Created
October 6, 2024 07:52
-
-
Save miglen/fb178236835745c5772426f946dd28e4 to your computer and use it in GitHub Desktop.
Phishing feeds collector
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
#!/bin/bash | |
folder_prefix="./feeds/" # $(date +%Y/%m/%d) | |
mkdir -p ${folder_prefix} | |
rm -f ${folder_prefix}/*.txt | |
curl -L -s https://phishing.army/download/phishing_army_blocklist_extended.txt -o ${folder_prefix}/phishing_army_domains.txt | |
curl -L -s https://hole.cert.pl/domains/domains.csv | cut -f 2 > ${folder_prefix}/cert_pl_domains.txt | |
curl -L -s https://urlabuse.com/public/data/phishing_url.txt -o ${folder_prefix}/urlabuse_urls.txt | |
curl -L -s https://threatview.io/Downloads/DOMAIN-High-Confidence-Feed.txt -o ${folder_prefix}/threatview_domains.txt | |
curl -L -s https://openphish.com/feed.txt -o ${folder_prefix}/openphish_urls.txt | |
curl -L -s "https://urlscan.io/api/v1/search/?q=task.tags:\"@phish_report\"&size=10000" | jq -r '.results[].task.url' > ${folder_prefix}/urlscan_urls.txt | |
curl -L -s https://data.phishtank.com/data/online-valid.json.gz | gunzip | jq -r '.[].url' > phishtank_urls.txt | |
curl -L -s https://raw.githubusercontent.com/mitchellkrogza/Phishing.Database/refs/heads/master/phishing-domains-ACTIVE.txt -o ${folder_prefix}/phishing_database_domains.txt | |
curl -L -s https://github.com/mitchellkrogza/Phishing.Database/raw/refs/heads/master/phishing-links-ACTIVE.txt -o ${folder_prefix}/phishing_database_urls.txt | |
curl -L -s https://phishstats.info/phish_score.csv | grep http | cut -d"," -f 3 | tr -d '"' > ${folder_prefix}/phishing_score_urls.txt | |
cd ${folder_prefix} | |
cat ./*domains.txt | egrep -o '([a-zA-Z0-9-]+\.)+[a-zA-Z]{2,}' | egrep -v '^[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+' | sed 's/^www\.//'| sort | uniq | > ./all_domains.txt | |
cat ./*urls.txt | egrep -i ^http| sed 's/\/\/www\./\/\//' | sort | uniq | egrep -v "^https://docs.google.com/" | > ./all_urls.txt | |
echo -ne "" | |
wc -l ./all*.txt | |
echo -ne top 10 domains from the urls | |
awk -F/ '{print $3}' ./all_*.txt | egrep -v '^[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+' | sort | uniq -c | sort -nr | head -10 | |
echo -ne top 10 primary domains | |
awk -F/ '{print $3}' ./all_urls.txt | egrep -v '^[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+' | awk -F. '{n=NF-1; print $(n) "." $(n+1)}' | sort | uniq -c | sort -nr | head -10 | |
echo -ne top 10 non-common domains | |
awk -F/ '{print $3}' ./all_urls.txt | egrep -v '^[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+' | awk -F. '{n=NF-1; print $(n) "." $(n+1)}' | egrep -v '\.(com|net|org|gov|edu|mil|io)$' | sort | uniq -c | sort -nr | head -10 | |
echo -ne top 10 TDLs | |
awk -F/ '{print $3}' ./all_*.txt | awk -F. '{print $NF}' | egrep -v '^(com|net|org|gov|edu|mil|io)$' | sort | uniq -c | sort -nr | head -10 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment