etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-22 02:15:12 +00:00
Code Issues Projects Releases Wiki Activity

[ie/Zoom] gh-7784 fix password handling logic

Browse source
This commit is contained in:
Lucas Rademaker 2024-10-18 11:50:17 +07:00
parent 367ec929f4
commit 2eaf303b63
1 changed files with 37 additions and 17 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

54
yt_dlp/extractor/zoom.py
View file

@ -7,6 +7,7 @@
parse_resolution,
str_or_none,
traverse_obj,
update_url,
url_basename,
urlencode_postdata,
urljoin,
@ -62,39 +63,59 @@ def _get_page_data(self, webpage, video_id):
return self._search_json(
r'window\.__data__\s*=', webpage, 'data', video_id, transform_source=js_to_json)
def _get_real_webpage(self, url, base_url, video_id, url_type):
webpage = self._download_webpage(url, video_id, note=f'Downloading {url_type} webpage')
try:
form = self._form_hidden_inputs('password_form', webpage)
except ExtractorError:
return webpage
def _try_login(self, url, base_url, video_id, form):
# This will most likely only work for password-protected meetings
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 ''),
base_url + 'nws/recording/1.0/validate%s-passwd' % ('-meeting' if is_meeting else ''),
video_id, 'Validating passcode', 'Wrong passcode', data=urlencode_postdata({
'id': form[('meet' if is_meeting else 'file') + 'Id'],
'id': form[('meeting' if is_meeting else 'file') + '_id'],
'passwd': password,
'action': form.get('action'),
}))
if not validation.get('status'):
raise ExtractorError(validation['errorMessage'], expected=True)
return self._download_webpage(url, video_id, note=f'Re-downloading {url_type} webpage')
def _get_real_webpage(self, url, base_url, video_id, url_type):
webpage = self._download_webpage(url, video_id, note=f'Downloading {url_type} webpage')
data = self._get_page_data(webpage, video_id)
if data.get('componentName') != 'need-password': # not password protected
return webpage
# Password-protected:
self._try_login(url, base_url, video_id, form=data)
# Return the new HTML document
new_url = f"{base_url}rec/share/{data['meeting_id']}"
return self._download_webpage(new_url, video_id, note=f'Re-downloading {url_type} webpage')
def _get_share_redirect_url(self, url, base_url, video_id):
"""Converts a `/rec/share` url to the corresponding `/rec/play` url, performs login if necessary"""
webpage = self._get_real_webpage(url, base_url, video_id, 'share')
meeting_id = self._get_page_data(webpage, video_id)['meetingId']
redirect_dict = self._download_json(
f'{base_url}nws/recording/1.0/play/share-info/{meeting_id}',
video_id, note='Downloading share info JSON')['result']
redirect_path = redirect_dict.pop('redirectUrl')
url = update_url(urljoin(base_url, redirect_path), query_update=redirect_dict)
if redirect_dict.get('componentName') == 'need-password':
# First login, then return redirection URL
return self._get_share_redirect_url(url, base_url, video_id)
return url
def _real_extract(self, url):
base_url, url_type, video_id = self._match_valid_url(url).group('base_url', 'type', 'id')
if url_type == 'share':
webpage = self._get_real_webpage(url, base_url, video_id, 'share')
meeting_id = self._get_page_data(webpage, video_id)['meetingId']
redirect_path = self._download_json(
f'{base_url}nws/recording/1.0/play/share-info/{meeting_id}',
video_id, note='Downloading share info JSON')['result']['redirectUrl']
url = urljoin(base_url, redirect_path)
url = self._get_share_redirect_url(url, base_url, video_id)
webpage = self._get_real_webpage(url, base_url, video_id, 'play')
file_id = self._get_page_data(webpage, video_id)['fileId']
@ -107,7 +128,6 @@ def _real_extract(self, url):
'continueMode': 'true', # Makes this return value include interpreter audio information
},
note='Downloading play info JSON')['result']
subtitles = {}
# XXX: Would be more appropriate to parse chapters separate from subtitles
for _type in ('transcript', 'cc', 'chapter'):