Extract PII from files
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Visa | |
cat *.txt | grep -E -o "4[0-9]{3}[ -]?[0-9]{4}[ -]?[0-9]{4}[ -]?[0-9]{4}" > visa.txt | |
# MasterCard | |
cat *.txt | grep -E -o "5[0-9]{3}[ -]?[0-9]{4}[ -]?[0-9]{4}[ -]?[0-9]{4}" > mastercard.txt | |
# American Express | |
cat *.txt | grep -E -o "3[47][0-9]{13}" > american-express.txt | |
# Diners Club | |
cat *.txt | grep -E -o "3(?:0[0-5]|[68][0-9])[0-9]{11}" > diners.txt | |
# Discover | |
cat *.txt | grep -E -o "6011[ -]?[0-9]{4}[ -]?[0-9]{4}[ -]?[0-9]{4}" > discover.txt | |
# JCB | |
cat *.txt | grep -E -o "(?:2131|1800|35d{3})d{11}" > jcb.txt | |
# AMEX | |
cat *.txt | grep -E -o "3[47][0-9]{2}[ -]?[0-9]{6}[ -]?[0-9]{5}" > amex.txt | |
# Extract Social Security Number (SSN) | |
cat *.txt | grep -E -o "[0-9]{3}[ -]?[0-9]{2}[ -]?[0-9]{4}" > ssn.txt | |
# Extract Indiana Driver License Number | |
cat *.txt | grep -E -o "[0-9]{4}[ -]?[0-9]{2}[ -]?[0-9]{4}" > indiana-dln.txt | |
# Extract US Passport Cards | |
cat *.txt | grep -E -o "C0[0-9]{7}" > us-pass-card.txt | |
# Extract US Passport Number | |
cat *.txt | grep -E -o "[23][0-9]{8}" > us-pass-num.txt | |
# Extract US Phone Numberss | |
cat *.txt | grep -Po 'd{3}[s-_]?d{3}[s-_]?d{4}' > us-phones.txt | |
# Extract ISBN Numbers | |
cat *.txt | egrep -a -o "ISBN(?:-1[03])?:? (?=[0-9X]{10}$|(?=(?:[0-9]+[- ]){3})[- 0-9X]{13}$|97[89][0-9]{10}$|(?=(?:[0-9]+[- ]){4})[- 0-9]{17}$)(?:97[89][- ]?)?[0-9]{1,5}[- ]?[0-9]+[- ]?[0-9]+[- ]?[0-9X]" > isbn.txt |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment