]>
Commit | Line | Data |
---|---|---|
93b22c78 | 1 | # encoding: utf-8 |
9148eb00 PH |
2 | from __future__ import unicode_literals |
3 | ||
b3d14cbf PH |
4 | import json |
5 | import re | |
caeefc29 | 6 | import itertools |
b3d14cbf PH |
7 | |
8 | from .common import InfoExtractor | |
8c25f81b | 9 | from ..compat import ( |
1060425c | 10 | compat_HTTPError, |
b3d14cbf | 11 | compat_urllib_request, |
9c44d242 | 12 | compat_urlparse, |
8c25f81b PH |
13 | ) |
14 | from ..utils import ( | |
852fad92 | 15 | encode_dict, |
b3d14cbf | 16 | ExtractorError, |
9c44d242 PH |
17 | InAdvancePagedList, |
18 | int_or_none, | |
55b3e45b | 19 | RegexNotFoundError, |
30965ac6 | 20 | smuggle_url, |
b3d14cbf | 21 | std_headers, |
3c6f2450 | 22 | unified_strdate, |
9d4660ca | 23 | unsmuggle_url, |
a980bc43 | 24 | urlencode_postdata, |
b407e173 | 25 | unescapeHTML, |
b3d14cbf PH |
26 | ) |
27 | ||
bbafbe20 | 28 | |
efb7e119 JMF |
29 | class VimeoBaseInfoExtractor(InfoExtractor): |
30 | _NETRC_MACHINE = 'vimeo' | |
31 | _LOGIN_REQUIRED = False | |
f6c3664d | 32 | _LOGIN_URL = 'https://vimeo.com/log_in' |
efb7e119 JMF |
33 | |
34 | def _login(self): | |
35 | (username, password) = self._get_login_info() | |
36 | if username is None: | |
37 | if self._LOGIN_REQUIRED: | |
4f3e9430 | 38 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) |
efb7e119 JMF |
39 | return |
40 | self.report_login() | |
f6c3664d | 41 | webpage = self._download_webpage(self._LOGIN_URL, None, False) |
7c845629 | 42 | token, vuid = self._extract_xsrft_and_vuid(webpage) |
3fa3ff1b | 43 | data = urlencode_postdata(encode_dict({ |
f6c3664d | 44 | 'action': 'login', |
efb7e119 JMF |
45 | 'email': username, |
46 | 'password': password, | |
efb7e119 JMF |
47 | 'service': 'vimeo', |
48 | 'token': token, | |
3fa3ff1b | 49 | })) |
f6c3664d | 50 | login_request = compat_urllib_request.Request(self._LOGIN_URL, data) |
efb7e119 | 51 | login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') |
47c165c3 | 52 | login_request.add_header('Cookie', 'vuid=%s' % vuid) |
f6c3664d | 53 | login_request.add_header('Referer', self._LOGIN_URL) |
efb7e119 JMF |
54 | self._download_webpage(login_request, None, False, 'Wrong login info') |
55 | ||
7c845629 S |
56 | def _extract_xsrft_and_vuid(self, webpage): |
57 | xsrft = self._search_regex( | |
f6c3664d S |
58 | r'xsrft\s*[=:]\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)', |
59 | webpage, 'login token', group='xsrft') | |
7c845629 S |
60 | vuid = self._search_regex( |
61 | r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1', | |
62 | webpage, 'vuid', group='vuid') | |
63 | return xsrft, vuid | |
f6c3664d | 64 | |
efb7e119 | 65 | |
65469a7f | 66 | class VimeoIE(VimeoBaseInfoExtractor): |
b3d14cbf PH |
67 | """Information extractor for vimeo.com.""" |
68 | ||
69 | # _VALID_URL matches Vimeo URLs | |
bbafbe20 | 70 | _VALID_URL = r'''(?x) |
3357110a | 71 | https?:// |
bbafbe20 PH |
72 | (?:(?:www|(?P<player>player))\.)? |
73 | vimeo(?P<pro>pro)?\.com/ | |
2929b3e7 | 74 | (?!channels/[^/?#]+/?(?:$|[?#])|album/) |
bbafbe20 | 75 | (?:.*?/)? |
7115ca84 | 76 | (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)? |
bbafbe20 PH |
77 | (?:videos?/)? |
78 | (?P<id>[0-9]+) | |
7115ca84 | 79 | /?(?:[?&].*)?(?:[#].*)?$''' |
9148eb00 | 80 | IE_NAME = 'vimeo' |
a91b954b JMF |
81 | _TESTS = [ |
82 | { | |
9148eb00 | 83 | 'url': 'http://vimeo.com/56015672#at=0', |
9148eb00 PH |
84 | 'md5': '8879b6cc097e987f02484baf890129e5', |
85 | 'info_dict': { | |
ad5976b4 PH |
86 | 'id': '56015672', |
87 | 'ext': 'mp4', | |
68f3b61f S |
88 | 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", |
89 | 'description': 'md5:2d3305bad981a06ff79f027f19865021', | |
90 | 'upload_date': '20121220', | |
91 | 'uploader_id': 'user7108434', | |
92 | 'uploader': 'Filippo Valsorda', | |
93 | 'duration': 10, | |
a91b954b JMF |
94 | }, |
95 | }, | |
96 | { | |
9148eb00 | 97 | 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876', |
9148eb00 PH |
