From 468a7b6f91c5b3b0a80e3c82c408b8e02ce71e13 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Fri, 15 Jul 2022 14:42:00 -0700 Subject: html: mangled JSON-in-URL pattern --- python/sandcrawler/html_metadata.py | 1 + 1 file changed, 1 insertion(+) (limited to 'python') diff --git a/python/sandcrawler/html_metadata.py b/python/sandcrawler/html_metadata.py index c64d4f3..114d9a1 100644 --- a/python/sandcrawler/html_metadata.py +++ b/python/sandcrawler/html_metadata.py @@ -653,6 +653,7 @@ FULLTEXT_URL_PATTERNS_SKIP: List[str] = [ "://onlinelibrary.wiley.com/doi/pdf/", "://doi.org/", "://dx.doi.org/", + "{'embed': '", ] FULLTEXT_URL_PREFIX_SKIP: List[str] = [ -- cgit v1.2.3