]>
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 PH |
11 | compat_urllib_parse, |
12 | compat_urllib_request, | |
9c44d242 | 13 | compat_urlparse, |
8c25f81b PH |
14 | ) |
15 | from ..utils import ( | |
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, |
b3d14cbf PH |
25 | ) |
26 | ||
bbafbe20 | 27 | |
efb7e119 JMF |
28 | class VimeoBaseInfoExtractor(InfoExtractor): |
29 | _NETRC_MACHINE = 'vimeo' | |
30 | _LOGIN_REQUIRED = False | |
31 | ||
32 | def _login(self): | |
33 | (username, password) = self._get_login_info() | |
34 | if username is None: | |
35 | if self._LOGIN_REQUIRED: | |
4f3e9430 | 36 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) |
efb7e119 JMF |
37 | return |
38 | self.report_login() | |
39 | login_url = 'https://vimeo.com/log_in' | |
40 | webpage = self._download_webpage(login_url, None, False) | |
b8403701 | 41 | token = self._search_regex(r'xsrft = \'(.*?)\'', webpage, 'login token') |
efb7e119 JMF |
42 | data = urlencode_postdata({ |
43 | 'email': username, | |
44 | 'password': password, | |
45 | 'action': 'login', | |
46 | 'service': 'vimeo', | |
47 | 'token': token, | |
48 | }) | |
49 | login_request = compat_urllib_request.Request(login_url, data) | |
50 | login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') | |
51 | login_request.add_header('Cookie', 'xsrft=%s' % token) | |
52 | self._download_webpage(login_request, None, False, 'Wrong login info') | |
53 | ||
54 | ||
65469a7f | 55 | class VimeoIE(VimeoBaseInfoExtractor): |
b3d14cbf PH |
56 | """Information extractor for vimeo.com.""" |
57 | ||
58 | # _VALID_URL matches Vimeo URLs | |
bbafbe20 | 59 | _VALID_URL = r'''(?x) |
3357110a | 60 | https?:// |
bbafbe20 PH |
61 | (?:(?:www|(?P<player>player))\.)? |
62 | vimeo(?P<pro>pro)?\.com/ | |
2929b3e7 | 63 | (?!channels/[^/?#]+/?(?:$|[?#])|album/) |
bbafbe20 | 64 | (?:.*?/)? |
7115ca84 | 65 | (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)? |
bbafbe20 PH |
66 | (?:videos?/)? |
67 | (?P<id>[0-9]+) | |
7115ca84 | 68 | /?(?:[?&].*)?(?:[#].*)?$''' |
9148eb00 | 69 | IE_NAME = 'vimeo' |
a91b954b JMF |
70 | _TESTS = [ |
71 | { | |
9148eb00 | 72 | 'url': 'http://vimeo.com/56015672#at=0', |
9148eb00 PH |
73 | 'md5': '8879b6cc097e987f02484baf890129e5', |
74 | 'info_dict': { | |
ad5976b4 PH |
75 | 'id': '56015672', |
76 | 'ext': 'mp4', | |
77 | "upload_date": "20121220", | |
78 | "description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", | |
79 | "uploader_id": "user7108434", | |
80 | "uploader": "Filippo Valsorda", | |
9148eb00 | 81 | "title": "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", |
69c8fb9e | 82 | "duration": 10, |
a91b954b JMF |
83 | }, |
84 | }, | |
85 | { | |
9148eb00 | 86 | 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876', |
9148eb00 PH |
87 | 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82', |
88 | 'note': 'Vimeo Pro video (#1197)', | |
89 | 'info_dict': { | |
4f3e9430 JMF |
90 | 'id': '68093876', |
91 | 'ext': 'mp4', | |
9148eb00 PH |
92 | 'uploader_id': 'openstreetmapus', |
93 | 'uploader': 'OpenStreetMap US', | |
94 | 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography', | |
58ea7ec8 | 95 | 'description': 'md5:380943ec71b89736ff4bf27183233d09', |
69c8fb9e | 96 | 'duration': 1595, |
a91b954b JMF |
97 | }, |
98 | }, | |
aa32314d | 99 | { |
9148eb00 | 100 | 'url': 'http://player.vimeo.com/video/54469442', |
9148eb00 PH |
101 | 'md5': '619b811a4417aa4abe78dc653becf511', |
102 | 'note': 'Videos that embed the url in the player page', | |
103 | 'info_dict': { | |
4f3e9430 JMF |
104 | 'id': '54469442', |
105 | 'ext': 'mp4', | |
