MarcoBuster/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-23 05:06:49 +01:00
Code Issues Projects Releases Wiki Activity

Merge 3302588c77 into f919729538

Browse Source
This commit is contained in:
ringus1 2024-11-18 15:33:37 +05:30 committed by GitHub
commit 69bda7aa72
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 38 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
yt_dlp/extractor/facebook.py
View File

@ -443,7 +443,9 @@ def _perform_login(self, username, password):
try:
login_results = self._download_webpage(request, None,
note='Logging in', errnote='unable to fetch login page')
if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
if 'Your Request Couldn' in login_results:
self.raise_login_required('Failed to login with credentials', method='cookies')
elif re.search(r'<form[^>]*name="login"[^<]*</form>', login_results):
error = self._html_search_regex(
r'(?s)<div[^>]+class=(["\']).*?login_error_box.*?\1[^>]*><div[^>]*>.*?</div><div[^>]*>(?P<error>.+?)</div>',
login_results, 'login error', default=None, group='error')
@ -476,13 +478,41 @@ def _perform_login(self, username, password):
return
def _extract_from_url(self, url, video_id):
cookies = self._get_cookies(url)
# user passed logged-in cookies or attempted to login
login_data = cookies.get('c_user') and cookies.get('xs')
logged_in = False
webpage = self._download_webpage(
url.replace('://m.facebook.com/', '://www.facebook.com/'), video_id)
sjs_data = [self._parse_json(j, video_id, fatal=False) for j in re.findall(
r'data-sjs>({.*?ScheduledServerJS.*?})</script>', webpage)]
if login_data:
logged_in = get_first(sjs_data, (
'require', ..., ..., ..., '__bbox', 'define',
lambda _, v: 'CurrentUserInitialData' in v, ..., 'ACCOUNT_ID'), default='0') != '0'
if logged_in and (info := get_first(sjs_data, ('require', ..., ..., ..., '__bbox', 'require', ..., ..., ...,
'__bbox', 'result', 'data', (('ufac_client', 'state',
(('set_contact_point_state_renderer', 'title'),
('intro_state_renderer', 'header_title'))),
('epsilon_checkpoint', 'screen', 'title'))))):
if any(content in info for content in ['days left to appeal', 'suspended your account']):
raise ExtractorError('Your account is suspended', expected=True)
if 'Enter mobile number' == info:
raise ExtractorError('Facebook is requiring mobile number confirmation', expected=True)
if 'your account has been locked' in info:
raise ExtractorError('Your account has been locked', expected=True)
if props := get_first(sjs_data, (
'require', ..., ..., ..., '__bbox', 'require', ..., ..., ..., 'rootView',
lambda _, v: v['title'].startswith('This content isn\'t available'))):
raise ExtractorError(
f'Content unavailable. Facebook said: {props.get("body") or props["title"]}', expected=True)
def extract_metadata(webpage):
post_data = [self._parse_json(j, video_id, fatal=False) for j in re.findall(
r'data-sjs>({.*?ScheduledServerJS.*?})</script>', webpage)]
post = traverse_obj(post_data, (
post = traverse_obj(sjs_data, (
..., 'require', ..., ..., ..., '__bbox', 'require', ..., ..., ..., '__bbox', 'result', 'data'), expected_type=dict) or []
media = traverse_obj(post, (..., 'attachments', ..., lambda k, v: (
k == 'media' and str(v['id']) == video_id and v['__typename'] == 'Video')), expected_type=dict)
@ -835,6 +865,10 @@ def parse_attachment(attachment, key='media'):
video_data = extract_from_jsmods_instances(tahoe_js_data)
if not video_data:
if not login_data:
raise ExtractorError('Cannot parse data. Try logging in.', expected=True)
if not logged_in:
raise ExtractorError('Failed to login with provided data.', expected=True)
raise ExtractorError('Cannot parse data')
if len(video_data) > 1: