pi-hole/gravity.sh

191 lines
6.1 KiB
Bash
Raw Normal View History

2014-06-08 15:03:56 +00:00
#!/bin/bash
2015-05-19 18:31:37 +00:00
# http://pi-hole.net
# Compiles a list of ad-serving domains by downloading them from multiple sources
2014-06-08 15:03:56 +00:00
# This script should only be run after you have a static IP address set on the Pi
piholeIP=$(hostname -I)
2015-05-19 18:31:37 +00:00
# Ad-list sources--one per line in single quotes
sources=('https://adaway.org/hosts.txt'
'http://adblock.gjtech.net/?format=unix-hosts'
'http://adblock.mahakala.is/'
'http://hosts-file.net/.%5Cad_servers.txt'
'http://www.malwaredomainlist.com/hostslist/hosts.txt'
'http://pgl.yoyo.org/adservers/serverlist.php?'
'http://someonewhocares.org/hosts/hosts'
'http://winhelp2002.mvps.org/hosts.txt')
2014-06-08 15:03:56 +00:00
2015-05-19 18:31:37 +00:00
# Variables for various stages of downloading and formatting the list
adList=/etc/pihole/gravity.list
origin=/etc/pihole
2015-05-19 18:31:37 +00:00
piholeDir=/etc/pihole
if [[ -f $piholeDir/pihole.conf ]];then
. $piholeDir/pihole.conf
fi
2015-05-19 18:31:37 +00:00
justDomainsExtension=domains
matter=pihole.0.matter.txt
andLight=pihole.1.andLight.txt
supernova=pihole.2.supernova.txt
eventHorizon=pihole.3.eventHorizon.txt
accretionDisc=pihole.4.accretionDisc.txt
eyeOfTheNeedle=pihole.5.wormhole.txt
blacklist=$piholeDir/blacklist.txt
latentBlacklist=$origin/latentBlacklist.txt
whitelist=$piholeDir/whitelist.txt
latentWhitelist=$origin/latentWhitelist.txt
2014-06-08 15:03:56 +00:00
2015-05-19 18:31:37 +00:00
echo "** Neutrino emissions detected..."
2014-06-08 15:03:56 +00:00
2015-05-19 18:31:37 +00:00
# Create the pihole resource directory if it doesn't exist. Future files will be stored here
if [[ -d $piholeDir ]];then
2015-05-19 18:31:37 +00:00
:
else
echo "** Creating pihole directory..."
sudo mkdir $piholeDir
2015-05-19 18:31:37 +00:00
fi
# Add additional swap to prevent the "Error fork: unable to allocate memory" message: https://github.com/jacobsalmela/pi-hole/issues/37
function createSwapFile()
#########################
{
echo "** Creating more swap space to accomodate large solar masses..."
sudo dphys-swapfile swapoff
sudo curl -s -o /etc/dphys-swapfile https://raw.githubusercontent.com/jacobsalmela/pi-hole/master/advanced/dphys-swapfile
sudo dphys-swapfile setup
sudo dphys-swapfile swapon
}
if [[ -f /etc/dphys-swapfile ]];then
swapSize=$(cat /etc/dphys-swapfile | grep -m1 CONF_SWAPSIZE | cut -d'=' -f2)
if [[ $swapSize != 500 ]];then
mv /etc/dphys-swapfile /etc/dphys-swapfile.orig
echo "** Current swap size is $swapSize"
createSwapFile
else
:
fi
else
echo "** No swap file found. Creating one..."
createSwapFile
fi
2015-05-19 18:31:37 +00:00
# Loop through domain list. Download each one and remove commented lines (lines beginning with '# 'or '/') and blank lines
for ((i = 0; i < "${#sources[@]}"; i++))
do
url=${sources[$i]}
2015-05-19 18:31:37 +00:00
# Get just the domain from the URL
domain=$(echo "$url" | cut -d'/' -f3)
2015-05-19 18:31:37 +00:00
# Save the file as list.#.domain
saveLocation=$origin/list.$i.$domain.$justDomainsExtension
agent="Mozilla/10.0"
2015-05-19 18:31:37 +00:00
echo -n "Getting $domain list... "
# Use a case statement to download lists that need special cURL commands
# to complete properly and reset the user agent when required
case "$domain" in
"adblock.mahakala.is")
agent='Mozilla/5.0 (X11; Linux x86_64; rv:30.0) Gecko/20100101 Firefox/30.0'
cmd="curl -e http://forum.xda-developers.com/"
;;
2015-05-19 18:31:37 +00:00
"pgl.yoyo.org")
2015-09-12 04:08:43 +00:00
cmd="curl -d mimetype=plaintext -d hostformat=hosts"
;;
2015-05-19 18:31:37 +00:00
# Default is a simple curl request
*) cmd="curl"
2015-05-19 18:31:37 +00:00
esac
# tmp file, so we don't have to store the (long!) lists in RAM
tmpfile=`mktemp`
timeCheck=""
if [ -r $saveLocation ]; then
timeCheck="-z $saveLocation"
fi
CMD="$cmd -s $timeCheck -A '$agent' $url > $tmpfile"
echo "running [$CMD]"
$cmd -s $timeCheck -A "$agent" $url > $tmpfile
2015-05-19 18:31:37 +00:00
if [[ -s "$tmpfile" ]];then
2015-05-19 18:31:37 +00:00
# Remove comments and print only the domain name
# Most of the lists downloaded are already in hosts file format but the spacing/formating is not contigious
# This helps with that and makes it easier to read
# It also helps with debugging so each stage of the script can be researched more in depth
awk '($1 !~ /^#/) { if (NF>1) {print $2} else {print $1}}' $tmpfile | \
sed -nr -e 's/\.{2,}/./g' -e '/\./p' > $saveLocation
echo "Done."