98 | 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82', |
99 | 'note': 'Vimeo Pro video (#1197)', | |
100 | 'info_dict': { | |
4f3e9430 JMF |
101 | 'id': '68093876', |
102 | 'ext': 'mp4', | |
9148eb00 PH |
103 | 'uploader_id': 'openstreetmapus', |
104 | 'uploader': 'OpenStreetMap US', | |
105 | 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography', | |
68f3b61f | 106 | 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30', |
69c8fb9e | 107 | 'duration': 1595, |
a91b954b JMF |
108 | }, |
109 | }, | |
aa32314d | 110 | { |
9148eb00 | 111 | 'url': 'http://player.vimeo.com/video/54469442', |
9148eb00 PH |
112 | 'md5': '619b811a4417aa4abe78dc653becf511', |
113 | 'note': 'Videos that embed the url in the player page', | |
114 | 'info_dict': { | |
4f3e9430 JMF |
115 | 'id': '54469442', |
116 | 'ext': 'mp4', | |
0e6ebc13 | 117 | 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012', |
9148eb00 PH |
118 | 'uploader': 'The BLN & Business of Software', |
119 | 'uploader_id': 'theblnbusinessofsoftware', | |
69c8fb9e | 120 | 'duration': 3610, |
58ea7ec8 | 121 | 'description': None, |
aa32314d | 122 | }, |
93b22c78 JMF |
123 | }, |
124 | { | |
9148eb00 | 125 | 'url': 'http://vimeo.com/68375962', |
9148eb00 PH |
126 | 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7', |
127 | 'note': 'Video protected with password', | |
128 | 'info_dict': { | |
4f3e9430 JMF |
129 | 'id': '68375962', |
130 | 'ext': 'mp4', | |
9148eb00 PH |
131 | 'title': 'youtube-dl password protected test video', |
132 | 'upload_date': '20130614', | |
133 | 'uploader_id': 'user18948128', | |
134 | 'uploader': 'Jaime Marquínez Ferrándiz', | |
69c8fb9e | 135 | 'duration': 10, |
8bea039b | 136 | 'description': 'This is "youtube-dl password protected test video" by Jaime Marquínez Ferrándiz on Vimeo, the home for high quality videos and the people\u2026', |
93b22c78 | 137 | }, |
9148eb00 PH |
138 | 'params': { |
139 | 'videopassword': 'youtube-dl', | |
93b22c78 JMF |
140 | }, |
141 | }, | |
548f31d9 S |
142 | { |
143 | 'url': 'http://vimeo.com/channels/keypeele/75629013', | |
144 | 'md5': '2f86a05afe9d7abc0b9126d229bbe15d', | |
145 | 'note': 'Video is freely available via original URL ' | |
146 | 'and protected with password when accessed via http://vimeo.com/75629013', | |
147 | 'info_dict': { | |
148 | 'id': '75629013', | |
149 | 'ext': 'mp4', | |
150 | 'title': 'Key & Peele: Terrorist Interrogation', | |
151 | 'description': 'md5:8678b246399b070816b12313e8b4eb5c', | |
152 | 'uploader_id': 'atencio', | |
153 | 'uploader': 'Peter Atencio', | |
3c6f2450 | 154 | 'upload_date': '20130927', |
548f31d9 S |
155 | 'duration': 187, |
156 | }, | |
157 | }, | |
1eac553e S |
158 | { |
159 | 'url': 'http://vimeo.com/76979871', | |
1eac553e S |
160 | 'note': 'Video with subtitles', |
161 | 'info_dict': { | |
162 | 'id': '76979871', | |
163 | 'ext': 'mp4', | |
164 | 'title': 'The New Vimeo Player (You Know, For Videos)', | |
165 | 'description': 'md5:2ec900bf97c3f389378a96aee11260ea', | |
166 | 'upload_date': '20131015', | |
167 | 'uploader_id': 'staff', | |
168 | 'uploader': 'Vimeo Staff', | |
69c8fb9e | 169 | 'duration': 62, |
1eac553e S |
170 | } |
171 | }, | |
4698f0d8 JMF |
172 | { |
173 | # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/ | |
174 | 'url': 'https://player.vimeo.com/video/98044508', | |
175 | 'note': 'The js code contains assignments to the same variable as the config', | |
176 | 'info_dict': { | |
177 | 'id': '98044508', | |
178 | 'ext': 'mp4', | |
179 | 'title': 'Pier Solar OUYA Official Trailer', | |
180 | 'uploader': 'Tulio Gonçalves', | |
181 | 'uploader_id': 'user28849593', | |
182 | }, | |
183 | }, | |
8bea039b LL |
184 | { |
185 | 'url': 'https://vimeo.com/109815029', | |
186 | 'note': 'Video not completely processed, "failed" seed status', | |
187 | 'only_matching': True, | |
188 | }, | |
a91b954b | 189 | ] |
b3d14cbf | 190 | |
b407e173 YCH |
191 | @staticmethod |
192 | def _extract_vimeo_url(url, webpage): | |
