aboutsummaryrefslogtreecommitdiffstats
path: root/python/sandcrawler/pdfextract.py
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2020-08-06 13:47:24 -0700
committerBryan Newbold <bnewbold@archive.org>2020-08-06 13:47:24 -0700
commit76d2d00e1cec59ad37ed11ec7f47aab8f745511a (patch)
tree05fe1972a3b2618378c89316959ce7f827c97f4c /python/sandcrawler/pdfextract.py
parent5aa5683cabcf773d8eabc962afc79b1f4cc511fb (diff)
downloadsandcrawler-76d2d00e1cec59ad37ed11ec7f47aab8f745511a.tar.gz
sandcrawler-76d2d00e1cec59ad37ed11ec7f47aab8f745511a.zip
and more bad sha1
Diffstat (limited to 'python/sandcrawler/pdfextract.py')
-rw-r--r--python/sandcrawler/pdfextract.py3
1 files changed, 3 insertions, 0 deletions
diff --git a/python/sandcrawler/pdfextract.py b/python/sandcrawler/pdfextract.py
index a6be786..efed479 100644
--- a/python/sandcrawler/pdfextract.py
+++ b/python/sandcrawler/pdfextract.py
@@ -23,14 +23,17 @@ BAD_PDF_SHA1HEX = [
"0641822e68c5a07538b967489fd19a1d5dc371a5",
"09cba9b00494d12759c50cb914f1fb7c9746f5d1",
"09db7c9f2efb496c974427a61e84292ae27fc702",
+ "0d1c1567ea70e7b922ba88ccb868ffc7ca18e75c",
"10c6577a658bf6203557e2998b25ea9788f8adfe",
"182749ad1db1d5e999d07f010bdcfc2978dadc88",
"20589d9dd0a22c8c938ad97b7f4f12648aa119fa",
"25ab9e6169f041be05844a9b4edd6574918af769",
+ "281de904c4642a9be4f17b9774fc0a2bdc8a90e3",
"373f84dfab4ed47047826e604e2918a9cd6a95b2",
"445968ef735b228c08c3ff4238d99fc9f4824619",
"447fa6b5a90742a86429a932f6608d8e141688c0",
"4c81129904f7976a50825595a3497ea7b52579ef",
+ "646c4a654270606256397684204ff0f3d17be2e7",
"64d821d728f9a3dc944b4c03be00feea0b57e314",
"88edcbab1cac2d70af5870422974afc253f4f0c6",
"8e4f03c29ae1fe7227140ab4b625f375f6c00d31",