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
|
import re
import urllib.parse
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
js_to_json,
parse_duration,
parse_iso8601,
)
class ViideaIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://(?:www\.)?(?:
videolectures\.net|
flexilearn\.viidea\.net|
presentations\.ocwconsortium\.org|
video\.travel-zoom\.si|
video\.pomp-forum\.si|
tv\.nil\.si|
video\.hekovnik.com|
video\.szko\.si|
kpk\.viidea\.com|
inside\.viidea\.net|
video\.kiberpipa\.org|
bvvideo\.si|
kongres\.viidea\.net|
edemokracija\.viidea\.com
)(?:/lecture)?/(?P<id>[^/]+)(?:/video/(?P<part>\d+))?/*(?:[#?].*)?$'''
_TESTS = [{
'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/',
'info_dict': {
'id': '20171',
'display_id': 'promogram_igor_mekjavic_eng',
'ext': 'mp4',
'title': 'Automatics, robotics and biocybernetics',
'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
'thumbnail': r're:http://.*\.jpg',
'timestamp': 1372349289,
'upload_date': '20130627',
'duration': 565,
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
# video with invalid direct format links (HTTP 403)
'url': 'http://videolectures.net/russir2010_filippova_nlp/',
'info_dict': {
'id': '14891',
'display_id': 'russir2010_filippova_nlp',
'ext': 'flv',
'title': 'NLP at Google',
'description': 'md5:fc7a6d9bf0302d7cc0e53f7ca23747b3',
'thumbnail': r're:http://.*\.jpg',
'timestamp': 1284375600,
'upload_date': '20100913',
'duration': 5352,
},
'params': {
# rtmp download
'skip_download': True,
},
}, {
# event playlist
'url': 'http://videolectures.net/deeplearning2015_montreal/',
'info_dict': {
'id': '23181',
'title': 'Deep Learning Summer School, Montreal 2015',
'description': 'md5:0533a85e4bd918df52a01f0e1ebe87b7',
'thumbnail': r're:http://.*\.jpg',
'timestamp': 1438560000,
},
'playlist_count': 30,
}, {
# multi part lecture
'url': 'http://videolectures.net/mlss09uk_bishop_ibi/',
'info_dict': {
'id': '9737',
'display_id': 'mlss09uk_bishop_ibi',
'title': 'Introduction To Bayesian Inference',
'thumbnail': r're:http://.*\.jpg',
'timestamp': 1251622800,
},
'playlist': [{
'info_dict': {
'id': '9737_part1',
'display_id': 'mlss09uk_bishop_ibi_part1',
'ext': 'wmv',
'title': 'Introduction To Bayesian Inference (Part 1)',
'thumbnail': r're:http://.*\.jpg',
'duration': 4622,
'timestamp': 1251622800,
'upload_date': '20090830',
},
}, {
'info_dict': {
'id': '9737_part2',
'display_id': 'mlss09uk_bishop_ibi_part2',
'ext': 'wmv',
'title': 'Introduction To Bayesian Inference (Part 2)',
'thumbnail': r're:http://.*\.jpg',
'duration': 5641,
'timestamp': 1251622800,
'upload_date': '20090830',
},
}],
'playlist_count': 2,
}]
def _real_extract(self, url):
lecture_slug, explicit_part_id = self._match_valid_url(url).groups()
webpage = self._download_webpage(url, lecture_slug)
cfg = self._parse_json(self._search_regex(
[r'cfg\s*:\s*({.+?})\s*,\s*[\da-zA-Z_]+\s*:\s*\(?\s*function',
r'cfg\s*:\s*({[^}]+})'],
webpage, 'cfg'), lecture_slug, js_to_json)
lecture_id = str(cfg['obj_id'])
base_url = self._proto_relative_url(cfg['livepipe'], 'http:')
try:
lecture_data = self._download_json(
f'{base_url}/site/api/lecture/{lecture_id}?format=json',
lecture_id)['lecture'][0]
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
msg = self._parse_json(
e.cause.response.read().decode('utf-8'), lecture_id)
raise ExtractorError(msg['detail'], expected=True)
raise
lecture_info = {
'id': lecture_id,
'display_id': lecture_slug,
'title': lecture_data['title'],
'timestamp': parse_iso8601(lecture_data.get('time')),
'description': lecture_data.get('description_wiki'),
'thumbnail': lecture_data.get('thumb'),
}
playlist_entries = []
lecture_type = lecture_data.get('type')
parts = [str(video) for video in cfg.get('videos', [])]
if parts:
multipart = len(parts) > 1
def extract_part(part_id):
smil_url = f'{base_url}/{lecture_slug}/video/{part_id}/smil.xml'
smil = self._download_smil(smil_url, lecture_id)
info = self._parse_smil(smil, smil_url, lecture_id)
info['id'] = lecture_id if not multipart else f'{lecture_id}_part{part_id}'
info['display_id'] = lecture_slug if not multipart else f'{lecture_slug}_part{part_id}'
if multipart:
info['title'] += f' (Part {part_id})'
switch = smil.find('.//switch')
if switch is not None:
info['duration'] = parse_duration(switch.attrib.get('dur'))
item_info = lecture_info.copy()
item_info.update(info)
return item_info
if explicit_part_id or not multipart:
result = extract_part(explicit_part_id or parts[0])
else:
result = {
'_type': 'multi_video',
'entries': [extract_part(part) for part in parts],
}
result.update(lecture_info)
# Immediately return explicitly requested part or non event item
if explicit_part_id or lecture_type != 'evt':
return result
playlist_entries.append(result)
# It's probably a playlist
if not parts or lecture_type == 'evt':
playlist_webpage = self._download_webpage(
f'{base_url}/site/ajax/drilldown/?id={lecture_id}', lecture_id)
entries = [
self.url_result(urllib.parse.urljoin(url, video_url), 'Viidea')
for _, video_url in re.findall(
r'<a[^>]+href=(["\'])(.+?)\1[^>]+id=["\']lec=\d+', playlist_webpage)]
playlist_entries.extend(entries)
playlist = self.playlist_result(playlist_entries, lecture_id)
playlist.update(lecture_info)
return playlist
|