0e6ebc13 | 106 | 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012', |
9148eb00 PH |
107 | 'uploader': 'The BLN & Business of Software', |
108 | 'uploader_id': 'theblnbusinessofsoftware', | |
69c8fb9e | 109 | 'duration': 3610, |
58ea7ec8 | 110 | 'description': None, |
aa32314d | 111 | }, |
93b22c78 JMF |
112 | }, |
113 | { | |
9148eb00 | 114 | 'url': 'http://vimeo.com/68375962', |
9148eb00 PH |
115 | 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7', |
116 | 'note': 'Video protected with password', | |
117 | 'info_dict': { | |
4f3e9430 JMF |
118 | 'id': '68375962', |
119 | 'ext': 'mp4', | |
9148eb00 PH |
120 | 'title': 'youtube-dl password protected test video', |
121 | 'upload_date': '20130614', | |
122 | 'uploader_id': 'user18948128', | |
123 | 'uploader': 'Jaime Marquínez Ferrándiz', | |
69c8fb9e | 124 | 'duration': 10, |
58ea7ec8 | 125 | 'description': 'This is "youtube-dl password protected test video" by Jaime Marquínez Ferrándiz on Vimeo, the home for high quality videos and the people who love them.', |
93b22c78 | 126 | }, |
9148eb00 PH |
127 | 'params': { |
128 | 'videopassword': 'youtube-dl', | |
93b22c78 JMF |
129 | }, |
130 | }, | |
548f31d9 S |
131 | { |
132 | 'url': 'http://vimeo.com/channels/keypeele/75629013', | |
133 | 'md5': '2f86a05afe9d7abc0b9126d229bbe15d', | |
134 | 'note': 'Video is freely available via original URL ' | |
135 | 'and protected with password when accessed via http://vimeo.com/75629013', | |
136 | 'info_dict': { | |
137 | 'id': '75629013', | |
138 | 'ext': 'mp4', | |
139 | 'title': 'Key & Peele: Terrorist Interrogation', | |
140 | 'description': 'md5:8678b246399b070816b12313e8b4eb5c', | |
141 | 'uploader_id': 'atencio', | |
142 | 'uploader': 'Peter Atencio', | |
3c6f2450 | 143 | 'upload_date': '20130927', |
548f31d9 S |
144 | 'duration': 187, |
145 | }, | |
146 | }, | |
1eac553e S |
147 | { |
148 | 'url': 'http://vimeo.com/76979871', | |
149 | 'md5': '3363dd6ffebe3784d56f4132317fd446', | |
150 | 'note': 'Video with subtitles', | |
151 | 'info_dict': { | |
152 | 'id': '76979871', | |
153 | 'ext': 'mp4', | |
154 | 'title': 'The New Vimeo Player (You Know, For Videos)', | |
155 | 'description': 'md5:2ec900bf97c3f389378a96aee11260ea', | |
156 | 'upload_date': '20131015', | |
157 | 'uploader_id': 'staff', | |
158 | 'uploader': 'Vimeo Staff', | |
69c8fb9e | 159 | 'duration': 62, |
1eac553e S |
160 | } |
161 | }, | |
4698f0d8 JMF |
162 | { |
163 | # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/ | |
164 | 'url': 'https://player.vimeo.com/video/98044508', | |
165 | 'note': 'The js code contains assignments to the same variable as the config', | |
166 | 'info_dict': { | |
167 | 'id': '98044508', | |
168 | 'ext': 'mp4', | |
169 | 'title': 'Pier Solar OUYA Official Trailer', | |
170 | 'uploader': 'Tulio Gonçalves', | |
171 | 'uploader_id': 'user28849593', | |
172 | }, | |
173 | }, | |
a91b954b | 174 | ] |
b3d14cbf PH |
175 | |
176 | def _verify_video_password(self, url, video_id, webpage): | |
c6c19746 | 177 | password = self._downloader.params.get('videopassword', None) |
b3d14cbf | 178 | if password is None: |
93a16ba2 | 179 | raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True) |
9c85b537 JMF |
180 | token = self._search_regex(r'xsrft = \'(.*?)\'', webpage, 'login token') |
181 | data = urlencode_postdata({ | |
4f3e9430 JMF |
182 | 'password': password, |
183 | 'token': token, | |
184 | }) | |
9c85b537 JMF |
185 | if url.startswith('http://'): |
186 | # vimeo only supports https now, but the user can give an http url | |
187 | url = url.replace('http://', 'https://') | |
188 | password_request = compat_urllib_request.Request(url + '/password', data) | |
b3d14cbf PH |
189 | password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') |
190 | password_request.add_header('Cookie', 'xsrft=%s' % token) | |
bf8f082a PH |
191 | return self._download_webpage( |
192 | password_request, video_id, | |
193 | 'Verifying the password', 'Wrong password') | |
b3d14cbf | 194 | |
0eecc6a4 PH |
195 | def _verify_player_video_password(self, url, video_id): |
196 | password = self._downloader.params.get('videopassword', None) | |
197 | if password is None: | |
198 | raise ExtractorError('This video is protected by a password, use the --video-password option') | |
199 | data = compat_urllib_parse.urlencode({'password': password}) | |
200 | pass_url = url + '/check-password' | |
201 | password_request = compat_urllib_request.Request(pass_url, data) | |
202 | password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') | |
203 | return self._download_json( | |
204 | password_request, video_id, | |
205 | 'Verifying the password', | |
206 | 'Wrong password') | |
207 | ||
fc79158d JMF |
208 | def _real_initialize(self): |
209 | self._login() | |
210 | ||
a0088bdf | 211 | def _real_extract(self, url): |
9d4660ca PH |
212 | url, data = unsmuggle_url(url) |
213 | headers = std_headers | |
214 | if data is not None: | |
215 | headers = headers.copy() | |
216 | headers.update(data) | |
ba5d51b3 PH |
217 | if 'Referer' not in headers: |
218 | headers['Referer'] = url | |
9d4660ca | 219 | |
b3d14cbf PH |
220 | # Extract ID from URL |
221 | mobj = re.match(self._VALID_URL, url) | |
b3d14cbf | 222 | video_id = mobj.group('id') |
58ea7ec8 | 223 | orig_url = url |
9103bbc5 | 224 | if mobj.group('pro') or mobj.group('player'): |
61e00a97 | 225 | url = 'https://player.vimeo.com/video/' + video_id |
b3d14cbf PH |
226 | |
227 | # Retrieve video webpage to extract further information | |
9d4660ca | 228 | request = compat_urllib_request.Request(url, None, headers) |
1060425c PH |
229 | try: |
230 | webpage = self._download_webpage(request, video_id) | |
231 | except ExtractorError as ee: | |
232 | if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: | |
233 | errmsg = ee.cause.read() | |
234 | if b'Because of its privacy settings, this video cannot be played here' in errmsg: | |
235 | raise ExtractorError( | |
236 | 'Cannot download embed-only video without embedding ' | |
237 | 'URL. Please call youtube-dl with the URL of the page ' | |
238 | 'that embeds this video.', | |
239 | expected=True) | |
240 | raise | |
b3d14cbf PH |
241 | |
242 | # Now we begin extracting as much information as we can from what we | |
243 | # retrieved. First we extract the information common to all extractors, | |
244 | # and latter we extract those that are Vimeo specific. | |
245 | self.report_extraction(video_id) | |
246 | ||
998e6cdb S |
247 | vimeo_config = self._search_regex( |
248 | r'vimeo\.config\s*=\s*({.+?});', webpage, | |
249 | 'vimeo config', default=None) | |
250 | if vimeo_config: | |
251 | seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {}) | |
252 | if seed_status.get('state') == 'failed': | |
253 | raise ExtractorError( | |
254 | '%s returned error: %s' % (self.IE_NAME, seed_status['title']), | |
255 | expected=True) | |
256 | ||
b3d14cbf PH |
257 | # Extract the config JSON |
258 | try: | |
93b22c78 JMF |
259 | try: |
260 | config_url = self._html_search_regex( | |
9148eb00 | 261 | r' data-config-url="(.+?)"', webpage, 'config URL') |
93b22c78 JMF |
262 | config_json = self._download_webpage(config_url, video_id) |
263 | config = json.loads(config_json) | |
264 | except RegexNotFoundError: | |
265 | # For pro videos or player.vimeo.com urls | |
48ad51b2 JMF |
266 | # We try to find out to which variable is assigned the config dic |
267 | m_variable_name = re.search('(\w)\.video\.id', webpage) | |
268 | if m_variable_name is not None: | |
4698f0d8 | 269 | config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1)) |
48ad51b2 JMF |
270 | else: |
271 | config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});'] | |
9148eb00 | 272 | config = self._search_regex(config_re, webpage, 'info section', |
9e1a5b84 | 273 | flags=re.DOTALL) |
93b22c78 | 274 | config = json.loads(config) |
71907db3 | 275 | except Exception as e: |
b3d14cbf | 276 | if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage): |
9148eb00 | 277 | raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option') |
b3d14cbf | 278 | |
bf8f082a | 279 | if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None: |
30965ac6 PH |
280 | if data and '_video_password_verified' in data: |
281 | raise ExtractorError('video password verification failed!') | |
b3d14cbf | 282 | self._verify_video_password(url, video_id, webpage) |
30965ac6 PH |
283 | return self._real_extract( |
284 | smuggle_url(url, {'_video_password_verified': 'verified'})) | |
b3d14cbf | 285 | else: |
9148eb00 | 286 | raise ExtractorError('Unable to extract info section', |
71907db3 | 287 | cause=e) |
559e370f PH |
288 | else: |
289 | if config.get('view') == 4: | |
0eecc6a4 | 290 | config = self._verify_player_video_password(url, video_id) |
b3d14cbf PH |
291 | |
292 | # Extract title | |
293 | video_title = config["video"]["title"] | |
294 | ||
295 | # Extract uploader and uploader_id | |
296 | video_uploader = config["video"]["owner"]["name"] | |
297 | video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None | |
298 | ||
299 | # Extract video thumbnail | |
aa32314d | 300 | video_thumbnail = config["video"].get("thumbnail") |
c0e5d856 S |
301 | if video_thumbnail is None: |
302 | video_thumbs = config["video"].get("thumbs") | |
303 | if video_thumbs and isinstance(video_thumbs, dict): | |
3e510af3 | 304 | _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1] |
b3d14cbf PH |
305 | |
306 | # Extract video description | |
58ea7ec8 | 307 | |
25930395 | 308 | video_description = self._html_search_regex( |
58ea7ec8 PH |
309 | r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>', |
310 | webpage, 'description', default=None) | |
311 | if not video_description: | |
312 | video_description = self._html_search_meta( | |
313 | 'description', webpage, default=None) | |
314 | if not video_description and mobj.group('pro'): | |
315 | orig_webpage = self._download_webpage( | |
316 | orig_url, video_id, | |
317 | note='Downloading webpage for description', | |
318 | fatal=False) | |
319 | if orig_webpage: | |
320 | video_description = self._html_search_meta( | |
321 | 'description', orig_webpage, default=None) | |
322 | if not video_description and not mobj.group('player'): | |
323 | self._downloader.report_warning('Cannot find video description') | |
b3d14cbf | 324 | |
69c8fb9e S |
325 | # Extract video duration |
326 | video_duration = int_or_none(config["video"].get("duration")) | |
327 | ||
b3d14cbf PH |
328 | # Extract upload date |
329 | video_upload_date = None | |
3c6f2450 | 330 | mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage) |
b3d14cbf | 331 | if mobj is not None: |
3c6f2450 | 332 | video_upload_date = unified_strdate(mobj.group(1)) |
b3d14cbf | 333 | |
4e761794 | 334 | try: |
9148eb00 PH |
335 | view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count')) |
336 | like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count')) | |
337 | comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count')) | |
4e761794 JMF |
338 | except RegexNotFoundError: |
339 | # This info is only available in vimeo.com/{id} urls | |
340 | view_count = None | |
341 | like_count = None | |
342 | comment_count = None | |
343 | ||
b3d14cbf PH |
344 | # Vimeo specific: extract request signature and timestamp |
345 | sig = config['request']['signature'] | |
346 | timestamp = config['request']['timestamp'] | |
347 | ||
348 | # Vimeo specific: extract video codec and quality information | |
349 | # First consider quality, then codecs, then take everything | |
a6387bfd | 350 | codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')] |
a56f9de1 | 351 | files = {'hd': [], 'sd': [], 'other': []} |
aa32314d | 352 | config_files = config["video"].get("files") or config["request"].get("files") |
b3d14cbf | 353 | for codec_name, codec_extension in codecs: |
a6387bfd JE |
354 | for quality in config_files.get(codec_name, []): |
355 | format_id = '-'.join((codec_name, quality)).lower() | |
356 | key = quality if quality in files else 'other' | |
357 | video_url = None | |
358 | if isinstance(config_files[codec_name], dict): | |
359 | file_info = config_files[codec_name][quality] | |
360 | video_url = file_info.get('url') | |
b3d14cbf | 361 | else: |
a6387bfd JE |
362 | file_info = {} |
363 | if video_url is None: | |
364 | 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 | 365 | % (video_id, sig, timestamp, quality, codec_name.upper()) |
a6387bfd JE |
366 | |
367 | files[key].append({ | |
368 | 'ext': codec_extension, | |
369 | 'url': video_url, | |
370 | 'format_id': format_id, | |
371 | 'width': file_info.get('width'), | |
372 | 'height': file_info.get('height'), | |
373 | }) | |
374 | formats = [] | |
375 | for key in ('other', 'sd', 'hd'): | |
376 | formats += files[key] | |
377 | if len(formats) == 0: | |
9148eb00 | 378 | raise ExtractorError('No known codec found') |
b3d14cbf | 379 | |
1eac553e S |
380 | subtitles = {} |
381 | text_tracks = config['request'].get('text_tracks') | |
382 | if text_tracks: | |
383 | for tt in text_tracks: | |
65469a7f JMF |
384 | subtitles[tt['lang']] = [{ |
385 | 'ext': 'vtt', | |
3946864c | 386 | 'url': 'https://vimeo.com' + tt['url'], |
65469a7f | 387 | }] |
1eac553e | 388 | |
9103bbc5 | 389 | return { |
b0268cb6 | 390 | 'id': video_id, |
b3d14cbf PH |
391 | 'uploader': video_uploader, |
392 | 'uploader_id': video_uploader_id, | |
b0268cb6 S |
393 | 'upload_date': video_upload_date, |
394 | 'title': video_title, | |
395 | 'thumbnail': video_thumbnail, | |
396 | 'description': video_description, | |
69c8fb9e | 397 | 'duration': video_duration, |
a6387bfd | 398 | 'formats': formats, |
9103bbc5 | 399 | 'webpage_url': url, |
4e761794 JMF |
400 | 'view_count': view_count, |
401 | 'like_count': like_count, | |
402 | 'comment_count': comment_count, | |
65469a7f | 403 | 'subtitles': subtitles, |
9103bbc5 | 404 | } |
caeefc29 JMF |
405 | |
406 | ||
407 | class VimeoChannelIE(InfoExtractor): | |
9148eb00 | 408 | IE_NAME = 'vimeo:channel' |
3946864c | 409 | _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])' |
caeefc29 | 410 | _MORE_PAGES_INDICATOR = r'<a.+?rel="next"' |
55a10eab | 411 | _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"' |
2929b3e7 | 412 | _TESTS = [{ |
3946864c | 413 | 'url': 'https://vimeo.com/channels/tributes', |
2929b3e7 | 414 | 'info_dict': { |
a3fa5da4 | 415 | 'id': 'tributes', |
2929b3e7 PH |
416 | 'title': 'Vimeo Tributes', |
417 | }, | |
418 | 'playlist_mincount': 25, | |
419 | }] | |
caeefc29 | 420 | |
5cc14c2f JMF |
421 | def _page_url(self, base_url, pagenum): |
422 | return '%s/videos/page:%d/' % (base_url, pagenum) | |
423 | ||
fb30ec22 | 424 | def _extract_list_title(self, webpage): |
9148eb00 | 425 | return self._html_search_regex(self._TITLE_RE, webpage, 'list title') |
fb30ec22 | 426 | |
bf8f082a PH |
427 | def _login_list_password(self, page_url, list_id, webpage): |
428 | login_form = self._search_regex( | |
429 | r'(?s)<form[^>]+?id="pw_form"(.*?)</form>', | |
430 | webpage, 'login form', default=None) | |
431 | if not login_form: | |
432 | return webpage | |
433 | ||
434 | password = self._downloader.params.get('videopassword', None) | |
435 | if password is None: | |
436 | raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True) | |
437 | fields = dict(re.findall(r'''(?x)<input\s+ | |
438 | type="hidden"\s+ | |
439 | name="([^"]+)"\s+ | |
440 | value="([^"]*)" | |
441 | ''', login_form)) | |
d1508cd6 | 442 | token = self._search_regex(r'xsrft = \'(.*?)\'', webpage, 'login token') |
bf8f082a PH |
443 | fields['token'] = token |
444 | fields['password'] = password | |
d1508cd6 | 445 | post = urlencode_postdata(fields) |
bf8f082a PH |
446 | password_path = self._search_regex( |
447 | r'action="([^"]+)"', login_form, 'password URL') | |
448 | password_url = compat_urlparse.urljoin(page_url, password_path) | |
449 | password_request = compat_urllib_request.Request(password_url, post) | |
450 | password_request.add_header('Content-type', 'application/x-www-form-urlencoded') | |
451 | self._set_cookie('vimeo.com', 'xsrft', token) | |
452 | ||
453 | return self._download_webpage( | |
454 | password_request, list_id, | |
455 | 'Verifying the password', 'Wrong password') | |
456 | ||
55a10eab | 457 | def _extract_videos(self, list_id, base_url): |
caeefc29 | 458 | video_ids = [] |
caeefc29 | 459 | for pagenum in itertools.count(1): |
bf8f082a | 460 | page_url = self._page_url(base_url, pagenum) |
55a10eab | 461 | webpage = self._download_webpage( |
bf8f082a | 462 | page_url, list_id, |
9148eb00 | 463 | 'Downloading page %s' % pagenum) |
bf8f082a PH |
464 | |
465 | if pagenum == 1: | |
466 | webpage = self._login_list_password(page_url, list_id, webpage) | |
467 | ||
caeefc29 JMF |
468 | video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage)) |
469 | if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: | |
470 | break | |
471 | ||
3946864c | 472 | entries = [self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo') |
caeefc29 | 473 | for video_id in video_ids] |
caeefc29 | 474 | return {'_type': 'playlist', |
55a10eab | 475 | 'id': list_id, |
fb30ec22 | 476 | 'title': self._extract_list_title(webpage), |
caeefc29 JMF |
477 | 'entries': entries, |
478 | } | |
55a10eab JMF |
479 | |
480 | def _real_extract(self, url): | |
481 | mobj = re.match(self._VALID_URL, url) | |
4f3e9430 | 482 | channel_id = mobj.group('id') |
3946864c | 483 | return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id) |
55a10eab JMF |
484 | |
485 | ||
486 | class VimeoUserIE(VimeoChannelIE): | |
9148eb00 | 487 | IE_NAME = 'vimeo:user' |
3946864c | 488 | _VALID_URL = r'https://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)' |
55a10eab | 489 | _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>' |
2929b3e7 | 490 | _TESTS = [{ |
3946864c | 491 | 'url': 'https://vimeo.com/nkistudio/videos', |
2929b3e7 PH |
492 | 'info_dict': { |
493 | 'title': 'Nki', | |
a3fa5da4 | 494 | 'id': 'nkistudio', |
2929b3e7 PH |
495 | }, |
496 | 'playlist_mincount': 66, | |
497 | }] | |
55a10eab JMF |
498 | |
499 | def _real_extract(self, url): | |
500 | mobj = re.match(self._VALID_URL, url) | |
501 | name = mobj.group('name') | |
3946864c | 502 | return self._extract_videos(name, 'https://vimeo.com/%s' % name) |
5cc14c2f JMF |
503 | |
504 | ||
505 | class VimeoAlbumIE(VimeoChannelIE): | |
9148eb00 | 506 | IE_NAME = 'vimeo:album' |
d1508cd6 | 507 | _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)' |
5cc14c2f | 508 | _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>' |
2929b3e7 | 509 | _TESTS = [{ |
d1508cd6 | 510 | 'url': 'https://vimeo.com/album/2632481', |
2929b3e7 | 511 | 'info_dict': { |
a3fa5da4 | 512 | 'id': '2632481', |
2929b3e7 PH |
513 | 'title': 'Staff Favorites: November 2013', |
514 | }, | |
515 | 'playlist_mincount': 13, | |
bf8f082a PH |
516 | }, { |
517 | 'note': 'Password-protected album', | |
518 | 'url': 'https://vimeo.com/album/3253534', | |
519 | 'info_dict': { | |
520 | 'title': 'test', | |
521 | 'id': '3253534', | |
522 | }, | |
523 | 'playlist_count': 1, | |
524 | 'params': { | |
525 | 'videopassword': 'youtube-dl', | |
526 | } | |
2929b3e7 | 527 | }] |
5cc14c2f JMF |
528 | |
529 | def _page_url(self, base_url, pagenum): | |
530 | return '%s/page:%d/' % (base_url, pagenum) | |
531 | ||
532 | def _real_extract(self, url): | |
bf8f082a | 533 | album_id = self._match_id(url) |
d1508cd6 | 534 | return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id) |
fb30ec22 JMF |
535 | |
536 | ||
537 | class VimeoGroupsIE(VimeoAlbumIE): | |
9148eb00 | 538 | IE_NAME = 'vimeo:group' |
3946864c | 539 | _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)' |
2929b3e7 | 540 | _TESTS = [{ |
3946864c | 541 | 'url': 'https://vimeo.com/groups/rolexawards', |
2929b3e7 | 542 | 'info_dict': { |
a3fa5da4 | 543 | 'id': 'rolexawards', |
2929b3e7 PH |
544 | 'title': 'Rolex Awards for Enterprise', |
545 | }, | |
546 | 'playlist_mincount': 73, | |
547 | }] | |
fb30ec22 JMF |
548 | |
549 | def _extract_list_title(self, webpage): | |
550 | return self._og_search_title(webpage) | |
551 | ||
552 | def _real_extract(self, url): | |
553 | mobj = re.match(self._VALID_URL, url) | |
554 | name = mobj.group('name') | |
3946864c | 555 | return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name) |
fcea44c6 PH |
556 | |
557 | ||
558 | class VimeoReviewIE(InfoExtractor): | |
9148eb00 PH |
559 | IE_NAME = 'vimeo:review' |
560 | IE_DESC = 'Review pages on vimeo' | |
3946864c | 561 | _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)' |
d36d3f42 | 562 | _TESTS = [{ |
fcea44c6 | 563 | 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d', |
fcea44c6 PH |
564 | 'md5': 'c507a72f780cacc12b2248bb4006d253', |
565 | 'info_dict': { | |
fc09240e PH |
566 | 'id': '75524534', |
567 | 'ext': 'mp4', | |
fcea44c6 PH |
568 | 'title': "DICK HARDWICK 'Comedian'", |
569 | 'uploader': 'Richard Hardwick', | |
570 | } | |
d36d3f42 PH |
571 | }, { |
572 | 'note': 'video player needs Referer', | |
3946864c | 573 | 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053', |
d36d3f42 PH |
574 | 'md5': '6295fdab8f4bf6a002d058b2c6dce276', |
575 | 'info_dict': { | |
576 | 'id': '91613211', | |
577 | 'ext': 'mp4', | |
9dec9930 | 578 | 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn', |
d36d3f42 PH |
579 | 'uploader': 'DevWeek Events', |
580 | 'duration': 2773, | |
581 | 'thumbnail': 're:^https?://.*\.jpg$', | |
582 | } | |
583 | }] | |
fcea44c6 PH |
584 | |
585 | def _real_extract(self, url): | |
586 | mobj = re.match(self._VALID_URL, url) | |
587 | video_id = mobj.group('id') | |
588 | player_url = 'https://player.vimeo.com/player/' + video_id | |
589 | return self.url_result(player_url, 'Vimeo', video_id) | |
efb7e119 JMF |
590 | |
591 | ||
592 | class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE): | |
593 | IE_NAME = 'vimeo:watchlater' | |
594 | IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)' | |
3946864c | 595 | _VALID_URL = r'https://vimeo\.com/home/watchlater|:vimeowatchlater' |
efb7e119 JMF |
596 | _LOGIN_REQUIRED = True |
597 | _TITLE_RE = r'href="/home/watchlater".*?>(.*?)<' | |
2929b3e7 | 598 | _TESTS = [{ |
3946864c | 599 | 'url': 'https://vimeo.com/home/watchlater', |
2929b3e7 PH |
600 | 'only_matching': True, |
601 | }] | |
efb7e119 JMF |
602 | |
603 | def _real_initialize(self): | |
604 | self._login() | |
605 | ||
606 | def _page_url(self, base_url, pagenum): | |
607 | url = '%s/page:%d/' % (base_url, pagenum) | |
608 | request = compat_urllib_request.Request(url) | |
609 | # Set the header to get a partial html page with the ids, | |
610 | # the normal page doesn't contain them. | |
611 | request.add_header('X-Requested-With', 'XMLHttpRequest') | |
612 | return request | |
613 | ||
614 | def _real_extract(self, url): | |
615 | return self._extract_videos('watchlater', 'https://vimeo.com/home/watchlater') | |
d6e6a422 PH |
616 | |
617 | ||
618 | class VimeoLikesIE(InfoExtractor): | |
3946864c | 619 | _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)' |
d6e6a422 PH |
620 | IE_NAME = 'vimeo:likes' |
621 | IE_DESC = 'Vimeo user likes' | |
622 | _TEST = { | |
9c44d242 PH |
623 | 'url': 'https://vimeo.com/user755559/likes/', |
624 | 'playlist_mincount': 293, | |
d6e6a422 | 625 | "info_dict": { |
a3fa5da4 | 626 | 'id': 'user755559_likes', |
9c44d242 PH |
627 | "description": "See all the videos urza likes", |
628 | "title": 'Videos urza likes', | |
d6e6a422 PH |
629 | }, |
630 | } | |
631 | ||
632 | def _real_extract(self, url): | |
633 | user_id = self._match_id(url) | |
9c44d242 PH |
634 | webpage = self._download_webpage(url, user_id) |
635 | page_count = self._int( | |
636 | self._search_regex( | |
637 | r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)"> | |
638 | .*?</a></li>\s*<li\s+class="pagination_next"> | |
639 | ''', webpage, 'page count'), | |
640 | 'page count', fatal=True) | |
641 | PAGE_SIZE = 12 | |
642 | title = self._html_search_regex( | |
643 | r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False) | |
644 | description = self._html_search_meta('description', webpage) | |
645 | ||
646 | def _get_page(idx): | |
3946864c JMF |
647 | page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % ( |
648 | user_id, idx + 1) | |
9c44d242 PH |
649 | webpage = self._download_webpage( |
650 | page_url, user_id, | |
651 | note='Downloading page %d/%d' % (idx + 1, page_count)) | |
652 | video_list = self._search_regex( | |
653 | r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>', | |
654 | webpage, 'video content') | |
655 | paths = re.findall( | |
656 | r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list) | |
657 | for path in paths: | |
658 | yield { | |
659 | '_type': 'url', | |
660 | 'url': compat_urlparse.urljoin(page_url, path), | |
661 | } | |
662 | ||
663 | pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE) | |
d6e6a422 PH |
664 | |
665 | return { | |
9c44d242 PH |
666 | '_type': 'playlist', |
667 | 'id': 'user%s_likes' % user_id, | |
668 | 'title': title, | |
669 | 'description': description, | |
670 | 'entries': pl, | |
d6e6a422 | 671 | } |