diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-06-30 11:26:04 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-06-30 11:26:04 -0700 |
| commit | 0b0f747002e621621bb09d97826c807dd966d6c8 (patch) | |
| tree | aa7880ea48bcf41b0ee946dc21f65b4458e19a37 | |
| parent | 2f4b35f29f53b0e643c3e7cd74e63370758dc490 (diff) | |
| download | sandcrawler-0b0f747002e621621bb09d97826c807dd966d6c8.tar.gz sandcrawler-0b0f747002e621621bb09d97826c807dd966d6c8.zip | |
another bad PDF SHA-1
| -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 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 |