193 | # Look for embedded (iframe) Vimeo player | |
194 | mobj = re.search( | |
195 | r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage) | |
196 | if mobj: | |
197 | player_url = unescapeHTML(mobj.group('url')) | |
198 | surl = smuggle_url(player_url, {'Referer': url}) | |
199 | return surl | |
200 | # Look for embedded (swf embed) Vimeo player | |
201 | mobj = re.search( | |
202 | r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage) | |
203 | if mobj: | |
204 | return mobj.group(1) | |
205 | ||
b3d14cbf | 206 | def _verify_video_password(self, url, video_id, webpage): |
c6c19746 | 207 | password = self._downloader.params.get('videopassword', None) |
b3d14cbf | 208 | if password is None: |
93a16ba2 | 209 | raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True) |
7c845629 | 210 | token, vuid = self._extract_xsrft_and_vuid(webpage) |
852fad92 | 211 | data = urlencode_postdata(encode_dict({ |
4f3e9430 JMF |
212 | 'password': password, |
213 | 'token': token, | |
852fad92 | 214 | })) |
9c85b537 JMF |
215 | if url.startswith('http://'): |
216 | # vimeo only supports https now, but the user can give an http url | |
217 | url = url.replace('http://', 'https://') | |
218 | password_request = compat_urllib_request.Request(url + '/password', data) | |
b3d14cbf | 219 | password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') |
1f36085d | 220 | password_request.add_header('Cookie', 'clip_test2=1; vuid=%s' % vuid) |
12bb392a | 221 | password_request.add_header('Referer', url) |
bf8f082a PH |
222 | return self._download_webpage( |
223 | password_request, video_id, | |
224 | 'Verifying the password', 'Wrong password') | |
b3d14cbf | 225 | |
0eecc6a4 PH |
226 | def _verify_player_video_password(self, url, video_id): |
227 | password = self._downloader.params.get('videopassword', None) | |
228 | if password is None: | |
229 | raise ExtractorError('This video is protected by a password, use the --video-password option') | |
0a0110fc | 230 | data = urlencode_postdata(encode_dict({'password': password})) |
0eecc6a4 PH |
231 | pass_url = url + '/check-password' |
232 | password_request = compat_urllib_request.Request(pass_url, data) | |
233 | password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') | |
234 | return self._download_json( | |
235 | password_request, video_id, | |
236 | 'Verifying the password', | |
237 | 'Wrong password') | |
238 | ||
fc79158d JMF |
239 | def _real_initialize(self): |
240 | self._login() | |
241 | ||
a0088bdf | 242 | def _real_extract(self, url): |
9d4660ca PH |
243 | url, data = unsmuggle_url(url) |
244 | headers = std_headers | |
245 | if data is not None: | |
246 | headers = headers.copy() | |
247 | headers.update(data) | |
ba5d51b3 PH |
248 | if 'Referer' not in headers: |
249 | headers['Referer'] = url | |
9d4660ca | 250 | |
b3d14cbf PH |
251 | # Extract ID from URL |
252 | mobj = re.match(self._VALID_URL, url) | |
b3d14cbf | 253 | video_id = mobj.group('id') |
58ea7ec8 | 254 | orig_url = url |
9103bbc5 | 255 | if mobj.group('pro') or mobj.group('player'): |
61e00a97 | 256 | url = 'https://player.vimeo.com/video/' + video_id |
10831b5e | 257 | else: |
258 | url = 'https://vimeo.com/' + video_id | |
b3d14cbf PH |
259 | |
260 | # Retrieve video webpage to extract further information | |
9d4660ca | 261 | request = compat_urllib_request.Request(url, None, headers) |
1060425c PH |
262 | try: |
263 | webpage = self._download_webpage(request, video_id) | |
264 | except ExtractorError as ee: | |
265 | if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: | |
266 | errmsg = ee.cause.read() | |
267 | if b'Because of its privacy settings, this video cannot be played here' in errmsg: | |
268 | raise ExtractorError( | |
269 | 'Cannot download embed-only video without embedding ' | |
270 | 'URL. Please call youtube-dl with the URL of the page ' | |
271 | 'that embeds this video.', | |
272 | expected=True) | |
273 | raise | |
b3d14cbf PH |
274 | |
275 | # Now we begin extracting as much information as we can from what we | |
276 | # retrieved. First we extract the information common to all extractors, | |
277 | # and latter we extract those that are Vimeo specific. | |
278 | self.report_extraction(video_id) | |
279 | ||
998e6cdb | 280 | vimeo_config = self._search_regex( |
b6aa99af | 281 | r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage, |
998e6cdb S |
282 | 'vimeo config', default=None) |
283 | if vimeo_config: | |
284 | seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {}) | |
285 | if seed_status.get('state') == 'failed': | |
286 | raise ExtractorError( | |
b6aa99af | 287 | '%s said: %s' % (self.IE_NAME, seed_status['title']), |
998e6cdb S |
288 | expected=True) |
289 | ||
b3d14cbf PH |
290 | # Extract the config JSON |
291 | try: | |
93b22c78 JMF |
292 | try: |
293 | config_url = self._html_search_regex( | |
41a7b00f LL |
294 | r' data-config-url="(.+?)"', webpage, |
295 | 'config URL', default=None) | |
296 | if not config_url: | |
dd841752 S |
297 | # Sometimes new react-based page is served instead of old one that require |
298 | # different config URL extraction approach (see | |
299 | # https://github.com/rg3/youtube-dl/pull/7209) | |
41a7b00f LL |
300 | vimeo_clip_page_config = self._search_regex( |
301 | r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage, | |
302 | 'vimeo clip page config') | |
dd841752 S |
303 | config_url = self._parse_json( |
304 | vimeo_clip_page_config, video_id)['player']['config_url'] | |
93b22c78 JMF |
305 | config_json = self._download_webpage(config_url, video_id) |
306 | config = json.loads(config_json) | |
307 | except RegexNotFoundError: | |
308 | # For pro videos or player.vimeo.com urls | |
48ad51b2 JMF |
309 | # We try to find out to which variable is assigned the config dic |
310 | m_variable_name = re.search('(\w)\.video\.id', webpage) | |
311 | if m_variable_name is not None: | |
4698f0d8 | 312 | config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1)) |
48ad51b2 JMF |
313 | else: |
314 | config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});'] | |
9148eb00 | 315 | config = self._search_regex(config_re, webpage, 'info section', |
9e1a5b84 | 316 | flags=re.DOTALL) |
93b22c78 | 317 | config = json.loads(config) |
71907db3 | 318 | except Exception as e: |
b3d14cbf | 319 | if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage): |
9148eb00 | 320 | raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option') |
b3d14cbf | 321 | |
bf8f082a | 322 | if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None: |
30965ac6 PH |
323 | if data and '_video_password_verified' in data: |
324 | raise ExtractorError('video password verification failed!') | |
b3d14cbf | 325 | self._verify_video_password(url, video_id, webpage) |
30965ac6 PH |
326 | return self._real_extract( |
327 | smuggle_url(url, {'_video_password_verified': 'verified'})) | |
b3d14cbf | 328 | else: |
9148eb00 | 329 | raise ExtractorError('Unable to extract info section', |
71907db3 | 330 | cause=e) |
559e370f PH |
331 | else: |
332 | if config.get('view') == 4: | |
0eecc6a4 | 333 | config = self._verify_player_video_password(url, video_id) |
b3d14cbf PH |
334 | |
335 | # Extract title | |
336 | video_title = config["video"]["title"] | |
337 | ||
338 | # Extract uploader and uploader_id | |
339 | video_uploader = config["video"]["owner"]["name"] | |
340 | video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None | |
341 | ||
342 | # Extract video thumbnail | |
aa32314d | 343 | video_thumbnail = config["video"].get("thumbnail") |
c0e5d856 S |
344 | if video_thumbnail is None: |
345 | video_thumbs = config["video"].get("thumbs") | |
346 | if video_thumbs and isinstance(video_thumbs, dict): | |
3e510af3 | 347 | _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1] |
b3d14cbf PH |
348 | |
349 | # Extract video description | |
58ea7ec8 | 350 | |
25930395 | 351 | video_description = self._html_search_regex( |
