]>
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 | |
1eac553e | 9 | from .subtitles import SubtitlesInfoExtractor |
b3d14cbf | 10 | from ..utils import ( |
9c44d242 | 11 | clean_html, |
1060425c | 12 | compat_HTTPError, |
b3d14cbf PH |
13 | compat_urllib_parse, |
14 | compat_urllib_request, | |
9c44d242 | 15 | compat_urlparse, |
b3d14cbf | 16 | ExtractorError, |
9c44d242 PH |
17 | get_element_by_attribute, |
18 | InAdvancePagedList, | |
19 | int_or_none, | |
55b3e45b | 20 | RegexNotFoundError, |
b3d14cbf | 21 | std_headers, |
9d4660ca | 22 | unsmuggle_url, |
a980bc43 | 23 | urlencode_postdata, |
b3d14cbf PH |
24 | ) |
25 | ||
bbafbe20 | 26 | |
efb7e119 JMF |
27 | class VimeoBaseInfoExtractor(InfoExtractor): |
28 | _NETRC_MACHINE = 'vimeo' | |
29 | _LOGIN_REQUIRED = False | |
30 | ||
31 | def _login(self): | |
32 | (username, password) = self._get_login_info() | |
33 | if username is None: | |
34 | if self._LOGIN_REQUIRED: | |
4f3e9430 | 35 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) |
efb7e119 JMF |
36 | return |
37 | self.report_login() | |
38 | login_url = 'https://vimeo.com/log_in' | |
39 | webpage = self._download_webpage(login_url, None, False) | |
40 | token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token') | |
41 | data = urlencode_postdata({ | |
42 | 'email': username, | |
43 | 'password': password, | |
44 | 'action': 'login', | |
45 | 'service': 'vimeo', | |
46 | 'token': token, | |
47 | }) | |
48 | login_request = compat_urllib_request.Request(login_url, data) | |
49 | login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') | |
50 | login_request.add_header('Cookie', 'xsrft=%s' % token) | |
51 | self._download_webpage(login_request, None, False, 'Wrong login info') | |
52 | ||
53 | ||
54 | class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): | |
b3d14cbf PH |
55 | """Information extractor for vimeo.com.""" |
56 | ||
57 | # _VALID_URL matches Vimeo URLs | |
bbafbe20 | 58 | _VALID_URL = r'''(?x) |
3fabeaa1 | 59 | (?P<proto>(?:https?:)?//)? |
bbafbe20 PH |
60 | (?:(?:www|(?P<player>player))\.)? |
61 | vimeo(?P<pro>pro)?\.com/ | |
2929b3e7 | 62 | (?!channels/[^/?#]+/?(?:$|[?#])|album/) |
bbafbe20 | 63 | (?:.*?/)? |
7115ca84 | 64 | (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)? |
bbafbe20 PH |
65 | (?:videos?/)? |
66 | (?P<id>[0-9]+) | |
7115ca84 | 67 | /?(?:[?&].*)?(?:[#].*)?$''' |
9148eb00 | 68 | IE_NAME = 'vimeo' |
a91b954b JMF |
69 | _TESTS = [ |
70 | { | |
9148eb00 | 71 | 'url': 'http://vimeo.com/56015672#at=0', |
9148eb00 PH |
72 | 'md5': '8879b6cc097e987f02484baf890129e5', |
73 | 'info_dict': { | |
ad5976b4 PH |
74 | 'id': '56015672', |
75 | 'ext': 'mp4', | |
76 | "upload_date": "20121220", | |
77 | "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", | |
78 | "uploader_id": "user7108434", | |
79 | "uploader": "Filippo Valsorda", | |
9148eb00 | 80 | "title": "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", |
69c8fb9e | 81 | "duration": 10, |
a91b954b JMF |
82 | }, |
83 | }, | |
84 | { | |
9148eb00 | 85 | 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876', |
9148eb00 PH |
86 | 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82', |
87 | 'note': 'Vimeo Pro video (#1197)', | |
88 | 'info_dict': { | |
4f3e9430 JMF |
89 | 'id': '68093876', |
90 | 'ext': 'mp4', | |
9148eb00 PH |
91 | 'uploader_id': 'openstreetmapus', |
92 | 'uploader': 'OpenStreetMap US', | |
93 | 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography', | |
69c8fb9e | 94 | 'duration': 1595, |
a91b954b JMF |
95 | }, |
96 | }, | |
aa32314d | 97 | { |
