From da25a961189b0e733843a07a08a78987f7a0db44 Mon Sep 17 00:00:00 2001 From: Hugo Date: Mon, 2 Oct 2023 11:38:36 +0200 Subject: [PATCH] sources and script cleaning for match pattern --- scripts/update.sh | 2 +- .../Malvertisement external forwarding.txt | 5 ++++- sources/Malware/Malvertisement redirection.txt | 16 ++++++++++++++++ ... software.txt => Software name squatting.txt} | 0 4 files changed, 21 insertions(+), 2 deletions(-) rename sources/Malware/{Name squatting software.txt => Software name squatting.txt} (100%) diff --git a/scripts/update.sh b/scripts/update.sh index f537f130..d380fc0e 100755 --- a/scripts/update.sh +++ b/scripts/update.sh @@ -6,7 +6,7 @@ # Cleanup sources: ## Normalizes URLs into domains: lowercases, remove leading spaces, protocol (`x://`) `www.` subdomains, everything after `/`, only one space before `#`. Keeps comments intact. -find ./sources -type f -name "*.txt" -exec sed -ri 'h; s/[^#]*//1; x; s/#.*//; s/.*/\L&/; s/^[[:space:]]*//i; s/^.*:\/\///i; s/^www\.//i; s/\/[^[:space:]]*//i; s/[[:space:]].*$/ /i; G; s/(.*)\n/\1/' {} \; +find ./sources -type f -name "*.txt" -exec sed -ri 'h; s/[^#]*//1; x; s/#.*//; s/.*/\L&/; s/^[[:space:]]*//i; s/^.*:\/\///i; s/^[.*]*//i; s/^www\.//i; s/\/[^[:space:]]*//i; s/[[:space:]].*$/ /i; G; s/(.*)\n/\1/' {} \; ## Remove duplicate domains from each source file (keeps repeated comments and empty lines for organization). find ./sources -type f -name "*.txt" -exec bash -c ' awk "(\$0 ~ /^[[:space:]]*#/ || NF == 0 || !seen[\$0]++)" "$0" > "$0_temp.txt"; diff --git a/sources/Malware/Malvertisement external forwarding.txt b/sources/Malware/Malvertisement external forwarding.txt index fcf1ff1f..ee94d85c 100644 --- a/sources/Malware/Malvertisement external forwarding.txt +++ b/sources/Malware/Malvertisement external forwarding.txt @@ -1,3 +1,6 @@ -# Uses the external forwarding service to redirect to a string of websites which trigger advertisement, badware and malware adblock filter lists. +# These URLs are called by the external forwarding service of a legitimate website +# The site is not fully compromised but used to redirect to a string of websites which trigger advertisement, badware and malware adblock filter lists. sudrtestt.ru +rxpromsoftware.ru +vestibularfce.com.br \ No newline at end of file diff --git a/sources/Malware/Malvertisement redirection.txt b/sources/Malware/Malvertisement redirection.txt index b1d019e3..f131e4cf 100644 --- a/sources/Malware/Malvertisement redirection.txt +++ b/sources/Malware/Malvertisement redirection.txt @@ -42,3 +42,19 @@ immobiliensky24.de adriamoevents.pl forum-wissenschaft-und-kunst.de agentur-hagemeier.de +https://lrdyi.gartenbau-u.de/ +*://*.trockenbau-trebsen.de/* +*://*.indexdummy3.de/* +*://*.elternverein-cvd-gs.de/* +*://*.webock.de/* +*://*.kintagencia.es/* +*://*.medcarelabjo.com/* +*://*.h4s-baustelle.de/* +*://*.makler-schiermeyer.de/* +*://*.ekw-sport-sozialmarketing.de/* +*://*.mkkinsektenschutz.de/* +*://*.meblegrzywacz.pl/* +*://*.bremen-kammerjaeger.de/* +*://*.contact-protect.de/* +*://*.phillee-sports.de/* +*://*.mennica-woda.pl/* \ No newline at end of file diff --git a/sources/Malware/Name squatting software.txt b/sources/Malware/Software name squatting.txt similarity index 100% rename from sources/Malware/Name squatting software.txt rename to sources/Malware/Software name squatting.txt