1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
|
# encoding: utf-8
import json
import re
import itertools
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
compat_urllib_request,
clean_html,
get_element_by_attribute,
ExtractorError,
RegexNotFoundError,
std_headers,
unsmuggle_url,
)
class VimeoIE(InfoExtractor):
"""Information extractor for vimeo.com."""
# _VALID_URL matches Vimeo URLs
_VALID_URL = r'''(?x)
(?P<proto>https?://)?
(?:(?:www|(?P<player>player))\.)?
vimeo(?P<pro>pro)?\.com/
(?:.*?/)?
(?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)?
(?:videos?/)?
(?P<id>[0-9]+)
/?(?:[?&].*)?(?:[#].*)?$'''
_NETRC_MACHINE = 'vimeo'
IE_NAME = u'vimeo'
_TESTS = [
{
u'url': u'http://vimeo.com/56015672#at=0',
u'file': u'56015672.mp4',
u'md5': u'8879b6cc097e987f02484baf890129e5',
u'info_dict': {
u"upload_date": u"20121220",
u"description": u"This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
u"uploader_id": u"user7108434",
u"uploader": u"Filippo Valsorda",
u"title": u"youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
},
},
{
u'url': u'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
u'file': u'68093876.mp4',
u'md5': u'3b5ca6aa22b60dfeeadf50b72e44ed82',
u'note': u'Vimeo Pro video (#1197)',
u'info_dict': {
u'uploader_id': u'openstreetmapus',
u'uploader': u'OpenStreetMap US',
u'title': u'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
},
},
{
u'url': u'http://player.vimeo.com/video/54469442',
u'file': u'54469442.mp4',
u'md5': u'619b811a4417aa4abe78dc653becf511',
u'note': u'Videos that embed the url in the player page',
u'info_dict': {
u'title': u'Kathy Sierra: Building the minimum Badass User, Business of Software',
u'uploader': u'The BLN & Business of Software',
},
},
{
u'url': u'http://vimeo.com/68375962',
u'file': u'68375962.mp4',
u'md5': u'aaf896bdb7ddd6476df50007a0ac0ae7',
u'note': u'Video protected with password',
u'info_dict': {
u'title': u'youtube-dl password protected test video',
u'upload_date': u'20130614',
u'uploader_id': u'user18948128',
u'uploader': u'Jaime Marquínez Ferrándiz',
},
u'params': {
u'videopassword': u'youtube-dl',
},
},
]
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
self.report_login()
login_url = 'https://vimeo.com/log_in'
webpage = self._download_webpage(login_url, None, False)
token = re.search(r'xsrft: \'(.*?)\'', webpage).group(1)
data = compat_urllib_parse.urlencode({'email': username,
'password': password,
'action': 'login',
'service': 'vimeo',
'token': token,
})
login_request = compat_urllib_request.Request(login_url, data)
login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
login_request.add_header('Cookie', 'xsrft=%s' % token)
self._download_webpage(login_request, None, False, u'Wrong login info')
def _verify_video_password(self, url, video_id, webpage):
password = self._downloader.params.get('videopassword', None)
if password is None:
raise ExtractorError(u'This video is protected by a password, use the --video-password option')
token = re.search(r'xsrft: \'(.*?)\'', webpage).group(1)
data = compat_urllib_parse.urlencode({'password': password,
'token': token})
# I didn't manage to use the password with https
if url.startswith('https'):
pass_url = url.replace('https','http')
else:
pass_url = url
password_request = compat_urllib_request.Request(pass_url+'/password', data)
password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
password_request.add_header('Cookie', 'xsrft=%s' % token)
self._download_webpage(password_request, video_id,
u'Verifying the password',
u'Wrong password')
def _real_initialize(self):
self._login()
def _real_extract(self, url):
url, data = unsmuggle_url(url)
headers = std_headers
if data is not None:
headers = headers.copy()
headers.update(data)
# Extract ID from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('id')
if mobj.group('pro') or mobj.group('player'):
url = 'http://player.vimeo.com/video/' + video_id
else:
url = 'https://vimeo.com/' + video_id
# Retrieve video webpage to extract further information
request = compat_urllib_request.Request(url, None, headers)
webpage = self._download_webpage(request, video_id)
# Now we begin extracting as much information as we can from what we
# retrieved. First we extract the information common to all extractors,
# and latter we extract those that are Vimeo specific.
self.report_extraction(video_id)
# Extract the config JSON
try:
try:
config_url = self._html_search_regex(
r' data-config-url="(.+?)"', webpage, u'config URL')
config_json = self._download_webpage(config_url, video_id)
config = json.loads(config_json)
except RegexNotFoundError:
# For pro videos or player.vimeo.com urls
# We try to find out to which variable is assigned the config dic
m_variable_name = re.search('(\w)\.video\.id', webpage)
if m_variable_name is not None:
config_re = r'%s=({.+?});' % re.escape(m_variable_name.group(1))
else:
config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
config = self._search_regex(config_re, webpage, u'info section',
flags=re.DOTALL)
config = json.loads(config)
except Exception as e:
if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
raise ExtractorError(u'The author has restricted the access to this video, try with the "--referer" option')
if re.search('<form[^>]+?id="pw_form"', webpage) is not None:
self._verify_video_password(url, video_id, webpage)
return self._real_extract(url)
else:
raise ExtractorError(u'Unable to extract info section',
cause=e)
# Extract title
video_title = config["video"]["title"]
# Extract uploader and uploader_id
video_uploader = config["video"]["owner"]["name"]
video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None
# Extract video thumbnail
video_thumbnail = config["video"].get("thumbnail")
if video_thumbnail is None:
_, video_thumbnail = sorted((int(width), t_url) for (width, t_url) in config["video"]["thumbs"].items())[-1]
# Extract video description
video_description = None
try:
video_description = get_element_by_attribute("itemprop", "description", webpage)
if video_description: video_description = clean_html(video_description)
except AssertionError as err:
# On some pages like (http://player.vimeo.com/video/54469442) the
# html tags are not closed, python 2.6 cannot handle it
if err.args[0] == 'we should not get here!':
pass
else:
raise
# Extract upload date
video_upload_date = None
mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage)
if mobj is not None:
video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)
try:
view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, u'view count'))
like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, u'like count'))
comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, u'comment count'))
except RegexNotFoundError:
# This info is only available in vimeo.com/{id} urls
view_count = None
like_count = None
comment_count = None
# Vimeo specific: extract request signature and timestamp
sig = config['request']['signature']
timestamp = config['request']['timestamp']
# Vimeo specific: extract video codec and quality information
# First consider quality, then codecs, then take everything
codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')]
files = {'hd': [], 'sd': [], 'other': []}
config_files = config["video"].get("files") or config["request"].get("files")
for codec_name, codec_extension in codecs:
for quality in config_files.get(codec_name, []):
format_id = '-'.join((codec_name, quality)).lower()
key = quality if quality in files else 'other'
video_url = None
if isinstance(config_files[codec_name], dict):
file_info = config_files[codec_name][quality]
video_url = file_info.get('url')
else:
file_info = {}
if video_url is None:
video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
%(video_id, sig, timestamp, quality, codec_name.upper())
files[key].append({
'ext': codec_extension,
'url': video_url,
'format_id': format_id,
'width': file_info.get('width'),
'height': file_info.get('height'),
})
formats = []
for key in ('other', 'sd', 'hd'):
formats += files[key]
if len(formats) == 0:
raise ExtractorError(u'No known codec found')
return {
'id': video_id,
'uploader': video_uploader,
'uploader_id': video_uploader_id,
'upload_date': video_upload_date,
'title': video_title,
'thumbnail': video_thumbnail,
'description': video_description,
'formats': formats,
'webpage_url': url,
'view_count': view_count,
'like_count': like_count,
'comment_count': comment_count,
}
class VimeoChannelIE(InfoExtractor):
IE_NAME = u'vimeo:channel'
_VALID_URL = r'(?:https?://)?vimeo.\com/channels/(?P<id>[^/]+)'
_MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
_TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
def _page_url(self, base_url, pagenum):
return '%s/videos/page:%d/' % (base_url, pagenum)
def _extract_list_title(self, webpage):
return self._html_search_regex(self._TITLE_RE, webpage, u'list title')
def _extract_videos(self, list_id, base_url):
video_ids = []
for pagenum in itertools.count(1):
webpage = self._download_webpage(
self._page_url(base_url, pagenum) ,list_id,
u'Downloading page %s' % pagenum)
video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
break
entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
for video_id in video_ids]
return {'_type': 'playlist',
'id': list_id,
'title': self._extract_list_title(webpage),
'entries': entries,
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
channel_id = mobj.group('id')
return self._extract_videos(channel_id, 'http://vimeo.com/channels/%s' % channel_id)
class VimeoUserIE(VimeoChannelIE):
IE_NAME = u'vimeo:user'
_VALID_URL = r'(?:https?://)?vimeo.\com/(?P<name>[^/]+)(?:[#?]|$)'
_TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
@classmethod
def suitable(cls, url):
if VimeoChannelIE.suitable(url) or VimeoIE.suitable(url) or VimeoAlbumIE.suitable(url) or VimeoGroupsIE.suitable(url):
return False
return super(VimeoUserIE, cls).suitable(url)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
name = mobj.group('name')
return self._extract_videos(name, 'http://vimeo.com/%s' % name)
class VimeoAlbumIE(VimeoChannelIE):
IE_NAME = u'vimeo:album'
_VALID_URL = r'(?:https?://)?vimeo.\com/album/(?P<id>\d+)'
_TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
def _page_url(self, base_url, pagenum):
return '%s/page:%d/' % (base_url, pagenum)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
album_id = mobj.group('id')
return self._extract_videos(album_id, 'http://vimeo.com/album/%s' % album_id)
class VimeoGroupsIE(VimeoAlbumIE):
IE_NAME = u'vimeo:group'
_VALID_URL = r'(?:https?://)?vimeo.\com/groups/(?P<name>[^/]+)'
def _extract_list_title(self, webpage):
return self._og_search_title(webpage)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
name = mobj.group('name')
return self._extract_videos(name, 'http://vimeo.com/groups/%s' % name)
class VimeoReviewIE(InfoExtractor):
IE_NAME = u'vimeo:review'
IE_DESC = u'Review pages on vimeo'
_VALID_URL = r'(?:https?://)?vimeo.\com/[^/]+/review/(?P<id>[^/]+)'
_TEST = {
'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
'file': '75524534.mp4',
'md5': 'c507a72f780cacc12b2248bb4006d253',
'info_dict': {
'title': "DICK HARDWICK 'Comedian'",
'uploader': 'Richard Hardwick',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
player_url = 'https://player.vimeo.com/player/' + video_id
return self.url_result(player_url, 'Vimeo', video_id)
|