9148eb00 | 98 | 'url': 'http://player.vimeo.com/video/54469442', |
9148eb00 PH |
99 | 'md5': '619b811a4417aa4abe78dc653becf511', |
100 | 'note': 'Videos that embed the url in the player page', | |
101 | 'info_dict': { | |
4f3e9430 JMF |
102 | 'id': '54469442', |
103 | 'ext': 'mp4', | |
0e6ebc13 | 104 | 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012', |
9148eb00 PH |
105 | 'uploader': 'The BLN & Business of Software', |
106 | 'uploader_id': 'theblnbusinessofsoftware', | |
69c8fb9e | 107 | 'duration': 3610, |
aa32314d | 108 | }, |
93b22c78 JMF |
109 | }, |
110 | { | |
9148eb00 | 111 | 'url': 'http://vimeo.com/68375962', |
9148eb00 PH |
112 | 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7', |
113 | 'note': 'Video protected with password', | |
114 | 'info_dict': { | |
4f3e9430 JMF |
115 | 'id': '68375962', |
116 | 'ext': 'mp4', | |
9148eb00 PH |
117 | 'title': 'youtube-dl password protected test video', |
118 | 'upload_date': '20130614', | |
119 | 'uploader_id': 'user18948128', | |
120 | 'uploader': 'Jaime Marquínez Ferrándiz', | |
69c8fb9e | 121 | 'duration': 10, |
93b22c78 | 122 | }, |
9148eb00 PH |
123 | 'params': { |
124 | 'videopassword': 'youtube-dl', | |
93b22c78 JMF |
125 | }, |
126 | }, | |
548f31d9 S |
127 | { |
128 | 'url': 'http://vimeo.com/channels/keypeele/75629013', | |
129 | 'md5': '2f86a05afe9d7abc0b9126d229bbe15d', | |
130 | 'note': 'Video is freely available via original URL ' | |
131 | 'and protected with password when accessed via http://vimeo.com/75629013', | |
132 | 'info_dict': { | |
133 | 'id': '75629013', | |
134 | 'ext': 'mp4', | |
135 | 'title': 'Key & Peele: Terrorist Interrogation', | |
136 | 'description': 'md5:8678b246399b070816b12313e8b4eb5c', | |
137 | 'uploader_id': 'atencio', | |
138 | 'uploader': 'Peter Atencio', | |
139 | 'duration': 187, | |
140 | }, | |
141 | }, | |
1eac553e S |
142 | { |
143 | 'url': 'http://vimeo.com/76979871', | |
144 | 'md5': '3363dd6ffebe3784d56f4132317fd446', | |
145 | 'note': 'Video with subtitles', | |
146 | 'info_dict': { | |
147 | 'id': '76979871', | |
148 | 'ext': 'mp4', | |
149 | 'title': 'The New Vimeo Player (You Know, For Videos)', | |
150 | 'description': 'md5:2ec900bf97c3f389378a96aee11260ea', | |
151 | 'upload_date': '20131015', | |
152 | 'uploader_id': 'staff', | |
153 | 'uploader': 'Vimeo Staff', | |
69c8fb9e | 154 | 'duration': 62, |
1eac553e S |
155 | } |
156 | }, | |
a91b954b | 157 | ] |
b3d14cbf PH |
158 | |
159 | def _verify_video_password(self, url, video_id, webpage): | |
c6c19746 | 160 | password = self._downloader.params.get('videopassword', None) |
b3d14cbf | 161 | if password is None: |
9148eb00 | 162 | raise ExtractorError('This video is protected by a password, use the --video-password option') |
fcee8ee7 | 163 | token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token') |
4f3e9430 JMF |
164 | data = compat_urllib_parse.urlencode({ |
165 | 'password': password, | |
166 | 'token': token, | |
167 | }) | |
b3d14cbf PH |
168 | # I didn't manage to use the password with https |
169 | if url.startswith('https'): | |
4f3e9430 | 170 | pass_url = url.replace('https', 'http') |
b3d14cbf PH |
171 | else: |
172 | pass_url = url | |
4f3e9430 | 173 | password_request = compat_urllib_request.Request(pass_url + '/password', data) |
b3d14cbf PH |
174 | password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') |
175 | password_request.add_header('Cookie', 'xsrft=%s' % token) | |
176 | self._download_webpage(password_request, video_id, | |
9148eb00 PH |
177 | 'Verifying the password', |
178 | 'Wrong password') | |
b3d14cbf | 179 | |
0eecc6a4 PH |
