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
|
from __future__ import unicode_literals
import random
import re
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urlparse,
)
from ..utils import (
encode_data_uri,
ExtractorError,
int_or_none,
float_or_none,
mimetype2ext,
str_or_none,
)
class UstreamIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ustream\.tv/(?P<type>recorded|embed|embed/recorded)/(?P<id>\d+)'
IE_NAME = 'ustream'
_TESTS = [{
'url': 'http://www.ustream.tv/recorded/20274954',
'md5': '088f151799e8f572f84eb62f17d73e5c',
'info_dict': {
'id': '20274954',
'ext': 'flv',
'title': 'Young Americans for Liberty February 7, 2012 2:28 AM',
'description': 'Young Americans for Liberty February 7, 2012 2:28 AM',
'timestamp': 1328577035,
'upload_date': '20120207',
'uploader': 'yaliberty',
'uploader_id': '6780869',
},
}, {
# From http://sportscanada.tv/canadagames/index.php/week2/figure-skating/444
# Title and uploader available only from params JSON
'url': 'http://www.ustream.tv/embed/recorded/59307601?ub=ff0000&lc=ff0000&oc=ffffff&uc=ffffff&v=3&wmode=direct',
'md5': '5a2abf40babeac9812ed20ae12d34e10',
'info_dict': {
'id': '59307601',
'ext': 'flv',
'title': '-CG11- Canada Games Figure Skating',
'uploader': 'sportscanadatv',
},
'skip': 'This Pro Broadcaster has chosen to remove this video from the ustream.tv site.',
}, {
'url': 'http://www.ustream.tv/embed/10299409',
'info_dict': {
'id': '10299409',
},
'playlist_count': 3,
}, {
'url': 'http://www.ustream.tv/recorded/91343263',
'info_dict': {
'id': '91343263',
'ext': 'mp4',
'title': 'GitHub Universe - General Session - Day 1',
'upload_date': '20160914',
'description': 'GitHub Universe - General Session - Day 1',
'timestamp': 1473872730,
'uploader': 'wa0dnskeqkr',
'uploader_id': '38977840',
},
'params': {
'skip_download': True, # m3u8 download
},
}]
@staticmethod
def _extract_url(webpage):
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
if mobj is not None:
return mobj.group('url')
def _get_stream_info(self, url, video_id, app_id_ver, extra_note=None):
def num_to_hex(n):
return hex(n)[2:]
rnd = random.randrange
if not extra_note:
extra_note = ''
conn_info = self._download_json(
'http://r%d-1-%s-recorded-lp-live.ums.ustream.tv/1/ustream' % (rnd(1e8), video_id),
video_id, note='Downloading connection info' + extra_note,
query={
'type': 'viewer',
'appId': app_id_ver[0],
'appVersion': app_id_ver[1],
'rsid': '%s:%s' % (num_to_hex(rnd(1e8)), num_to_hex(rnd(1e8))),
'rpin': '_rpin.%d' % rnd(1e15),
'referrer': url,
'media': video_id,
'application': 'recorded',
})
host = conn_info[0]['args'][0]['host']
connection_id = conn_info[0]['args'][0]['connectionId']
return self._download_json(
'http://%s/1/ustream?connectionId=%s' % (host, connection_id),
video_id, note='Downloading stream info' + extra_note)
def _get_streams(self, url, video_id, app_id_ver):
# Sometimes the return dict does not have 'stream'
for trial_count in range(3):
stream_info = self._get_stream_info(
url, video_id, app_id_ver,
extra_note=' (try %d)' % (trial_count + 1) if trial_count > 0 else '')
if 'stream' in stream_info[0]['args'][0]:
return stream_info[0]['args'][0]['stream']
return []
def _parse_segmented_mp4(self, dash_stream_info):
def resolve_dash_template(template, idx, chunk_hash):
return template.replace('%', compat_str(idx), 1).replace('%', chunk_hash)
formats = []
for stream in dash_stream_info['streams']:
# Use only one provider to avoid too many formats
provider = dash_stream_info['providers'][0]
fragments = [{
'url': resolve_dash_template(
provider['url'] + stream['initUrl'], 0, dash_stream_info['hashes']['0'])
}]
for idx in range(dash_stream_info['videoLength'] // dash_stream_info['chunkTime']):
fragments.append({
'url': resolve_dash_template(
provider['url'] + stream['segmentUrl'], idx,
dash_stream_info['hashes'][compat_str(idx // 10 * 10)])
})
content_type = stream['contentType']
kind = content_type.split('/')[0]
f = {
'format_id': '-'.join(filter(None, [
'dash', kind, str_or_none(stream.get('bitrate'))])),
'protocol': 'http_dash_segments',
# TODO: generate a MPD doc for external players?
'url': encode_data_uri(b'<MPD/>', 'text/xml'),
'ext': mimetype2ext(content_type),
'height': stream.get('height'),
'width': stream.get('width'),
'fragments': fragments,
}
if kind == 'video':
f.update({
'vcodec': stream.get('codec'),
'acodec': 'none',
'vbr': stream.get('bitrate'),
})
else:
f.update({
'vcodec': 'none',
'acodec': stream.get('codec'),
'abr': stream.get('bitrate'),
})
formats.append(f)
return formats
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('id')
# some sites use this embed format (see: https://github.com/rg3/youtube-dl/issues/2990)
if m.group('type') == 'embed/recorded':
video_id = m.group('id')
desktop_url = 'http://www.ustream.tv/recorded/' + video_id
return self.url_result(desktop_url, 'Ustream')
if m.group('type') == 'embed':
video_id = m.group('id')
webpage = self._download_webpage(url, video_id)
content_video_ids = self._parse_json(self._search_regex(
r'ustream\.vars\.offAirContentVideoIds=([^;]+);', webpage,
'content video IDs'), video_id)
return self.playlist_result(
map(lambda u: self.url_result('http://www.ustream.tv/recorded/' + u, 'Ustream'), content_video_ids),
video_id)
params = self._download_json(
'https://api.ustream.tv/videos/%s.json' % video_id, video_id)
error = params.get('error')
if error:
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, error), expected=True)
video = params['video']
title = video['title']
filesize = float_or_none(video.get('file_size'))
formats = [{
'id': video_id,
'url': video_url,
'ext': format_id,
'filesize': filesize,
} for format_id, video_url in video['media_urls'].items() if video_url]
if not formats:
hls_streams = self._get_streams(url, video_id, app_id_ver=(11, 2))
if hls_streams:
# m3u8_native leads to intermittent ContentTooShortError
formats.extend(self._extract_m3u8_formats(
hls_streams[0]['url'], video_id, ext='mp4', m3u8_id='hls'))
'''
# DASH streams handling is incomplete as 'url' is missing
dash_streams = self._get_streams(url, video_id, app_id_ver=(3, 1))
if dash_streams:
formats.extend(self._parse_segmented_mp4(dash_streams))
'''
self._sort_formats(formats)
description = video.get('description')
timestamp = int_or_none(video.get('created_at'))
duration = float_or_none(video.get('length'))
view_count = int_or_none(video.get('views'))
uploader = video.get('owner', {}).get('username')
uploader_id = video.get('owner', {}).get('id')
thumbnails = [{
'id': thumbnail_id,
'url': thumbnail_url,
} for thumbnail_id, thumbnail_url in video.get('thumbnail', {}).items()]
return {
'id': video_id,
'title': title,
'description': description,
'thumbnails': thumbnails,
'timestamp': timestamp,
'duration': duration,
'view_count': view_count,
'uploader': uploader,
'uploader_id': uploader_id,
'formats': formats,
}
class UstreamChannelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ustream\.tv/channel/(?P<slug>.+)'
IE_NAME = 'ustream:channel'
_TEST = {
'url': 'http://www.ustream.tv/channel/channeljapan',
'info_dict': {
'id': '10874166',
},
'playlist_mincount': 17,
}
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
display_id = m.group('slug')
webpage = self._download_webpage(url, display_id)
channel_id = self._html_search_meta('ustream:channel_id', webpage)
BASE = 'http://www.ustream.tv'
next_url = '/ajax/socialstream/videos/%s/1.json' % channel_id
video_ids = []
while next_url:
reply = self._download_json(
compat_urlparse.urljoin(BASE, next_url), display_id,
note='Downloading video information (next: %d)' % (len(video_ids) + 1))
video_ids.extend(re.findall(r'data-content-id="(\d.*)"', reply['data']))
next_url = reply['nextUrl']
entries = [
self.url_result('http://www.ustream.tv/recorded/' + vid, 'Ustream')
for vid in video_ids]
return {
'_type': 'playlist',
'id': channel_id,
'display_id': display_id,
'entries': entries,
}
|
