diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-10-13 22:58:36 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-10-13 22:58:36 -0700 |
| commit | e15def6e10154d65ae8a7e49f1f693bb3c6f1462 (patch) | |
| tree | cbea371f9ce49943e67b7d785e098a27c6cd7402 | |
| parent | f5286affa62c0caf95ff4848626e85aff476737e (diff) | |
| download | sandcrawler-e15def6e10154d65ae8a7e49f1f693bb3c6f1462.tar.gz sandcrawler-e15def6e10154d65ae8a7e49f1f693bb3c6f1462.zip | |
another day, another bad PDF sha1
| -rw-r--r-- | python/sandcrawler/pdfextract.py | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/python/sandcrawler/pdfextract.py b/python/sandcrawler/pdfextract.py index 3affabc..1f59eb9 100644 --- a/python/sandcrawler/pdfextract.py +++ b/python/sandcrawler/pdfextract.py @@ -59,6 +59,7 @@ BAD_PDF_SHA1HEX = [ "88edcbab1cac2d70af5870422974afc253f4f0c6", "8e4f03c29ae1fe7227140ab4b625f375f6c00d31", "949dfb7d833da9576b2ccb9eb1ab5457469c53d3", + "9dbd05af3442e6f42d67868054751b76973f4171", "a2298c137b9c8c8975bad62eea9224edb95e6952", "a2671738755ab8b24775e95375dc72f1ca4e5fd6", "a9162b9aef5e5da0897275fede1a6cff8cc93dfc", |