From b7573a533a520d29bfc363b72d7a4e796fec6733 Mon Sep 17 00:00:00 2001
From: jacobsalmela <jacob.salmela@gmail.com>
Date: Tue, 17 Feb 2015 13:52:54 -0600
Subject: [PATCH] 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.
---
 gravity-adv.sh | 49 ++++++++++++++++++++++++++-----------------------
 1 file changed, 26 insertions(+), 23 deletions(-)

diff --git a/gravity-adv.sh b/gravity-adv.sh
index 1c23453..b024ec3 100755
--- a/gravity-adv.sh
+++ b/gravity-adv.sh
@@ -1,36 +1,39 @@
 #!/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"
 
-# Download the original URL to a text file for easier parsing
-echo "Getting yoyo ad list..."
-curl -o /tmp/yoyo.txt -s http://pgl.yoyo.org/adservers/serverlist.php?hostformat=unixhosts&mimetype=plaintext
-sleep 10
-if [ -f /tmp/yoyo.txt ];then
-	cat /tmp/yoyo.txt | grep -v "<" | sed '/^$/d' | sed 's/\ /\\ /g' | sort > /tmp/matter.txt
-else
-	echo "Unable to get yoyo ad list"
-fi
-
-# Download and append other ad URLs from different sources
-echo "Getting winhelp2002 ad list..."
+echo "Getting yoyo ad list..." # Approximately 2452 domains at the time of writing
+curl -s -d mimetype=plaintext -d hostformat=unixhosts http://pgl.yoyo.org/adservers/serverlist.php? | sort > /tmp/matter.txt
+echo "Getting winhelp2002 ad list..." # 12985 domains
 curl -s http://winhelp2002.mvps.org/hosts.txt | grep -v "#" | grep -v "127.0.0.1" | sed '/^$/d' | sed 's/\ /\\ /g' | awk '{print $2}' | sort >> /tmp/matter.txt
-echo "Getting adaway ad list..."
-curl -s https://adaway.org/hosts.txt | grep -v "#" | grep -v "::1" | sed '/^$/d' | sed 's/\ /\\ /g' | awk '{print $2}' | sort >> /tmp/matter.txt
-echo "Getting hosts-file ad list..."
-curl -s http://hosts-file.net/.%5Cad_servers.txt | grep -v "#" | grep -v "::1" | sed '/^$/d' | sed 's/\ /\\ /g' | awk '{print $2}' | sort >> /tmp/matter.txt
-echo "Getting malwaredomainlist ad list..."
-curl -s http://www.malwaredomainlist.com/hostslist/hosts.txt | grep -v "#" | sed '/^$/d' | sed 's/\ /\\ /g' | awk '{print $2}' | sort >> /tmp/matter.txt
-echo "Getting adblock.gjtech ad list..."
-curl -s http://adblock.gjtech.net/?format=unix-hosts | grep -v "#" | sed '/^$/d' | sed 's/\ /\\ /g' | awk '{print $2}' | sort >> /tmp/matter.txt
-echo "Getting someone who cares ad list..."
-curl -s http://someonewhocares.org/hosts/hosts | grep -v "#" | sed '/^$/d' | sed 's/\ /\\ /g' | awk '{print $2}' >> /tmp/matter.txt
+echo "Getting adaway ad list..." # 445 domains
+curl -s https://adaway.org/hosts.txt | grep -v "#" | grep -v "::1" | sed '/^$/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>/"$piholeIP
+echo "Removing duplicates and formatting to address=/<ad domain>/"$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