[ie/facebook] Detect age-restricted content (#18055)

Closes #17643
Authored by: ruben1PvP, bashonly

Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>
This commit is contained in:
ruben1PvP
2026-11-16 23:17:46 +00:00
committed by GitHub
co-authored by bashonly
parent 5aecc65a2a
commit 8f9e23a47e
+27 -10
View File
@@ -30,7 +30,14 @@ from ..utils import (
)
class FacebookIE(InfoExtractor):
class FacebookBaseIE(InfoExtractor):
@staticmethod
def _parse_all_data_sjs(webpage):
return traverse_obj(
re.findall(r'data-sjs>({.*?ScheduledServerJS.*?})</script>', webpage), (..., {json.loads}))
class FacebookIE(FacebookBaseIE):
_VALID_URL = r'''(?x)
(?:
https?://
@@ -84,7 +91,7 @@ class FacebookIE(InfoExtractor):
'view_count': int,
'concurrent_view_count': 0,
},
'expected_warnings': ['Cannot parse data'],
'skip': 'Video gone',
}, {
'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',
'md5': '6a40d33c0eccbb1af76cf0485a052659',
@@ -114,7 +121,6 @@ class FacebookIE(InfoExtractor):
'concurrent_view_count': int,
'view_count': int,
},
'expected_warnings': ['Cannot parse data'],
}, {
'note': 'Video with DASH manifest',
'url': 'https://www.facebook.com/video.php?v=957955867617029',
@@ -245,6 +251,7 @@ class FacebookIE(InfoExtractor):
},
'skip': 'Invalid URL',
}, {
# FIXME: falls back to tahoe API request and fails with 404 error
# data.node.comet_sections.content.story.attachments[].styles.attachment.media
'url': 'https://www.facebook.com/attn/posts/pfbid0j1Czf2gGDVqeQ8KiMLFm3pWN8GxsQmeRrVhimWDzMuKQoR8r4b1knNsejELmUgyhl',
'info_dict': {
@@ -261,6 +268,7 @@ class FacebookIE(InfoExtractor):
'timestamp': 1701975646,
},
}, {
# FIXME: falls back to tahoe API request and fails with 404 error
# data.node.comet_sections.content.story.attachments[].styles.attachment.media
'url': 'https://www.facebook.com/permalink.php?story_fbid=pfbid0fqQuVEQyXRa9Dp4RcaTR14KHU3uULHV1EK7eckNXSH63JMuoALsAvVCJ97zAGitil&id=100068861234290',
'info_dict': {
@@ -343,7 +351,6 @@ class FacebookIE(InfoExtractor):
'description': '',
'upload_date': '20190204',
},
'expected_warnings': ['Cannot parse data'],
}, {
# data.video.story.attachments[].media
'url': 'https://www.facebook.com/watch/?v=647537299265662',
@@ -409,6 +416,10 @@ class FacebookIE(InfoExtractor):
}, {
'url': 'https://www.facebook.com/groups/1513990329015294/posts/d41d8cd9/2013209885760000/?app=fbl',
'only_matching': True,
}, {
# Age-restricted video
'url': 'https://www.facebook.com/watch/?v=1388064706077874',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
# <iframe> embed
@@ -470,8 +481,7 @@ class FacebookIE(InfoExtractor):
url.replace('://m.facebook.com/', '://www.facebook.com/'), video_id)
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_data = self._parse_all_data_sjs(webpage)
post = traverse_obj(post_data, (
..., 'require', ..., ..., ..., '__bbox', 'require', ..., ..., ..., '__bbox', 'result', 'data'), expected_type=dict) or []
media = traverse_obj(post, (..., 'attachments', ..., lambda k, v: (
@@ -825,6 +835,11 @@ class FacebookIE(InfoExtractor):
video_data = extract_from_jsmods_instances(tahoe_js_data)
if not video_data:
if get_first(self._parse_all_data_sjs(webpage), (
'require', ..., ..., ..., '__bbox', 'require', ..., ...,
..., 'initialRouteInfo', 'route', 'rootView', 'props', 'is_age_gated', {bool},
)):
self.raise_login_required('This video is age-restricted and requires authentication')
raise ExtractorError('Cannot parse data')
if len(video_data) > 1:
@@ -975,6 +990,10 @@ class FacebookReelIE(InfoExtractor):
'comment_count': int,
'repost_count': int,
},
}, {
# Age-restricted video
'url': 'https://www.facebook.com/reel/1388064706077874',
'only_matching': True,
}]
def _real_extract(self, url):
@@ -983,7 +1002,7 @@ class FacebookReelIE(InfoExtractor):
f'https://m.facebook.com/watch/?v={video_id}&_rdr', FacebookIE, video_id)
class FacebookAdsIE(InfoExtractor):
class FacebookAdsIE(FacebookBaseIE):
_VALID_URL = r'https?://(?:[\w-]+\.)?facebook\.com/ads/library/?\?(?:[^#]+&)?id=(?P<id>\d+)'
IE_NAME = 'facebook:ads'
_TESTS = [{
@@ -1128,9 +1147,7 @@ class FacebookAdsIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_fb_webpage_and_verify(url, video_id)
post_data = traverse_obj(
re.findall(r'data-sjs>({.*?ScheduledServerJS.*?})</script>', webpage), (..., {json.loads}))
post_data = self._parse_all_data_sjs(webpage)
data = get_first(post_data, (
'require', ..., ..., ..., '__bbox', 'require', ..., ..., ..., (
('__bbox', 'result', 'data', 'ad_library_main', 'deeplink_ad_archive_result', 'deeplink_ad_archive'),