2015-05-19 18:31:37 +00:00
else
echo "Skipping list because it does not have any new entries."
2015-05-19 18:31:37 +00:00
fi
# cleanup
rm -f $tmpfile
2015-05-19 18:31:37 +00:00
done
2014-06-08 15:03:56 +00:00
# Find all files with the .domains extension and compile them into one file and remove CRs
2015-05-19 18:31:37 +00:00
echo "** Aggregating list of domains..."
find $origin/ -type f -name "*.$justDomainsExtension" -exec cat {} \; | tr -d '\r' > $origin/$matter
2015-05-19 18:31:37 +00:00
# Append blacklist entries if they exist
if [[ -r $blacklist ]];then
numberOf=$(cat $blacklist | sed '/^\s*$/d' | wc -l)
echo "** Blacklisting $numberOf domain(s)..."
cat $blacklist >> $origin/$matter
2014-06-08 15:03:56 +00:00
fi
2015-05-19 18:31:37 +00:00
###########################
function gravity_advanced() {
numberOf=$(wc -l $origin/$andLight)
2015-05-19 18:31:37 +00:00
echo "** $numberOf domains being pulled in by gravity..."
2015-05-19 18:31:37 +00:00
# Remove carriage returns and preceding whitespace
# not really needed anymore?
cp $origin/$andLight $origin/$supernova
2015-05-19 18:31:37 +00:00
# Sort and remove duplicates
sort -u $origin/$supernova > $origin/$eventHorizon
numberOf=$(wc -l $origin/$eventHorizon)
2015-05-19 18:31:37 +00:00
echo "** $numberOf unique domains trapped in the event horizon."
# Format domain list as "192.168.x.x domain.com"
2015-05-19 18:31:37 +00:00
echo "** Formatting domains into a HOSTS file..."
awk '{print "'"$piholeIP"'" $1}' $origin/$eventHorizon > $origin/$accretionDisc
# Copy the file over as /etc/pihole/gravity.list so dnsmasq can use it
2015-05-19 18:31:37 +00:00
sudo cp $origin/$accretionDisc $adList
kill -HUP $(pidof dnsmasq)
}
2015-05-19 18:31:37 +00:00
# Whitelist (if applicable) then remove duplicates and format for dnsmasq
if [[ -r $whitelist ]];then
2015-05-19 18:31:37 +00:00
# Remove whitelist entries
numberOf=$(cat $whitelist | sed '/^\s*$/d' | wc -l)
plural=; [[ "$numberOf" != "1" ]] && plural=s
echo "** Whitelisting $numberOf domain${plural}..."
# Append a "$" to the end, prepend a "^" to the beginning, and
# replace "." with "\." of each line to turn each entry into a
# regexp so it can be parsed out with grep -x
awk -F '[# \t]' 'NF>0&&$1!="" {print "^"$1"$"}' $whitelist | sed 's/\./\\./g' > $latentWhitelist
2015-05-19 18:31:37 +00:00
else
rm $latentWhitelist
fi
# Prevent our sources from being pulled into the hole
plural=; [[ "${#sources[@]}" != "1" ]] && plural=s
echo "** Whitelisting ${#sources[@]} ad list source${plural}..."
for url in ${sources[@]}
do
echo "$url" | awk -F '/' '{print "^"$3"$"}' | sed 's/\./\\./g' >> $latentWhitelist
done
# Remove whitelist entries from deduped list
grep -vxf $latentWhitelist $origin/$matter > $origin/$andLight
gravity_advanced