2 from __future__ import unicode_literals
8 from .common import InfoExtractor
9 from .subtitles import SubtitlesInfoExtractor
12 compat_urllib_request,
14 get_element_by_attribute,
22 class VimeoIE(SubtitlesInfoExtractor):
23 """Information extractor for vimeo.com."""
25 # _VALID_URL matches Vimeo URLs
27 (?P<proto>(?:https?:)?//)?
28 (?:(?:www|(?P<player>player))\.)?
29 vimeo(?P<pro>pro)?\.com/
31 (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)?
34 /?(?:[?&].*)?(?:[#].*)?$'''
35 _NETRC_MACHINE = 'vimeo'
39 'url': 'http://vimeo.com/56015672#at=0',
40 'md5': '8879b6cc097e987f02484baf890129e5',
44 "upload_date": "20121220",
45 "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",
46 "uploader_id": "user7108434",
47 "uploader": "Filippo Valsorda",
48 "title": "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
52 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
53 'file': '68093876.mp4',
54 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
55 'note': 'Vimeo Pro video (#1197)',
57 'uploader_id': 'openstreetmapus',
58 'uploader': 'OpenStreetMap US',
59 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
63 'url': 'http://player.vimeo.com/video/54469442',
64 'file': '54469442.mp4',
65 'md5': '619b811a4417aa4abe78dc653becf511',
66 'note': 'Videos that embed the url in the player page',
68 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software',
69 'uploader': 'The BLN & Business of Software',
70 'uploader_id': 'theblnbusinessofsoftware',
74 'url': 'http://vimeo.com/68375962',
75 'file': '68375962.mp4',
76 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
77 'note': 'Video protected with password',
79 'title': 'youtube-dl password protected test video',
80 'upload_date': '20130614',
81 'uploader_id': 'user18948128',
82 'uploader': 'Jaime Marquínez Ferrándiz',
85 'videopassword': 'youtube-dl',
89 'url': 'http://vimeo.com/76979871',
90 'md5': '3363dd6ffebe3784d56f4132317fd446',
91 'note': 'Video with subtitles',
95 'title': 'The New Vimeo Player (You Know, For Videos)',
96 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
97 'upload_date': '20131015',
98 'uploader_id': 'staff',
99 'uploader': 'Vimeo Staff',
105 (username, password) = self._get_login_info()
109 login_url = 'https://vimeo.com/log_in'
110 webpage = self._download_webpage(login_url, None, False)
111 token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
112 data = compat_urllib_parse.urlencode({'email': username,
113 'password': password,
118 login_request = compat_urllib_request.Request(login_url, data)
119 login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
120 login_request.add_header('Cookie', 'xsrft=%s' % token)
121 self._download_webpage(login_request, None, False, 'Wrong login info')
123 def _verify_video_password(self, url, video_id, webpage):
124 password = self._downloader.params.get('videopassword', None)
126 raise ExtractorError('This video is protected by a password, use the --video-password option')
127 token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
128 data = compat_urllib_parse.urlencode({'password': password,
130 # I didn't manage to use the password with https
131 if url.startswith('https'):
132 pass_url = url.replace('https','http')
135 password_request = compat_urllib_request.Request(pass_url+'/password', data)
136 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
137 password_request.add_header('Cookie', 'xsrft=%s' % token)
138 self._download_webpage(password_request, video_id,
139 'Verifying the password',
142 def _verify_player_video_password(self, url, video_id):
143 password = self._downloader.params.get('videopassword', None)
145 raise ExtractorError('This video is protected by a password, use the --video-password option')
146 data = compat_urllib_parse.urlencode({'password': password})
147 pass_url = url + '/check-password'
148 password_request = compat_urllib_request.Request(pass_url, data)
149 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
150 return self._download_json(
151 password_request, video_id,
152 'Verifying the password',
155 def _real_initialize(self):
158 def _real_extract(self, url):
159 url, data = unsmuggle_url(url)
160 headers = std_headers
162 headers = headers.copy()
165 # Extract ID from URL
166 mobj = re.match(self._VALID_URL, url)
167 video_id = mobj.group('id')
168 if mobj.group('pro') or mobj.group('player'):
169 url = 'http://player.vimeo.com/video/' + video_id
171 url = 'https://vimeo.com/' + video_id
173 # Retrieve video webpage to extract further information
174 request = compat_urllib_request.Request(url, None, headers)
175 webpage = self._download_webpage(request, video_id)
177 # Now we begin extracting as much information as we can from what we
178 # retrieved. First we extract the information common to all extractors,
179 # and latter we extract those that are Vimeo specific.
180 self.report_extraction(video_id)
182 # Extract the config JSON
185 config_url = self._html_search_regex(
186 r' data-config-url="(.+?)"', webpage, 'config URL')
187 config_json = self._download_webpage(config_url, video_id)
188 config = json.loads(config_json)
189 except RegexNotFoundError:
190 # For pro videos or player.vimeo.com urls
191 # We try to find out to which variable is assigned the config dic
192 m_variable_name = re.search('(\w)\.video\.id', webpage)
193 if m_variable_name is not None:
194 config_re = r'%s=({.+?});' % re.escape(m_variable_name.group(1))
196 config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
197 config = self._search_regex(config_re, webpage, 'info section',
199 config = json.loads(config)
200 except Exception as e:
201 if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
202 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
204 if re.search('<form[^>]+?id="pw_form"', webpage) is not None:
205 self._verify_video_password(url, video_id, webpage)
206 return self._real_extract(url)
208 raise ExtractorError('Unable to extract info section',
211 if config.get('view') == 4:
212 config = self._verify_player_video_password(url, video_id)
215 video_title = config["video"]["title"]
217 # Extract uploader and uploader_id
218 video_uploader = config["video"]["owner"]["name"]
219 video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None
221 # Extract video thumbnail
222 video_thumbnail = config["video"].get("thumbnail")
223 if video_thumbnail is None:
224 video_thumbs = config["video"].get("thumbs")
225 if video_thumbs and isinstance(video_thumbs, dict):
226 _, video_thumbnail = sorted((int(width), t_url) for (width, t_url) in video_thumbs.items())[-1]
228 # Extract video description
229 video_description = None
231 video_description = get_element_by_attribute("itemprop", "description", webpage)
232 if video_description: video_description = clean_html(video_description)
233 except AssertionError as err:
234 # On some pages like (http://player.vimeo.com/video/54469442) the
235 # html tags are not closed, python 2.6 cannot handle it
236 if err.args[0] == 'we should not get here!':
241 # Extract upload date
242 video_upload_date = None
243 mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage)
245 video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)
248 view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
249 like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
250 comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
251 except RegexNotFoundError:
252 # This info is only available in vimeo.com/{id} urls
257 # Vimeo specific: extract request signature and timestamp
258 sig = config['request']['signature']
259 timestamp = config['request']['timestamp']
261 # Vimeo specific: extract video codec and quality information
262 # First consider quality, then codecs, then take everything
263 codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')]
264 files = {'hd': [], 'sd': [], 'other': []}
265 config_files = config["video"].get("files") or config["request"].get("files")
266 for codec_name, codec_extension in codecs:
267 for quality in config_files.get(codec_name, []):
268 format_id = '-'.join((codec_name, quality)).lower()
269 key = quality if quality in files else 'other'
271 if isinstance(config_files[codec_name], dict):
272 file_info = config_files[codec_name][quality]
273 video_url = file_info.get('url')
276 if video_url is None:
277 video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
278 %(video_id, sig, timestamp, quality, codec_name.upper())
281 'ext': codec_extension,
283 'format_id': format_id,
284 'width': file_info.get('width'),
285 'height': file_info.get('height'),
288 for key in ('other', 'sd', 'hd'):
289 formats += files[key]
290 if len(formats) == 0:
291 raise ExtractorError('No known codec found')
294 text_tracks = config['request'].get('text_tracks')