58ea7ec8 PH |
352 | r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>', |
353 | webpage, 'description', default=None) | |
354 | if not video_description: | |
355 | video_description = self._html_search_meta( | |
356 | 'description', webpage, default=None) | |
357 | if not video_description and mobj.group('pro'): | |
358 | orig_webpage = self._download_webpage( | |
359 | orig_url, video_id, | |
360 | note='Downloading webpage for description', | |
361 | fatal=False) | |
362 | if orig_webpage: | |
363 | video_description = self._html_search_meta( | |
364 | 'description', orig_webpage, default=None) | |
365 | if not video_description and not mobj.group('player'): | |
366 | self._downloader.report_warning('Cannot find video description') | |
b3d14cbf | 367 | |
69c8fb9e S |
368 | # Extract video duration |
369 | video_duration = int_or_none(config["video"].get("duration")) | |
370 | ||
b3d14cbf PH |
371 | # Extract upload date |
372 | video_upload_date = None | |
3c6f2450 | 373 | mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage) |
b3d14cbf | 374 | if mobj is not None: |
3c6f2450 | 375 | video_upload_date = unified_strdate(mobj.group(1)) |
b3d14cbf | 376 | |
4e761794 | 377 | try: |
9148eb00 PH |
378 | view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count')) |
379 | like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count')) | |
380 | comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count')) | |
4e761794 JMF |
381 | except RegexNotFoundError: |
382 | # This info is only available in vimeo.com/{id} urls | |
383 | view_count = None | |
384 | like_count = None | |
385 | comment_count = None | |
386 | ||
b3d14cbf PH |
387 | # Vimeo specific: extract request signature and timestamp |
388 | sig = config['request']['signature'] | |
389 | timestamp = config['request']['timestamp'] | |
390 | ||
391 | # Vimeo specific: extract video codec and quality information | |
392 | # First consider quality, then codecs, then take everything | |
a6387bfd | 393 | codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')] |
a56f9de1 | 394 | files = {'hd': [], 'sd': [], 'other': []} |
aa32314d | 395 | config_files = config["video"].get("files") or config["request"].get("files") |
b3d14cbf | 396 | for codec_name, codec_extension in codecs: |
a6387bfd JE |
397 | for quality in config_files.get(codec_name, []): |
398 | format_id = '-'.join((codec_name, quality)).lower() | |
399 | key = quality if quality in files else 'other' | |
400 | video_url = None | |
401 | if isinstance(config_files[codec_name], dict): | |
402 | file_info = config_files[codec_name][quality] | |
403 | video_url = file_info.get('url') | |
b3d14cbf | 404 | else: |
a6387bfd JE |
405 | file_info = {} |
406 | if video_url is None: | |
407 | video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \ | |
4f3e9430 | 408 | % (video_id, sig, timestamp, quality, codec_name.upper()) |
a6387bfd JE |
409 | |
410 | files[key].append({ | |
411 | 'ext': codec_extension, | |
412 | 'url': video_url, | |
413 | 'format_id': format_id, | |
35a3ff1d | 414 | 'width': int_or_none(file_info.get('width')), |
415 | 'height': int_or_none(file_info.get('height')), | |
416 | 'tbr': int_or_none(file_info.get('bitrate')), | |
a6387bfd JE |
417 | }) |
418 | formats = [] | |
35a3ff1d | 419 | m3u8_url = config_files.get('hls', {}).get('all') |
420 | if m3u8_url: | |
da4daed5 S |
421 | m3u8_formats = self._extract_m3u8_formats( |
422 | m3u8_url, video_id, 'mp4', 'm3u8_native', 0, 'hls', fatal=False) | |
423 | if m3u8_formats: | |
73e732eb | 424 | formats.extend(m3u8_formats) |
a6387bfd JE |
425 | for key in ('other', 'sd', 'hd'): |
426 | formats += files[key] | |
e5c209a1 | 427 | self._sort_formats(formats) |
b3d14cbf | 428 | |
1eac553e S |
429 | subtitles = {} |
430 | text_tracks = config['request'].get('text_tracks') | |
431 | if text_tracks: | |
432 | for tt in text_tracks: | |
65469a7f JMF |
433 | subtitles[tt['lang']] = [{ |
434 | 'ext': 'vtt', | |
