'
240 'url': 'https://amp.twimg.com/v/0ba0c3c7-0af3-4c0a-bed5-7efd1ffa2951',
241 'md5': '7df102d0b9fd7066b86f3159f8e81bf6',
243 'id': '0ba0c3c7-0af3-4c0a-bed5-7efd1ffa2951',
245 'title': 'Twitter Video',
249 def _real_extract(self, url):
250 video_id = self._match_id(url)
251 webpage = self._download_webpage(url, video_id)
253 vmap_url = self._html_search_meta(
254 'twitter:amplify:vmap', webpage, 'vmap url')
255 video_url = self._get_vmap_video_url(vmap_url, video_id)
259 'title': 'Twitter Video',