296 for tt in text_tracks:
297 subtitles[tt['lang']] = 'http://vimeo.com' + tt['url']
299 video_subtitles = self.extract_subtitles(video_id, subtitles)
300 if self._downloader.params.get('listsubtitles', False):
301 self._list_available_subtitles(video_id, subtitles)
306 'uploader': video_uploader,
307 'uploader_id': video_uploader_id,
308 'upload_date': video_upload_date,
309 'title': video_title,
310 'thumbnail': video_thumbnail,
311 'description': video_description,
314 'view_count': view_count,
315 'like_count': like_count,
316 'comment_count': comment_count,
317 'subtitles': video_subtitles,
321 class VimeoChannelIE(InfoExtractor):
322 IE_NAME = 'vimeo:channel'
323 _VALID_URL = r'(?:https?://)?vimeo\.com/channels/(?P<id>[^/]+)'
324 _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
325 _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
327 def _page_url(self, base_url, pagenum):
328 return '%s/videos/page:%d/' % (base_url, pagenum)
330 def _extract_list_title(self, webpage):
331 return self._html_search_regex(self._TITLE_RE, webpage, 'list title')
333 def _extract_videos(self, list_id, base_url):
335 for pagenum in itertools.count(1):
336 webpage = self._download_webpage(
337 self._page_url(base_url, pagenum) ,list_id,
338 'Downloading page %s' % pagenum)
339 video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
340 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
343 entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
344 for video_id in video_ids]
345 return {'_type': 'playlist',
347 'title': self._extract_list_title(webpage),
351 def _real_extract(self, url):
352 mobj = re.match(self._VALID_URL, url)
353 channel_id = mobj.group('id')
354 return self._extract_videos(channel_id, 'http://vimeo.com/channels/%s' % channel_id)
357 class VimeoUserIE(VimeoChannelIE):
358 IE_NAME = 'vimeo:user'
359 _VALID_URL = r'(?:https?://)?vimeo\.com/(?P<name>[^/]+)(?:/videos|[#?]|$)'
360 _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
363 def suitable(cls, url):
364 if VimeoChannelIE.suitable(url) or VimeoIE.suitable(url) or VimeoAlbumIE.suitable(url) or VimeoGroupsIE.suitable(url):
366 return super(VimeoUserIE, cls).suitable(url)
368 def _real_extract(self, url):
369 mobj = re.match(self._VALID_URL, url)
370 name = mobj.group('name')
371 return self._extract_videos(name, 'http://vimeo.com/%s' % name)
374 class VimeoAlbumIE(VimeoChannelIE):
375 IE_NAME = 'vimeo:album'
376 _VALID_URL = r'(?:https?://)?vimeo\.com/album/(?P<id>\d+)'
377 _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
379 def _page_url(self, base_url, pagenum):
380 return '%s/page:%d/' % (base_url, pagenum)
382 def _real_extract(self, url):
383 mobj = re.match(self._VALID_URL, url)
384 album_id = mobj.group('id')
385 return self._extract_videos(album_id, 'http://vimeo.com/album/%s' % album_id)
388 class VimeoGroupsIE(VimeoAlbumIE):
389 IE_NAME = 'vimeo:group'
390 _VALID_URL = r'(?:https?://)?vimeo\.com/groups/(?P<name>[^/]+)'
392 def _extract_list_title(self, webpage):
393 return self._og_search_title(webpage)
395 def _real_extract(self, url):
396 mobj = re.match(self._VALID_URL, url)
397 name = mobj.group('name')
398 return self._extract_videos(name, 'http://vimeo.com/groups/%s' % name)
401 class VimeoReviewIE(InfoExtractor):
402 IE_NAME = 'vimeo:review'
403 IE_DESC = 'Review pages on vimeo'
404 _VALID_URL = r'(?:https?://)?vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
406 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
407 'file': '75524534.mp4',
408 'md5': 'c507a72f780cacc12b2248bb4006d253',
410 'title': "DICK HARDWICK 'Comedian'",
411 'uploader': 'Richard Hardwick',
415 def _real_extract(self, url):
416 mobj = re.match(self._VALID_URL, url)
417 video_id = mobj.group('id')
418 player_url = 'https://player.vimeo.com/player/' + video_id
419 return self.url_result(player_url, 'Vimeo', video_id)