Skip to content

A feature-rich command-line audio/video downloader

[ie/facebook:ads] Fix extractor (#15582)

Ștefan-Gabriel Muscaluf8b3fe33f684
diff --git a/yt_dlp/extractor/facebook.py b/yt_dlp/extractor/facebook.py
index 99f64272b2..2956516d90 100644
--- a/yt_dlp/extractor/facebook.py
+++ b/yt_dlp/extractor/facebook.py
@@ -4,6 +4,7 @@ import urllib.parse
from .common import InfoExtractor
from ..compat import compat_etree_fromstring
+from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
clean_html,
@@ -1017,6 +1018,7 @@ class FacebookAdsIE(InfoExtractor):
'upload_date': '20240812',
'like_count': int,
},
+ 'skip': 'Invalid URL',
}, {
'url': 'https://www.facebook.com/ads/library/?id=893637265423481',
'info_dict': {
@@ -1031,6 +1033,33 @@ class FacebookAdsIE(InfoExtractor):
},
'playlist_count': 3,
'skip': 'Invalid URL',
+ }, {
+ 'url': 'https://www.facebook.com/ads/library/?id=312304267031140',
+ 'info_dict': {
+ 'id': '312304267031140',
+ 'title': 'Casper Wave Hybrid Mattress',
+ 'uploader': 'Casper',
+ 'uploader_id': '224110981099062',
+ 'uploader_url': 'https://www.facebook.com/Casper/',
+ 'timestamp': 1766299837,
+ 'upload_date': '20251221',
+ 'like_count': int,
+ },
+ 'playlist_count': 2,
+ }, {
+ 'url': 'https://www.facebook.com/ads/library/?id=874812092000430',
+ 'info_dict': {
+ 'id': '874812092000430',
+ 'title': 'TikTok',
+ 'uploader': 'Case \u00e0 Chocs',
+ 'uploader_id': '112960472096793',
+ 'uploader_url': 'https://www.facebook.com/Caseachocs/',
+ 'timestamp': 1768498293,
+ 'upload_date': '20260115',
+ 'like_count': int,
+ 'description': 'md5:f02a255fcf7dce6ed40e9494cf4bc49a',
+ },
+ 'playlist_count': 3,
}, {
'url': 'https://es-la.facebook.com/ads/library/?id=901230958115569',
'only_matching': True,
@@ -1060,9 +1089,36 @@ class FacebookAdsIE(InfoExtractor):
})
return formats
+ def _download_fb_webpage_and_verify(self, url, video_id):
+ # See https://github.com/yt-dlp/yt-dlp/issues/15577
+
+ try:
+ return self._download_webpage(url, video_id)
+ except ExtractorError as e:
+ if (
+ not isinstance(e.cause, HTTPError)
+ or e.cause.status != 403
+ or e.cause.reason != 'Client challenge'
+ ):
+ raise
+ error_page = self._webpage_read_content(e.cause.response, url, video_id)
+
+ self.write_debug('Received a client challenge response')
+
+ challenge_path = self._search_regex(
+ r'fetch\s*\(\s*["\'](/__rd_verify[^"\']+)["\']',
+ error_page, 'challenge path')
+
+ # Successful response will set the necessary cookie
+ self._request_webpage(
+ urljoin(url, challenge_path), video_id, 'Requesting verification cookie',
+ 'Unable to get verification cookie', data=b'')
+
+ return self._download_webpage(url, video_id)
+
def _real_extract(self, url):
video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
+ webpage = self._download_fb_webpage_and_verify(url, video_id)
post_data = traverse_obj(
re.findall(r'data-sjs>({.*?ScheduledServerJS.*?})</script>', webpage), (..., {json.loads}))