3946864c | 435 | 'url': 'https://vimeo.com' + tt['url'], |
65469a7f | 436 | }] |
1eac553e | 437 | |
9103bbc5 | 438 | return { |
b0268cb6 | 439 | 'id': video_id, |
b3d14cbf PH |
440 | 'uploader': video_uploader, |
441 | 'uploader_id': video_uploader_id, | |
b0268cb6 S |
442 | 'upload_date': video_upload_date, |
443 | 'title': video_title, | |
444 | 'thumbnail': video_thumbnail, | |
445 | 'description': video_description, | |
69c8fb9e | 446 | 'duration': video_duration, |
a6387bfd | 447 | 'formats': formats, |
9103bbc5 | 448 | 'webpage_url': url, |
4e761794 JMF |
449 | 'view_count': view_count, |
450 | 'like_count': like_count, | |
451 | 'comment_count': comment_count, | |
65469a7f | 452 | 'subtitles': subtitles, |
9103bbc5 | 453 | } |
caeefc29 JMF |
454 | |
455 | ||
f6c3664d | 456 | class VimeoChannelIE(VimeoBaseInfoExtractor): |
9148eb00 | 457 | IE_NAME = 'vimeo:channel' |
3946864c | 458 | _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])' |
caeefc29 | 459 | _MORE_PAGES_INDICATOR = r'<a.+?rel="next"' |
84458766 | 460 | _TITLE = None |
55a10eab | 461 | _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"' |
2929b3e7 | 462 | _TESTS = [{ |
3946864c | 463 | 'url': 'https://vimeo.com/channels/tributes', |
2929b3e7 | 464 | 'info_dict': { |
a3fa5da4 | 465 | 'id': 'tributes', |
2929b3e7 PH |
466 | 'title': 'Vimeo Tributes', |
467 | }, | |
468 | 'playlist_mincount': 25, | |
469 | }] | |
caeefc29 | 470 | |
5cc14c2f JMF |
471 | def _page_url(self, base_url, pagenum): |
472 | return '%s/videos/page:%d/' % (base_url, pagenum) | |
473 | ||
fb30ec22 | 474 | def _extract_list_title(self, webpage): |
84458766 | 475 | return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title') |
fb30ec22 | 476 | |
bf8f082a PH |
477 | def _login_list_password(self, page_url, list_id, webpage): |
478 | login_form = self._search_regex( | |
479 | r'(?s)<form[^>]+?id="pw_form"(.*?)</form>', | |
480 | webpage, 'login form', default=None) | |
481 | if not login_form: | |
482 | return webpage | |
483 | ||
484 | password = self._downloader.params.get('videopassword', None) | |
485 | if password is None: | |
486 | raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True) | |
f8da79f8 | 487 | fields = self._hidden_inputs(login_form) |
7c845629 | 488 | token, vuid = self._extract_xsrft_and_vuid(webpage) |
bf8f082a PH |
489 | fields['token'] = token |
490 | fields['password'] = password | |
bfdf891f | 491 | post = urlencode_postdata(encode_dict(fields)) |
bf8f082a PH |
492 | password_path = self._search_regex( |
493 | r'action="([^"]+)"', login_form, 'password URL') | |
494 | password_url = compat_urlparse.urljoin(page_url, password_path) | |
495 | password_request = compat_urllib_request.Request(password_url, post) | |
496 | password_request.add_header('Content-type', 'application/x-www-form-urlencoded') | |
7c845629 | 497 | password_request.add_header('Cookie', 'vuid=%s' % vuid) |
bf8f082a PH |
498 | self._set_cookie('vimeo.com', 'xsrft', token) |
499 | ||
500 | return self._download_webpage( | |
501 | password_request, list_id, | |
502 | 'Verifying the password', 'Wrong password') | |
503 | ||
55a10eab | 504 | def _extract_videos(self, list_id, base_url): |
caeefc29 | 505 | video_ids = [] |
caeefc29 | 506 | for pagenum in itertools.count(1): |
bf8f082a | 507 | page_url = self._page_url(base_url, pagenum) |
55a10eab | 508 | webpage = self._download_webpage( |
bf8f082a | 509 | page_url, list_id, |
9148eb00 | 510 | 'Downloading page %s' % pagenum) |
bf8f082a PH |
511 | |
512 | if pagenum == 1: | |
513 | webpage = self._login_list_password(page_url, list_id, webpage) | |
514 | ||
caeefc29 JMF |
515 | video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage)) |
516 | if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: | |
517 | break | |
518 | ||
3946864c | 519 | entries = [self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo') |
caeefc29 | 520 | for video_id in video_ids] |
caeefc29 | 521 | return {'_type': 'playlist', |
55a10eab | 522 | 'id': list_id, |
fb30ec22 | 523 | 'title': self._extract_list_title(webpage), |
caeefc29 JMF |
524 | 'entries': entries, |
525 | } | |
55a10eab JMF |
526 | |
527 | def _real_extract(self, url): | |
528 | mobj = re.match(self._VALID_URL, url) | |
4f3e9430 | 529 | channel_id = mobj.group('id') |
3946864c | 530 | return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id) |
55a10eab JMF |
531 | |
532 | ||
533 | class VimeoUserIE(VimeoChannelIE): | |
9148eb00 | 534 | IE_NAME = 'vimeo:user' |
b29440ae | 535 | _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)' |
55a10eab | 536 | _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>' |
2929b3e7 | 537 | _TESTS = [{ |
3946864c | 538 | 'url': 'https://vimeo.com/nkistudio/videos', |
2929b3e7 PH |
539 | 'info_dict': { |
540 | 'title': 'Nki', | |
a3fa5da4 | 541 | 'id': 'nkistudio', |
2929b3e7 PH |
542 | }, |
543 | 'playlist_mincount': 66, | |
544 | }] | |
55a10eab JMF |
545 | |
546 | def _real_extract(self, url): | |
547 | mobj = re.match(self._VALID_URL, url) | |
548 | name = mobj.group('name') | |
3946864c | 549 | return self._extract_videos(name, 'https://vimeo.com/%s' % name) |
5cc14c2f JMF |
550 | |
551 | ||
552 | class VimeoAlbumIE(VimeoChannelIE): | |
9148eb00 | 553 | IE_NAME = 'vimeo:album' |
d1508cd6 | 554 | _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)' |
5cc14c2f | 555 | _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>' |
2929b3e7 | 556 | _TESTS = [{ |
d1508cd6 | 557 | 'url': 'https://vimeo.com/album/2632481', |
2929b3e7 | 558 | 'info_dict': { |
a3fa5da4 | 559 | 'id': '2632481', |
2929b3e7 PH |
560 | 'title': 'Staff Favorites: November 2013', |
561 | }, | |
562 | 'playlist_mincount': 13, | |
bf8f082a PH |
563 | }, { |
564 | 'note': 'Password-protected album', | |
565 | 'url': 'https://vimeo.com/album/3253534', | |
566 | 'info_dict': { | |
567 | 'title': 'test', | |
568 | 'id': '3253534', | |
569 | }, | |
570 | 'playlist_count': 1, | |
571 | 'params': { | |
572 | 'videopassword': 'youtube-dl', | |
573 | } | |
2929b3e7 | 574 | }] |
5cc14c2f JMF |
575 | |
576 | def _page_url(self, base_url, pagenum): | |
577 | return '%s/page:%d/' % (base_url, pagenum) | |
578 | ||
579 | def _real_extract(self, url): | |
bf8f082a | 580 | album_id = self._match_id(url) |
d1508cd6 | 581 | return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id) |
fb30ec22 JMF |
582 | |
583 | ||
584 | class VimeoGroupsIE(VimeoAlbumIE): | |
9148eb00 | 585 | IE_NAME = 'vimeo:group' |
3946864c | 586 | _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)' |
2929b3e7 | 587 | _TESTS = [{ |
3946864c | 588 | 'url': 'https://vimeo.com/groups/rolexawards', |
2929b3e7 | 589 | 'info_dict': { |
a3fa5da4 | 590 | 'id': 'rolexawards', |
2929b3e7 PH |
591 | 'title': 'Rolex Awards for Enterprise', |
592 | }, | |
593 | 'playlist_mincount': 73, | |
594 | }] | |
fb30ec22 JMF |
595 | |
596 | def _extract_list_title(self, webpage): | |
597 | return self._og_search_title(webpage) | |
598 | ||
599 | def _real_extract(self, url): | |
600 | mobj = re.match(self._VALID_URL, url) | |
601 | name = mobj.group('name') | |
3946864c | 602 | return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name) |
fcea44c6 PH |
603 | |
604 | ||
605 | class VimeoReviewIE(InfoExtractor): | |
9148eb00 PH |
606 | IE_NAME = 'vimeo:review' |
607 | IE_DESC = 'Review pages on vimeo' | |
3946864c | 608 | _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)' |
d36d3f42 | 609 | _TESTS = [{ |
fcea44c6 | 610 | 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d', |
fcea44c6 PH |
611 | 'md5': 'c507a72f780cacc12b2248bb4006d253', |
612 | 'info_dict': { | |
fc09240e PH |
613 | 'id': '75524534', |
614 | 'ext': 'mp4', | |
fcea44c6 PH |
615 | 'title': "DICK HARDWICK 'Comedian'", |
616 | 'uploader': 'Richard Hardwick', | |
617 | } | |
d36d3f42 PH |
618 | }, { |
619 | 'note': 'video player needs Referer', | |
3946864c | 620 | 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053', |
d36d3f42 PH |