180 | def _verify_player_video_password(self, url, video_id): |
181 | password = self._downloader.params.get('videopassword', None) | |
182 | if password is None: | |
183 | raise ExtractorError('This video is protected by a password, use the --video-password option') | |
184 | data = compat_urllib_parse.urlencode({'password': password}) | |
185 | pass_url = url + '/check-password' | |
186 | password_request = compat_urllib_request.Request(pass_url, data) | |
187 | password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') | |
188 | return self._download_json( | |
189 | password_request, video_id, | |
190 | 'Verifying the password', | |
191 | 'Wrong password') | |
192 | ||
fc79158d JMF |
193 | def _real_initialize(self): |
194 | self._login() | |
195 | ||
a0088bdf | 196 | def _real_extract(self, url): |
9d4660ca PH |
197 | url, data = unsmuggle_url(url) |
198 | headers = std_headers | |
199 | if data is not None: | |
200 | headers = headers.copy() | |
201 | headers.update(data) | |
ba5d51b3 PH |
202 | if 'Referer' not in headers: |
203 | headers['Referer'] = url | |
9d4660ca | 204 | |
b3d14cbf PH |
205 | # Extract ID from URL |
206 | mobj = re.match(self._VALID_URL, url) | |
b3d14cbf | 207 | video_id = mobj.group('id') |
9103bbc5 | 208 | if mobj.group('pro') or mobj.group('player'): |
a91b954b | 209 | url = 'http://player.vimeo.com/video/' + video_id |
b3d14cbf PH |
210 | |
211 | # Retrieve video webpage to extract further information | |
9d4660ca | 212 | request = compat_urllib_request.Request(url, None, headers) |
1060425c PH |
213 | try: |
214 | webpage = self._download_webpage(request, video_id) | |
215 | except ExtractorError as ee: | |
216 | if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: | |
217 | errmsg = ee.cause.read() | |
218 | if b'Because of its privacy settings, this video cannot be played here' in errmsg: | |
219 | raise ExtractorError( | |
220 | 'Cannot download embed-only video without embedding ' | |
221 | 'URL. Please call youtube-dl with the URL of the page ' | |
222 | 'that embeds this video.', | |
223 | expected=True) | |
224 | raise | |
b3d14cbf PH |
225 | |
226 | # Now we begin extracting as much information as we can from what we | |
227 | # retrieved. First we extract the information common to all extractors, | |
228 | # and latter we extract those that are Vimeo specific. | |
229 | self.report_extraction(video_id) | |
230 | ||
231 | # Extract the config JSON | |
232 | try: | |
93b22c78 JMF |
233 | try: |
234 | config_url = self._html_search_regex( | |
9148eb00 | 235 | r' data-config-url="(.+?)"', webpage, 'config URL') |
93b22c78 JMF |
236 | config_json = self._download_webpage(config_url, video_id) |
237 | config = json.loads(config_json) | |
238 | except RegexNotFoundError: | |
239 | # For pro videos or player.vimeo.com urls | |
48ad51b2 JMF |
240 | # We try to find out to which variable is assigned the config dic |
241 | m_variable_name = re.search('(\w)\.video\.id', webpage) | |
242 | if m_variable_name is not None: | |
243 | config_re = r'%s=({.+?});' % re.escape(m_variable_name.group(1)) | |
244 | else: | |
245 | config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});'] | |
9148eb00 | 246 | config = self._search_regex(config_re, webpage, 'info section', |
48ad51b2 | 247 | flags=re.DOTALL) |
93b22c78 | 248 | config = json.loads(config) |
71907db3 | 249 | except Exception as e: |
b3d14cbf | 250 | if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage): |
9148eb00 | 251 | raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option') |
b3d14cbf | 252 | |
