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
|
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,
std_headers,
)
class VimeoIE(InfoExtractor):
"""Information extractor for vimeo.com."""
# _VALID_URL matches Vimeo URLs
_VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)(?:[?].*)?$'
_NETRC_MACHINE = 'vimeo'
IE_NAME = u'vimeo'
_TESTS = [
{
u'url': u'http://vimeo.com/56015672',
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',
},
},
]
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, new_video=True):
# 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 not mobj.group('proto'):
url = 'https://' + url
elif mobj.group('pro'):
url = 'http://player.vimeo.com/video/' + video_id
elif mobj.group('direct_link'):
url = 'https://vimeo.com/' + video_id
# Retrieve video webpage to extract further information
request = compat_urllib_request.Request(url, None, std_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:
config = webpage.split(' = {config:')[1].split(',assets:')[0]
config = json.loads(config)
except:
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('If so please provide the correct password.', webpage):
self._verify_video_password(url, video_id, webpage)
return self._real_extract(url)
else:
raise ExtractorError(u'Unable to extract info section')
# 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"]["thumbnail"]
# Extract video description
video_description = get_element_by_attribute("itemprop", "description", webpage)
if video_description: video_description = clean_html(video_description)
else: video_description = u''
# 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)
# 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
# TODO bind to format param
codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')]
files = { 'hd': [], 'sd': [], 'other': []}
for codec_name, codec_extension in codecs:
if codec_name in config["video"]["files"]:
if 'hd' in config["video"]["files"][codec_name]:
files['hd'].append((codec_name, codec_extension, 'hd'))
elif 'sd' in config["video"]["files"][codec_name]:
files['sd'].append((codec_name, codec_extension, 'sd'))
else:
files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0]))
for quality in ('hd', 'sd', 'other'):
if len(files[quality]) > 0:
video_quality = files[quality][0][2]
video_codec = files[quality][0][0]
video_extension = files[quality][0][1]
self.to_screen(u'%s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality))
break
else:
raise ExtractorError(u'No known codec found')
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, video_quality, video_codec.upper())
return [{
'id': video_id,
'url': video_url,
'uploader': video_uploader,
'uploader_id': video_uploader_id,
'upload_date': video_upload_date,
'title': video_title,
'ext': video_extension,
'thumbnail': video_thumbnail,
'description': video_description,
}]
class VimeoChannelIE(InfoExtractor):
IE_NAME = u'vimeo:channel'
_VALID_URL = r'(?:https?://)?vimeo.\com/channels/(?P<id>[^/]+)'
_MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
channel_id = mobj.group('id')
video_ids = []
for pagenum in itertools.count(1):
webpage = self._download_webpage('http://vimeo.com/channels/%s/videos/page:%d' % (channel_id, pagenum),
channel_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]
channel_title = self._html_search_regex(r'<a href="/channels/%s">(.*?)</a>' % channel_id,
webpage, u'channel title')
return {'_type': 'playlist',
'id': channel_id,
'title': channel_title,
'entries': entries,
}
|