621 | 'md5': '6295fdab8f4bf6a002d058b2c6dce276', |
622 | 'info_dict': { | |
623 | 'id': '91613211', | |
624 | 'ext': 'mp4', | |
9dec9930 | 625 | 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn', |
d36d3f42 PH |
626 | 'uploader': 'DevWeek Events', |
627 | 'duration': 2773, | |
628 | 'thumbnail': 're:^https?://.*\.jpg$', | |
629 | } | |
630 | }] | |
fcea44c6 PH |
631 | |
632 | def _real_extract(self, url): | |
633 | mobj = re.match(self._VALID_URL, url) | |
634 | video_id = mobj.group('id') | |
635 | player_url = 'https://player.vimeo.com/player/' + video_id | |
636 | return self.url_result(player_url, 'Vimeo', video_id) | |
efb7e119 JMF |
637 | |
638 | ||
f6c3664d | 639 | class VimeoWatchLaterIE(VimeoChannelIE): |
efb7e119 JMF |
640 | IE_NAME = 'vimeo:watchlater' |
641 | IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)' | |
84458766 S |
642 | _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater' |
643 | _TITLE = 'Watch Later' | |
efb7e119 | 644 | _LOGIN_REQUIRED = True |
2929b3e7 | 645 | _TESTS = [{ |
84458766 | 646 | 'url': 'https://vimeo.com/watchlater', |
2929b3e7 PH |
647 | 'only_matching': True, |
648 | }] | |
efb7e119 JMF |
649 | |
650 | def _real_initialize(self): | |
651 | self._login() | |
652 | ||
653 | def _page_url(self, base_url, pagenum): | |
654 | url = '%s/page:%d/' % (base_url, pagenum) | |
655 | request = compat_urllib_request.Request(url) | |
656 | # Set the header to get a partial html page with the ids, | |
657 | # the normal page doesn't contain them. | |
658 | request.add_header('X-Requested-With', 'XMLHttpRequest') | |
659 | return request | |
660 | ||
661 | def _real_extract(self, url): | |
84458766 | 662 | return self._extract_videos('watchlater', 'https://vimeo.com/watchlater') |
d6e6a422 PH |
663 | |
664 | ||
665 | class VimeoLikesIE(InfoExtractor): | |
3946864c | 666 | _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)' |
d6e6a422 PH |
667 | IE_NAME = 'vimeo:likes' |
668 | IE_DESC = 'Vimeo user likes' | |
669 | _TEST = { | |
9c44d242 PH |
670 | 'url': 'https://vimeo.com/user755559/likes/', |
671 | 'playlist_mincount': 293, | |
d6e6a422 | 672 | "info_dict": { |
a3fa5da4 | 673 | 'id': 'user755559_likes', |
9c44d242 PH |
674 | "description": "See all the videos urza likes", |
675 | "title": 'Videos urza likes', | |
d6e6a422 PH |
676 | }, |
677 | } | |
678 | ||
679 | def _real_extract(self, url): | |
680 | user_id = self._match_id(url) | |
9c44d242 PH |
681 | webpage = self._download_webpage(url, user_id) |
682 | page_count = self._int( | |
683 | self._search_regex( | |
684 | r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)"> | |
685 | .*?</a></li>\s*<li\s+class="pagination_next"> | |
686 | ''', webpage, 'page count'), | |
687 | 'page count', fatal=True) | |
688 | PAGE_SIZE = 12 | |
689 | title = self._html_search_regex( | |
690 | r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False) | |
691 | description = self._html_search_meta('description', webpage) | |
692 | ||
693 | def _get_page(idx): | |
3946864c JMF |
694 | page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % ( |
695 | user_id, idx + 1) | |
9c44d242 PH |
696 | webpage = self._download_webpage( |
697 | page_url, user_id, | |
698 | note='Downloading page %d/%d' % (idx + 1, page_count)) | |
699 | video_list = self._search_regex( | |
700 | r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>', | |
701 | webpage, 'video content') | |
702 | paths = re.findall( | |
703 | r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list) | |
704 | for path in paths: | |
705 | yield { | |
706 | '_type': 'url', | |
707 | 'url': compat_urlparse.urljoin(page_url, path), | |
708 | } | |
709 | ||
710 | pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE) | |
d6e6a422 PH |
711 | |
712 | return { | |
9c44d242 PH |
713 | '_type': 'playlist', |
714 | 'id': 'user%s_likes' % user_id, | |
715 | 'title': title, | |
716 | 'description': description, | |
717 | 'entries': pl, | |
d6e6a422 | 718 | } |