93b22c78 | 253 | if re.search('<form[^>]+?id="pw_form"', webpage) is not None: |
b3d14cbf PH |
254 | self._verify_video_password(url, video_id, webpage) |
255 | return self._real_extract(url) | |
256 | else: | |
9148eb00 | 257 | raise ExtractorError('Unable to extract info section', |
71907db3 | 258 | cause=e) |
559e370f PH |
259 | else: |
260 | if config.get('view') == 4: | |
0eecc6a4 | 261 | config = self._verify_player_video_password(url, video_id) |
b3d14cbf PH |
262 | |
263 | # Extract title | |
264 | video_title = config["video"]["title"] | |
265 | ||
266 | # Extract uploader and uploader_id | |
267 | video_uploader = config["video"]["owner"]["name"] | |
268 | video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None | |
269 | ||
270 | # Extract video thumbnail | |
aa32314d | 271 | video_thumbnail = config["video"].get("thumbnail") |
c0e5d856 S |
272 | if video_thumbnail is None: |
273 | video_thumbs = config["video"].get("thumbs") | |
274 | if video_thumbs and isinstance(video_thumbs, dict): | |
3e510af3 | 275 | _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1] |
b3d14cbf PH |
276 | |
277 | # Extract video description | |
9c2ade40 JMF |
278 | video_description = None |
279 | try: | |
7558830f JMF |
280 | video_description = get_element_by_attribute("class", "description_wrapper", webpage) |
281 | if video_description: | |
282 | video_description = clean_html(video_description) | |
9c2ade40 JMF |
283 | except AssertionError as err: |
284 | # On some pages like (http://player.vimeo.com/video/54469442) the | |
285 | # html tags are not closed, python 2.6 cannot handle it | |
286 | if err.args[0] == 'we should not get here!': | |
287 | pass | |
288 | else: | |
289 | raise | |
b3d14cbf | 290 | |
69c8fb9e S |
291 | # Extract video duration |
292 | video_duration = int_or_none(config["video"].get("duration")) | |
293 | ||
b3d14cbf PH |
294 | # Extract upload date |
295 | video_upload_date = None | |
296 | mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage) | |
297 | if mobj is not None: | |
298 | video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3) | |
299 | ||
4e761794 | 300 | try: |
9148eb00 PH |
301 | view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count')) |
302 | like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count')) | |
303 | comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count')) | |
4e761794 JMF |
304 | except RegexNotFoundError: |
305 | # This info is only available in vimeo.com/{id} urls | |
306 | view_count = None | |
307 | like_count = None | |
308 | comment_count = None | |
309 | ||
b3d14cbf PH |
310 | # Vimeo specific: extract request signature and timestamp |
311 | sig = config['request']['signature'] | |
312 | timestamp = config['request']['timestamp'] | |
313 | ||
314 | # Vimeo specific: extract video codec and quality information | |
315 | # First consider quality, then codecs, then take everything | |
a6387bfd | 316 | codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')] |
a56f9de1 | 317 | files = {'hd': [], 'sd': [], 'other': []} |
aa32314d | 318 | config_files = config["video"].get("files") or config["request"].get("files") |
b3d14cbf | 319 | for codec_name, codec_extension in codecs: |
a6387bfd JE |
320 | for quality in config_files.get(codec_name, []): |
321 | format_id = '-'.join((codec_name, quality)).lower() | |
322 | key = quality if quality in files else 'other' | |
323 | video_url = None | |
324 | if isinstance(config_files[codec_name], dict): | |
325 | file_info = config_files[codec_name][quality] | |
326 | video_url = file_info.get('url') | |
