From 0b0f747002e621621bb09d97826c807dd966d6c8 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Tue, 30 Jun 2020 11:26:04 -0700 Subject: another bad PDF SHA-1 --- python/sandcrawler/pdfextract.py | 1 + 1 file changed, 1 insertion(+) (limited to 'python/sandcrawler') diff --git a/python/sandcrawler/pdfextract.py b/python/sandcrawler/pdfextract.py index c77a3f0..350c591 100644 --- a/python/sandcrawler/pdfextract.py +++ b/python/sandcrawler/pdfextract.py @@ -20,6 +20,7 @@ from .ia import WaybackClient, WaybackError, PetaboxError BAD_PDF_SHA1HEX = [ "373f84dfab4ed47047826e604e2918a9cd6a95b2", "88edcbab1cac2d70af5870422974afc253f4f0c6", + "8e4f03c29ae1fe7227140ab4b625f375f6c00d31", ] @dataclass -- cgit v1.2.3