mirror of
https://github.com/pi-hole/pi-hole.git
synced 2024-12-01 02:23:21 +00:00
Output shorter deleting subdomains when possible
what's new: - sorting not necessary on every source, it's already executed at the end - comments are allowed in blacklist and in whitelist. Everything following the symbol '#' is considered comment, even if it's not at the beginning of the line - blank lines are allowed in blacklist and whitelist. - tested this with awk (mac), mawk (raspbian) and also with gawk. - bugfix ... - subdomains removed from output when domain already exists - output sorted in reverse order (right to left) - filepaths defined at the top of the code. - subdomains of items in whitelist/blacklist are whitelisted/blacklisted too
This commit is contained in:
pizzafritta
parent
15c84db022
commit
a8eda1c289
1 changed files with 54 additions and 38 deletions
|
|
@ -1,5 +1,5 @@
|
||||||
#!/bin/bash
|
#!/bin/bash
|
||||||
# The Pi-hole now blocks over 120,000 ad domains
|
# The Pi-hole now blocks over 90,000 ad domains
|
||||||
# Address to send ads to (the RPi)
|
# Address to send ads to (the RPi)
|
||||||
piholeIP="127.0.0.1"
|
piholeIP="127.0.0.1"
|
||||||
# Optionally, uncomment to automatically detect the local IP address.
|
# Optionally, uncomment to automatically detect the local IP address.
|
||||||
|
|
@ -7,60 +7,76 @@ piholeIP="127.0.0.1"
|
||||||
|
|
||||||
# Config file to hold URL rules
|
# Config file to hold URL rules
|
||||||
eventHorizion="/etc/dnsmasq.d/adList.conf"
|
eventHorizion="/etc/dnsmasq.d/adList.conf"
|
||||||
blacklist=/etc/pihole/blacklist.txt
|
piholeDir='/etc/pihole/'
|
||||||
whitelist=/etc/pihole/whitelist.txt
|
|
||||||
|
blacklist=$piholeDir'blacklist.txt'
|
||||||
|
whitelist=$piholeDir'whitelist.txt'
|
||||||
|
|
||||||
# Create the pihole resource directory if it doesn't exist. Future files will be stored here
|
# Create the pihole resource directory if it doesn't exist. Future files will be stored here
|
||||||
if [[ -d /etc/pihole/ ]];then
|
if [[ -d $piholeDir ]];then
|
||||||
:
|
:
|
||||||
else
|
else
|
||||||
echo "Forming pihole directory..."
|
echo "Forming pihole directory..."
|
||||||
sudo mkdir /etc/pihole
|
sudo mkdir $piholeDir
|
||||||
fi
|
fi
|
||||||
|
|
||||||
echo "Getting yoyo ad list..." # Approximately 2452 domains at the time of writing
|
tmpDir='/tmp/'
|
||||||
curl -s -d mimetype=plaintext -d hostformat=unixhosts http://pgl.yoyo.org/adservers/serverlist.php? | sort > /tmp/matter.txt
|
tmpAdList=$tmpDir'matter.pihole.txt'
|
||||||
echo "Getting winhelp2002 ad list..." # 12985 domains
|
tmpConf=$tmpDir'andLight.pihole.txt'
|
||||||
curl -s http://winhelp2002.mvps.org/hosts.txt | grep -v "#" | grep -v "127.0.0.1" | sed '/^$/d' | sed 's/\ /\\ /g' | awk '{print $2}' | sort >> /tmp/matter.txt
|
tmpWhiteList=$tmpDir'yang.pihole.txt'
|
||||||
echo "Getting adaway ad list..." # 445 domains
|
tmpBlackList=$tmpDir'yin.pihole.txt'
|
||||||
curl -s https://adaway.org/hosts.txt | grep -v "#" | grep -v "::1" | sed '/^$/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
|
|
||||||
|
|
||||||
# Add entries from the local blacklist file if it exists in /etc/pihole directory
|
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 > $tmpAdList
|
||||||
|
echo "Getting winhelp2002 ad list..." # 12985 domains
|
||||||
|
curl -s http://winhelp2002.mvps.org/hosts.txt | grep -v "#" | grep -v "127.0.0.1" | sed '/^$/d' | sed 's/\ /\\ /g' | awk '{print $2}' >> $tmpAdList
|
||||||
|
echo "Getting adaway ad list..." # 445 domains
|
||||||
|
curl -s https://adaway.org/hosts.txt | grep -v "#" | grep -v "::1" | sed '/^$/d' | sed 's/\ /\\ /g' | awk '{print $2}' | grep -v '^\\' | grep -v '\\$' >> $tmpAdList
|
||||||
|
echo "Getting hosts-file ad list..." # 28050 domains
|
||||||
|
curl -s http://hosts-file.net/.%5Cad_servers.txt | grep -v "#" | grep -v "::1" | sed '/^$/d' | sed 's/\ /\\ /g' | awk '{print $2}' | grep -v '^\\' | grep -v '\\$' >> $tmpAdList
|
||||||
|
echo "Getting malwaredomainlist ad list..." # 1352 domains
|
||||||
|