b3d14cbf | 327 | else: |
a6387bfd JE |
328 | file_info = {} |
329 | if video_url is None: | |
330 | 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 | 331 | % (video_id, sig, timestamp, quality, codec_name.upper()) |
a6387bfd JE |
332 | |
333 | files[key].append({ | |
334 | 'ext': codec_extension, | |
335 | 'url': video_url, | |
336 | 'format_id': format_id, | |
337 | 'width': file_info.get('width'), | |
338 | 'height': file_info.get('height'), | |
339 | }) | |
340 | formats = [] | |
341 | for key in ('other', 'sd', 'hd'): | |
342 | formats += files[key] | |
343 | if len(formats) == 0: | |
9148eb00 | 344 | raise ExtractorError('No known codec found') |
b3d14cbf | 345 | |
1eac553e S |
346 | subtitles = {} |
347 | text_tracks = config['request'].get('text_tracks') | |
348 | if text_tracks: | |
349 | for tt in text_tracks: | |
350 | subtitles[tt['lang']] = 'http://vimeo.com' + tt['url'] | |
351 | ||
352 | video_subtitles = self.extract_subtitles(video_id, subtitles) | |
353 | if self._downloader.params.get('listsubtitles', False): | |
354 | self._list_available_subtitles(video_id, subtitles) | |
355 | return | |
356 | ||
9103bbc5 | 357 | return { |
b0268cb6 | 358 | 'id': video_id, |
b3d14cbf PH |
359 | 'uploader': video_uploader, |
360 | 'uploader_id': video_uploader_id, | |
b0268cb6 S |
361 | 'upload_date': video_upload_date, |
362 | 'title': video_title, | |
363 | 'thumbnail': video_thumbnail, | |
364 | 'description': video_description, | |
69c8fb9e | 365 | 'duration': video_duration, |
a6387bfd | 366 | 'formats': formats, |
9103bbc5 | 367 | 'webpage_url': url, |
4e761794 JMF |
368 | 'view_count': view_count, |
369 | 'like_count': like_count, | |
370 | 'comment_count': comment_count, | |
1eac553e | 371 | 'subtitles': video_subtitles, |
9103bbc5 | 372 | } |
caeefc29 JMF |
373 | |
374 | ||
375 | class VimeoChannelIE(InfoExtractor): | |
9148eb00 | 376 | IE_NAME = 'vimeo:channel' |
2929b3e7 | 377 | _VALID_URL = r'https?://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])' |
caeefc29 | 378 | _MORE_PAGES_INDICATOR = r'<a.+?rel="next"' |
55a10eab | 379 | _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"' |
2929b3e7 PH |
380 | _TESTS = [{ |
381 | 'url': 'http://vimeo.com/channels/tributes', | |
382 | 'info_dict': { | |
383 | 'title': 'Vimeo Tributes', | |
384 | }, | |
385 | 'playlist_mincount': 25, | |
386 | }] | |
caeefc29 | 387 | |
5cc14c2f JMF |
388 | def _page_url(self, base_url, pagenum): |
389 | return '%s/videos/page:%d/' % (base_url, pagenum) | |
390 | ||
fb30ec22 | 391 | def _extract_list_title(self, webpage): |
9148eb00 | 392 | return self._html_search_regex(self._TITLE_RE, webpage, 'list title') |
fb30ec22 | 393 | |
55a10eab | 394 | def _extract_videos(self, list_id, base_url): |
caeefc29 | 395 | video_ids = [] |
caeefc29 | 396 | for pagenum in itertools.count(1): |
55a10eab | 397 | webpage = self._download_webpage( |
4f3e9430 | 398 | self._page_url(base_url, pagenum), list_id, |
9148eb00 | 399 | 'Downloading page %s' % pagenum) |
caeefc29 JMF |
400 | video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage)) |
401 | if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: | |
402 | break | |
403 | ||
404 | entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo') | |
405 | for video_id in video_ids] | |
caeefc29 | 406 | return {'_type': 'playlist', |
55a10eab | 407 | 'id': list_id, |
fb30ec22 | 408 | 'title': self._extract_list_title(webpage), |
caeefc29 JMF |
409 | 'entries': entries, |
410 | } | |
55a10eab JMF |
411 | |
412 | def _real_extract(self, url): | |
413 | mobj = re.match(self._VALID_URL, url) | |
4f3e9430 | 414 | channel_id = mobj.group('id') |
55a10eab JMF |
415 | return self._extract_videos(channel_id, 'http://vimeo.com/channels/%s' % channel_id) |
416 | ||
417 | ||
418 | class VimeoUserIE(VimeoChannelIE): | |
9148eb00 | 419 | IE_NAME = 'vimeo:user' |
2929b3e7 | 420 | _VALID_URL = r'https?://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)' |
55a10eab | 421 | _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>' |
2929b3e7 PH |
422 | _TESTS = [{ |
423 | 'url': 'http://vimeo.com/nkistudio/videos', | |
424 | 'info_dict': { | |
425 | 'title': 'Nki', | |
426 | }, | |
427 | 'playlist_mincount': 66, | |
428 | }] | |
55a10eab JMF |
429 | |
430 | def _real_extract(self, url): | |
431 | mobj = re.match(self._VALID_URL, url) | |
432 | name = mobj.group('name') | |
433 | return self._extract_videos(name, 'http://vimeo.com/%s' % name) | |
5cc14c2f JMF |
434 | |
435 | ||
436 | class VimeoAlbumIE(VimeoChannelIE): | |
9148eb00 | 437 | IE_NAME = 'vimeo:album' |
2929b3e7 | 438 | _VALID_URL = r'https?://vimeo\.com/album/(?P<id>\d+)' |
5cc14c2f | 439 | _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>' |
2929b3e7 PH |
440 | _TESTS = [{ |
441 | 'url': 'http://vimeo.com/album/2632481', | |
442 | 'info_dict': { | |
443 | 'title': 'Staff Favorites: November 2013', | |
444 | }, | |
445 | 'playlist_mincount': 13, | |
446 | }] | |
5cc14c2f JMF |
447 | |
448 | def _page_url(self, base_url, pagenum): | |
449 | return '%s/page:%d/' % (base_url, pagenum) | |
450 | ||
451 | def _real_extract(self, url): | |
452 | mobj = re.match(self._VALID_URL, url) | |
fcea44c6 | 453 | album_id = mobj.group('id') |
5cc14c2f | 454 | return self._extract_videos(album_id, 'http://vimeo.com/album/%s' % album_id) |
fb30ec22 JMF |
455 | |
456 | ||
457 | class VimeoGroupsIE(VimeoAlbumIE): | |
9148eb00 | 458 | IE_NAME = 'vimeo:group' |
59188de1 | 459 | _VALID_URL = r'(?:https?://)?vimeo\.com/groups/(?P<name>[^/]+)' |
2929b3e7 PH |
460 | _TESTS = [{ |
461 | 'url': 'http://vimeo.com/groups/rolexawards', | |
462 | 'info_dict': { | |
463 | 'title': 'Rolex Awards for Enterprise', | |
464 | }, | |
465 | 'playlist_mincount': 73, | |
466 | }] | |
fb30ec22 JMF |
467 | |
468 | def _extract_list_title(self, webpage): | |
469 | return self._og_search_title(webpage) | |
470 | ||
471 | def _real_extract(self, url): | |
472 | mobj = re.match(self._VALID_URL, url) | |
473 | name = mobj.group('name') | |
474 | return self._extract_videos(name, 'http://vimeo.com/groups/%s' % name) | |
fcea44c6 PH |
475 | |
476 | ||
477 | class VimeoReviewIE(InfoExtractor): | |
9148eb00 PH |
478 | IE_NAME = 'vimeo:review' |
479 | IE_DESC = 'Review pages on vimeo' | |
d36d3f42 PH |
480 | _VALID_URL = r'https?://vimeo\.com/[^/]+/review/(?P<id>[^/]+)' |
481 | _TESTS = [{ | |
fcea44c6 PH |
482 | 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d', |
483 | 'file': '75524534.mp4', | |
484 | 'md5': 'c507a72f780cacc12b2248bb4006d253', | |
485 | 'info_dict': { | |
486 | 'title': "DICK HARDWICK 'Comedian'", | |
487 | 'uploader': 'Richard Hardwick', | |
488 | } | |
d36d3f42 PH |
489 | }, { |
490 | 'note': 'video player needs Referer', | |
491 | 'url': 'http://vimeo.com/user22258446/review/91613211/13f927e053', | |
492 | 'md5': '6295fdab8f4bf6a002d058b2c6dce276', | |
493 | 'info_dict': { | |
494 | 'id': '91613211', | |
495 | 'ext': 'mp4', | |
496 | 'title': 'Death by dogma versus assembling agile - Sander Hoogendoorn', | |
497 | 'uploader': 'DevWeek Events', | |
498 | 'duration': 2773, | |
499 | 'thumbnail': 're:^https?://.*\.jpg$', | |
500 | } | |
501 | }] | |
