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
|
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
str_or_none,
js_to_json,
parse_filesize,
urlencode_postdata,
urljoin,
)
class ZoomIE(InfoExtractor):
IE_NAME = 'zoom'
_VALID_URL = r'(?P<base_url>https?://(?:[^.]+\.)?zoom.us/)rec(?:ording)?/(?:play|share)/(?P<id>[A-Za-z0-9_.-]+)'
_TEST = {
'url': 'https://economist.zoom.us/rec/play/dUk_CNBETmZ5VA2BwEl-jjakPpJ3M1pcfVYAPRsoIbEByGsLjUZtaa4yCATQuOL3der8BlTwxQePl_j0.EImBkXzTIaPvdZO5',
'md5': 'ab445e8c911fddc4f9adc842c2c5d434',
'info_dict': {
'id': 'dUk_CNBETmZ5VA2BwEl-jjakPpJ3M1pcfVYAPRsoIbEByGsLjUZtaa4yCATQuOL3der8BlTwxQePl_j0.EImBkXzTIaPvdZO5',
'ext': 'mp4',
'title': 'China\'s "two sessions" and the new five-year plan',
},
'skip': 'Recording requires email authentication to access',
}
def _real_extract(self, url):
base_url, play_id = self._match_valid_url(url).groups()
webpage = self._download_webpage(url, play_id)
try:
form = self._form_hidden_inputs('password_form', webpage)
except ExtractorError:
form = None
if form:
password = self.get_param('videopassword')
if not password:
raise ExtractorError(
'This video is protected by a passcode, use the --video-password option', expected=True)
is_meeting = form.get('useWhichPasswd') == 'meeting'
validation = self._download_json(
base_url + 'rec/validate%s_passwd' % ('_meet' if is_meeting else ''),
play_id, 'Validating passcode', 'Wrong passcode', data=urlencode_postdata({
'id': form[('meet' if is_meeting else 'file') + 'Id'],
'passwd': password,
'action': form.get('action'),
}))
if not validation.get('status'):
raise ExtractorError(validation['errorMessage'], expected=True)
webpage = self._download_webpage(url, play_id)
data = self._parse_json(self._search_regex(
r'(?s)window\.__data__\s*=\s*({.+?});',
webpage, 'data'), play_id, js_to_json)
subtitles = {}
for _type in ('transcript', 'cc', 'chapter'):
if data.get('%sUrl' % _type):
subtitles[_type] = [{
'url': urljoin(base_url, data['%sUrl' % _type]),
'ext': 'vtt',
}]
formats = []
if data.get('viewMp4Url'):
formats.append({
'format_note': 'Camera stream',
'url': str_or_none(data.get('viewMp4Url')),
'width': int_or_none(data.get('viewResolvtionsWidth')),
'height': int_or_none(data.get('viewResolvtionsHeight')),
'format_id': str_or_none(data.get('recordingId')),
'ext': 'mp4',
'filesize_approx': parse_filesize(data.get('fileSize')),
'preference': 0
})
if data.get('shareMp4Url'):
formats.append({
'format_note': 'Screen share stream',
'url': str_or_none(data.get('shareMp4Url')),
'width': int_or_none(data.get('shareResolvtionsWidth')),
'height': int_or_none(data.get('shareResolvtionsHeight')),
'format_id': str_or_none(data.get('shareVideoId')),
'ext': 'mp4',
'preference': -1
})
return {
'id': play_id,
'title': data.get('topic'),
'subtitles': subtitles,
'formats': formats,
'http_headers': {
'Referer': base_url,
},
}
|
