pi-hole/gravity-adv.sh
jacobsalmela b7573a533a Now blocks over 140,000 ad domains
In addition to the extra domains, there are numerous performance
improvements so the script runs faster.  There were also some
extraneous domains that were either blank or had some special
characters that needed to be removed.

Since the ad lists are not under my control, the end of the script will
now tell you how many domains will be blocked.  In case the sources it
pulls from ever update, you can run this script again and see the
difference.
2015-02-17 13:52:54 -06:00

40 lines
No EOL
2.8 KiB
Bash
Executable file

#!/bin/bash
# The Pi-hole now blocks over 140,000 ad domains
# Address to send ads to (the RPi)
piholeIP="127.0.0.1"
# Optionally, uncomment to automatically detect the address. Thanks Gregg
#piholeIP=$(ifconfig eth0 | awk '/inet addr/{print substr($2,6)}')
# Config file to hold URL rules
eventHorizion="/etc/dnsmasq.d/adList.conf"
echo "Getting yoyo ad list..." # Approximately 2452 domains at the time of writing
curl -s -d mimetype=plaintext -d hostformat=unixhosts http://pgl.yoyo.org/adservers/serverlist.php? | sort > /tmp/matter.txt
echo "Getting winhelp2002 ad list..." # 12985 domains
curl -s http://winhelp2002.mvps.org/hosts.txt | grep -v "#" | grep -v "127.0.0.1" | sed '/^$/d' | sed 's/\ /\\ /g' | awk '{print $2}' | sort >> /tmp/matter.txt
echo "Getting adaway ad list..." # 445 domains
curl -s https://adaway.org/hosts.txt | grep -v "#" | grep -v "::1" | sed '/^$/d' | sed 's/\ /\\ /g' | awk '{print $2}' | grep -v '^\\' | grep -v '\\$' | sort >> /tmp/matter.txt
echo "Getting hosts-file ad list..." # 28050 domains
curl -s http://hosts-file.net/.%5Cad_servers.txt | grep -v "#" | grep -v "::1" | sed '/^$/d' | sed 's/\ /\\ /g' | awk '{print $2}' | grep -v '^\\' | grep -v '\\$' | sort >> /tmp/matter.txt
echo "Getting malwaredomainlist ad list..." # 1352 domains
curl -s http://www.malwaredomainlist.com/hostslist/hosts.txt | grep -v "#" | sed '/^$/d' | sed 's/\ /\\ /g' | awk '{print $3}' | grep -v '^\\' | grep -v '\\$' | sort >> /tmp/matter.txt
echo "Getting adblock.gjtech ad list..." # 696 domains
curl -s http://adblock.gjtech.net/?format=unix-hosts | grep -v "#" | sed '/^$/d' | sed 's/\ /\\ /g' | awk '{print $2}' | grep -v '^\\' | grep -v '\\$' | sort >> /tmp/matter.txt
echo "Getting someone who cares ad list..." # 10600
curl -s http://someonewhocares.org/hosts/hosts | grep -v "#" | sed '/^$/d' | sed 's/\ /\\ /g' | grep -v '^\\' | grep -v '\\$' | awk '{print $2}' | grep -v '^\\' | grep -v '\\$' | sort >> /tmp/matter.txt
echo "Getting Mother of All Ad Blocks list..." # 102168 domains!! Thanks Kacy
curl -A 'Mozilla/5.0 (X11; Linux x86_64; rv:30.0) Gecko/20100101 Firefox/30.0' -e http://forum.xda-developers.com/ http://adblock.mahakala.is/ | grep -v "#" | awk '{print $2}' | sort >> /tmp/matter.txt
# Sort the aggregated results and remove any duplicates
echo "Removing duplicates and formatting to address=/<ad domain>/"$piholeIP
cat /tmp/matter.txt | sort | uniq | sed '/^$/d' | awk -v "IP=$piholeIP" '{sub(/\r$/,""); print "address=/"$0"/"IP}' > /tmp/andLight.txt
# Count how many domains were added so it can be displayed to the user
numberOfAdsBlocked=$(cat /tmp/andLight.txt | wc -l | sed 's/^[ \t]*//')
echo "$numberOfAdsBlocked ad domains added to the blacklist"
# Turn the file into a dnsmasq config file
mv /tmp/andLight.txt $eventHorizion
# Restart DNS
service dnsmasq restart