fcea44c6 PH |
502 | |
503 | def _real_extract(self, url): | |
504 | mobj = re.match(self._VALID_URL, url) | |
505 | video_id = mobj.group('id') | |
506 | player_url = 'https://player.vimeo.com/player/' + video_id | |
507 | return self.url_result(player_url, 'Vimeo', video_id) | |
efb7e119 JMF |
508 | |
509 | ||
510 | class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE): | |
511 | IE_NAME = 'vimeo:watchlater' | |
512 | IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)' | |
513 | _VALID_URL = r'https?://vimeo\.com/home/watchlater|:vimeowatchlater' | |
514 | _LOGIN_REQUIRED = True | |
515 | _TITLE_RE = r'href="/home/watchlater".*?>(.*?)<' | |
2929b3e7 PH |
516 | _TESTS = [{ |
517 | 'url': 'http://vimeo.com/home/watchlater', | |
518 | 'only_matching': True, | |
519 | }] | |
efb7e119 JMF |
520 | |
521 | def _real_initialize(self): | |
522 | self._login() | |
523 | ||
524 | def _page_url(self, base_url, pagenum): | |
525 | url = '%s/page:%d/' % (base_url, pagenum) | |
526 | request = compat_urllib_request.Request(url) | |
527 | # Set the header to get a partial html page with the ids, | |
528 | # the normal page doesn't contain them. | |
529 | request.add_header('X-Requested-With', 'XMLHttpRequest') | |
530 | return request | |
531 | ||
532 | def _real_extract(self, url): | |
533 | return self._extract_videos('watchlater', 'https://vimeo.com/home/watchlater') | |
d6e6a422 PH |
534 | |
535 | ||
536 | class VimeoLikesIE(InfoExtractor): | |
9c44d242 | 537 | _VALID_URL = r'https?://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)' |
d6e6a422 PH |
538 | IE_NAME = 'vimeo:likes' |
539 | IE_DESC = 'Vimeo user likes' | |
540 | _TEST = { | |
9c44d242 PH |
541 | 'url': 'https://vimeo.com/user755559/likes/', |
542 | 'playlist_mincount': 293, | |
d6e6a422 | 543 | "info_dict": { |
9c44d242 PH |
544 | "description": "See all the videos urza likes", |
545 | "title": 'Videos urza likes', | |
d6e6a422 PH |
546 | }, |
547 | } | |
548 | ||
549 | def _real_extract(self, url): | |
550 | user_id = self._match_id(url) | |
9c44d242 PH |
551 | webpage = self._download_webpage(url, user_id) |
552 | page_count = self._int( | |
553 | self._search_regex( | |
554 | r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)"> | |
555 | .*?</a></li>\s*<li\s+class="pagination_next"> | |
556 | ''', webpage, 'page count'), | |
557 | 'page count', fatal=True) | |
558 | PAGE_SIZE = 12 | |
559 | title = self._html_search_regex( | |
560 | r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False) | |
561 | description = self._html_search_meta('description', webpage) | |
562 | ||
563 | def _get_page(idx): | |
564 | page_url = '%s//vimeo.com/user%s/likes/page:%d/sort:date' % ( | |
565 | self.http_scheme(), user_id, idx + 1) | |
566 | webpage = self._download_webpage( | |
567 | page_url, user_id, | |
568 | note='Downloading page %d/%d' % (idx + 1, page_count)) | |
569 | video_list = self._search_regex( | |
570 | r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>', | |
571 | webpage, 'video content') | |
572 | paths = re.findall( | |
573 | r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list) | |
574 | for path in paths: | |
575 | yield { | |
576 | '_type': 'url', | |
577 | 'url': compat_urlparse.urljoin(page_url, path), | |
578 | } | |
579 | ||
580 | pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE) | |
d6e6a422 PH |
581 | |
582 | return { | |
9c44d242 PH |
583 | '_type': 'playlist', |
584 | 'id': 'user%s_likes' % user_id, | |
585 | 'title': title, | |
586 | 'description': description, | |
587 | 'entries': pl, | |
d6e6a422 | 588 | } |