diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2022-07-13 13:23:57 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2022-07-13 13:23:57 -0700 |
| commit | c32b13949a06e9e834c1fac40e3609cb8eeb9f31 (patch) | |
| tree | 08b2c723af626bac3cfe147f6cad180a445e21e4 | |
| parent | 0202f325acd6436bf4753e62fd8803f29f4bd027 (diff) | |
| download | sandcrawler-c32b13949a06e9e834c1fac40e3609cb8eeb9f31.tar.gz sandcrawler-c32b13949a06e9e834c1fac40e3609cb8eeb9f31.zip | |
yet another bad PDF
| -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 2e13278..11c54e9 100644 --- a/python/sandcrawler/pdfextract.py +++ b/python/sandcrawler/pdfextract.py @@ -99,6 +99,7 @@ BAD_PDF_SHA1HEX: List[str] = [ "98b02eb70066c182c705ef4d14d8b723ad7f1fab", "993ca31f6974f8387bb18dd7d38987d290da8781", "9dbd05af3442e6f42d67868054751b76973f4171", + "a1cc781c694a48e018f4de110b58f561aa212051", "a2298c137b9c8c8975bad62eea9224edb95e6952", "a2671738755ab8b24775e95375dc72f1ca4e5fd6", "a26f299fb97c646effeebd4c5e2968786bd0f781", |