curl -s http://www.malwaredomainlist.com/hostslist/hosts.txt | grep -v "#" | sed '/^$/d' | sed 's/\ /\\ /g' | awk '{print $3}' | grep -v '^\\' | grep -v '\\$' >> $tmpAdList
|
||||||
|
echo "Getting adblock.gjtech ad list..." # 696 domains
|
||||||
|
curl -s http://adblock.gjtech.net/?format=unix-hosts | grep -v "#" | sed '/^$/d' | sed 's/\ /\\ /g' | awk '{print $2}' | grep -v '^\\' | grep -v '\\$' >> $tmpAdList
|
||||||
|
echo "Getting someone who cares ad list..." # 10600
|
||||||
|
curl -s http://someonewhocares.org/hosts/hosts | grep -v "#" | sed '/^$/d' | sed 's/\ /\\ /g' | grep -v '^\\' | grep -v '\\$' | awk '{print $2}' | grep -v '^\\' | grep -v '\\$' >> $tmpAdList
|
||||||
|
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}' >> $tmpAdList
|
||||||
|
|
||||||
|
# Add entries from the local blacklist file if it exists in $piholeDir directory
|
||||||
|
echo -n "" > $tmpBlackList
|
||||||
if [[ -f $blacklist ]];then
|
if [[ -f $blacklist ]];then
|
||||||
echo "Getting the local blacklist from /etc/pihole directory"
|
echo "Getting the local blacklist from $piholeDir directory"
|
||||||
cat $blacklist >> /tmp/matter.txt
|
awk -F'[# \t]' 'NF>0&&$1!="" {print $1}' $blacklist > $tmpBlackList
|
||||||
else
|
cat $tmpBlackList >> $tmpAdList
|
||||||
:
|
fi
|
||||||
|
|
||||||
|
# Clean-up entries from the local whitelist file if it exists in $piholeDir directory
|
||||||
|
echo -n "^$" > $tmpWhiteList
|
||||||
|
if [[ -f $whitelist ]];then
|
||||||
|
echo "Getting the local whitelist from $piholeDir directory"
|
||||||
|
awk -F'[# \t]' 'NF>0&&$1!="" {print $1"$"}' $whitelist > $tmpWhiteList
|
||||||
fi
|
fi
|
||||||
|
|
||||||
# Sort the aggregated results and remove any duplicates
|
# Sort the aggregated results and remove any duplicates
|
||||||
# Remove entries from the whitelist file if it exists at the root of the current user's home folder
|
# Remove entries from the whitelist file if it exists in $piholeDir folder
|
||||||
if [[ -f $whitelist ]];then
|
|
||||||
echo "Removing duplicates, whitelisting, and formatting the list of domains..."
|
echo "Removing duplicates, whitelisting, and formatting the list of domains..."
|
||||||
cat /tmp/matter.txt | sed $'s/\r$//' | sort | uniq | sed '/^$/d' | grep -v -x -f $whitelist | awk -v "IP=$piholeIP" '{sub(/\r$/,""); print "address=/"$0"/"IP}' > /tmp/andLight.txt
|
grep -vhE "^\s*(#|$)" $tmpAdList|
|
||||||
numberOfSitesWhitelisted=$(cat $whitelist | wc -l | sed 's/^[ \t]*//')
|
sed $'s/\r$//'|
|
||||||
echo "$numberOfSitesWhitelisted domains whitelisted."
|
awk -F. '{for (i=NF; i>1; --i) printf "%s.",$i;print $1}'|
|
||||||
else
|
sort -t'.' -k1,2| uniq | grep -vwf $tmpWhiteList |
|
||||||
echo "Removing duplicates and formatting the list of domains..."
|
awk -F. 'NR!=1&&substr($0,1,length(p))==p {next} {p=$0".";for (i=NF; i>1; --i) printf "%s.",$i;print $1}'|
|
||||||
cat /tmp/matter.txt | sed $'s/\r$//' | sort | uniq | sed '/^$/d' | awk -v "IP=$piholeIP" '{sub(/\r$/,""); print "address=/"$0"/"IP}' > /tmp/andLight.txt
|
awk -v "IP=$piholeIP" '{sub(/\r$/,""); print "address=/"$0"/"IP}' > $tmpConf
|
||||||
fi
|
numberOfSitesWhitelisted=$(cat $tmpWhiteList | wc -l | sed 's/^[ \t]*//')
|
||||||
|
numberOfSitesBlacklisted=$(cat $tmpBlackList | wc -l | sed 's/^[ \t]*//')
|
||||||
|
echo "$numberOfSitesWhitelisted domain(s) whitelisted, $numberOfSitesBlacklisted domain(s) blacklisted."
|
||||||
|
|
||||||
# Count how many domains/whitelists were added so it can be displayed to the user
|
# Count how many domains/whitelists were added so it can be displayed to the user
|
||||||
numberOfAdsBlocked=$(cat /tmp/andLight.txt | wc -l | sed 's/^[ \t]*//')
|
numberOfAdsBlocked=$(cat $tmpConf | wc -l | sed 's/^[ \t]*//')
|
||||||
echo "$numberOfAdsBlocked ad domains blocked."
|
echo "$numberOfAdsBlocked ad domains blocked."
|
||||||
|
|
||||||
# Turn the file into a dnsmasq config file
|
# Turn the file into a dnsmasq config file
|
||||||
sudo mv /tmp/andLight.txt $eventHorizion
|
sudo mv $tmpConf $eventHorizion
|
||||||
|
|
||||||
# Restart DNS
|
# Restart DNS
|
||||||
sudo service dnsmasq restart
|
sudo service dnsmasq restart
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue