Merge remote-tracking branch 'refs/remotes/jacobsalmela/master'

pull/67/head^2
Mel 9 years ago
commit 25e7cefeb4

@ -60,4 +60,7 @@ A technical and detailed description can be found [here](http://jacobsalmela.com
## Other Operating Systems
This script will work for other UNIX-like systems with some slight **modifications**. As long as you can install `dnsmasq` and a Webserver, it should work OK. The automated install only works for a clean install of Raspiban right now since that is how the project originated.
### Examples Of The Pi-hole On Other Operating Systems
- [Sky-Hole](http://dlaa.me/blog/post/skyhole)
[![Donate](https://www.paypalobjects.com/en_US/i/btn/btn_donateCC_LG.gif "AdminLTE Presentation")](https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=3J2L3Z4DHW9UY "Donate")

@ -0,0 +1,3 @@
#!/bin/bash
# Flushes /var/log/pihole.log
truncate -s 0 /var/log/pihole.log

@ -1,13 +1,44 @@
#!/bin/bash
if [ $# = 0 ]; then
echo "Immediately whitelists one or more domains."
echo "Usage: whitelist.sh domain1 [domain2 ...]"
fi
combopattern=""
# For each argument passed to this script
for var in "$@"
do
echo "Whitelisting $var..."
# Use sed to search for the domain in /etc/pihole/gravity.list and remove it using an in-place edit
sed -i "/$var/d" /etc/pihole/gravity.list
# Also add the domain to the whitelist.txt in /etc/pihole
echo "$var" >> /etc/pihole/whitelist.txt
echo "Whitelisting $var..."
# Construct basic pattern to match domain name.
basicpattern=$(echo $var | awk -F '[# \t]' 'NF>0&&$1!="" {print ""$1""}' | sed 's/\./\\./g')
if [ "$basicpattern" != "" ]; then
# Add to the combination pattern that will be used below
if [ "$combopattern" != "" ]; then combopattern="$combopattern|"; fi
combopattern="$combopattern$basicpattern"
# Also add the domain to the whitelist but only if it's not already present
grep -E -q "^$basicpattern$" /etc/pihole/whitelist.txt \
|| echo "$var" >> /etc/pihole/whitelist.txt
fi
done
echo "** $# domain(s) whitelisted."
# Force dnsmasq to reload /etc/pihole/gravity.list
kill -HUP $(pidof dnsmasq)
# Now report on and remove matched domains
if [ "$combopattern" != "" ]; then
echo "Modifying hosts file..."
# Construct pattern to match entry in hosts file.
# This consists of one or more IP addresses followed by the domain name.
pattern=$(echo $combopattern | awk -F '[# \t]' '{printf "%s", "^(([0-9]+\.){3}[0-9]+ +)+("$1")$"}')
# Output what will be removed and then actually remove
sed -r -n 's/'"$pattern"'/ Removed: \3/p' /etc/pihole/gravity.list
sed -r -i '/'"$pattern"'/d' /etc/pihole/gravity.list
echo "** $# domain(s) whitelisted."
# Force dnsmasq to reload /etc/pihole/gravity.list
kill -HUP $(pidof dnsmasq)
fi

@ -1 +1,26 @@
@weekly sudo /usr/local/bin/gravity.sh
# /etc/crontab: system-wide crontab
# Unlike any other crontab you don't have to run the `crontab'
# command to install the new version when you edit this file
# and files in /etc/cron.d. These files also have username fields,
# that none of the other crontabs do.
SHELL=/bin/sh
PATH=/usr/local/sbin:/usr/local/bin:/sbin:/bin:/usr/sbin:/usr/bin
# m h dom mon dow user command
17 * * * * root cd / && run-parts --report /etc/cron.hourly
25 6 * * * root test -x /usr/sbin/anacron || ( cd / && run-parts --report /etc/cron.daily )
47 6 * * 7 root test -x /usr/sbin/anacron || ( cd / && run-parts --report /etc/cron.weekly )
52 6 1 * * root test -x /usr/sbin/anacron || ( cd / && run-parts --report /etc/cron.monthly )
# Pi-hole: Update the ad sources once a week on Sunday at 01:59
# Download any updates from the ad lists
59 1 * * 7 root /usr/local/bin/gravity.sh
# Pi-hole: Parse the log file before it is flushed and save the stats to a database
# This will be used for a historical view of your Pi-hole's performance
#50 11 * * * root /usr/local/bin/dailyLog.sh
# Pi-hole: Flush the log daily at 11:58 so it doesn't get out of control
# Stats will be viewable in the Web interface thanks to the cron job above
58 11 * * * root /usr/local/bin/piholeLogFlush.sh

@ -9,7 +9,7 @@ piholeIP=$(hostname -I)
sources=('https://adaway.org/hosts.txt'
'http://adblock.gjtech.net/?format=unix-hosts'
#'http://adblock.mahakala.is/'
'http://hosts-file.net/.%5Cad_servers.txt'
'http://hosts-file.net/ad_servers.txt'
'http://www.malwaredomainlist.com/hostslist/hosts.txt'
'http://pgl.yoyo.org/adservers/serverlist.php?'
'http://someonewhocares.org/hosts/hosts'
@ -27,7 +27,6 @@ eventHorizon=pihole.3.eventHorizon.txt
accretionDisc=pihole.4.accretionDisc.txt
eyeOfTheNeedle=pihole.5.wormhole.txt
blacklist=$piholeDir/blacklist.txt
latentBlacklist=$origin/latentBlacklist.txt
whitelist=$piholeDir/whitelist.txt
latentWhitelist=$origin/latentWhitelist.txt
@ -36,8 +35,6 @@ if [[ -r $piholeDir/pihole.conf ]];then
echo "** Local calibration requested..."
. $piholeDir/pihole.conf
fi
echo "** Neutrino emissions detected..."
# Create the pihole resource directory if it doesn't exist. Future files will be stored here
@ -48,35 +45,6 @@ else
sudo mkdir $piholeDir
fi
# Add additional swap to prevent the "Error fork: unable to allocate memory" message: https://github.com/jacobsalmela/pi-hole/issues/37
function createSwapFile()
#########################
{
echo "** Creating more swap space to accomodate large solar masses..."
sudo dphys-swapfile swapoff
sudo curl -s -o /etc/dphys-swapfile https://raw.githubusercontent.com/jacobsalmela/pi-hole/master/advanced/dphys-swapfile
sudo dphys-swapfile setup
sudo dphys-swapfile swapon
}
if [[ -n "$noSwap" ]]; then
# if $noSwap is set, don't do anything
:
elif [[ -f /etc/dphys-swapfile ]];then
swapSize=$(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 $swapSize"
createSwapFile
else
:
fi
else
echo "** No swap file found. Creating one..."
createSwapFile
fi
# Loop through domain list. Download each one and remove commented lines (lines beginning with '# 'or '/') and blank lines
for ((i = 0; i < "${#sources[@]}"; i++))
do
@ -87,27 +55,50 @@ do
# Save the file as list.#.domain
saveLocation=$origin/list.$i.$domain.$justDomainsExtension
echo -n "Getting $domain list... "
# Use a case statement to download lists that need special cURL commands to complete properly
agent="Mozilla/10.0"
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") data=$(curl -s -A 'Mozilla/5.0 (X11; Linux x86_64; rv:30.0) Gecko/20100101 Firefox/30.0' -e http://forum.xda-developers.com/ -z $saveLocation $url);;
"adblock.mahakala.is")
agent='Mozilla/5.0 (X11; Linux x86_64; rv:30.0) Gecko/20100101 Firefox/30.0'
cmd="curl -e http://forum.xda-developers.com/"
;;
"pgl.yoyo.org") data=$(curl -s -d mimetype=plaintext -d hostformat=hosts -z $saveLocation $url);;
"pgl.yoyo.org")
cmd="curl -d mimetype=plaintext -d hostformat=hosts"
;;
*) data=$(curl -s -z $saveLocation -A "Mozilla/10.0" $url);;
# Default is a simple curl request
*) cmd="curl"
esac
if [[ -n "$data" ]];then
# tmp file, so we don't have to store the (long!) lists in RAM
patternBuffer=$(mktemp)
heisenbergCompensator=""
if [[ -r $saveLocation ]]; then
heisenbergCompensator="-z $saveLocation"
fi
CMD="$cmd -s $heisenbergCompensator -A '$agent' $url > $patternBuffer"
$cmd -s $heisenbergCompensator -A "$agent" $url > $patternBuffer
if [[ -s "$patternBuffer" ]];then
# 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
echo "$data" | awk 'NF {if ($1 !~ "#") { if (NF>1) {print $2} else {print $1}}}' | \
sed -e 's/^[. \t]*//' -e 's/\.\.\+/./g' -e 's/[. \t]*$//' | grep "\." > $saveLocation
awk '($1 !~ /^#/) { if (NF>1) {print $2} else {print $1}}' $patternBuffer | \
sed -nr -e 's/\.{2,}/./g' -e '/\./p' > $saveLocation
echo "Done."
else
echo "Skipping list because it does not have any new entries."
echo "Skipping pattern because transporter logic detected no changes..."
fi
# Cleanup
rm -f $patternBuffer
done
# Find all files with the .domains extension and compile them into one file and remove CRs
@ -115,39 +106,43 @@ echo "** Aggregating list of domains..."
find $origin/ -type f -name "*.$justDomainsExtension" -exec cat {} \; | tr -d '\r' > $origin/$matter
# Append blacklist entries if they exist
if [[ -f $blacklist ]];then
if [[ -r $blacklist ]];then
numberOf=$(cat $blacklist | sed '/^\s*$/d' | wc -l)
echo "** Blacklisting $numberOf domain(s)..."
cat $blacklist >> $origin/$matter
else
:
fi
function gravity_advanced()
###########################
{
numberOf=$(cat $origin/$andLight | sed '/^\s*$/d' | wc -l)
function gravity_advanced() {
numberOf=$(wc -l < $origin/$andLight)
echo "** $numberOf domains being pulled in by gravity..."
# Remove carriage returns and preceding whitespace
cat $origin/$andLight | sed $'s/\r$//' | sed '/^\s*$/d' > $origin/$supernova
# not really needed anymore?
cp $origin/$andLight $origin/$supernova
# Sort and remove duplicates
cat $origin/$supernova | sort | uniq > $origin/$eventHorizon
numberOf=$(cat $origin/$eventHorizon | sed '/^\s*$/d' | wc -l)
sort -u $origin/$supernova > $origin/$eventHorizon
numberOf=$(wc -l < $origin/$eventHorizon)
echo "** $numberOf unique domains trapped in the event horizon."
# Format domain list as "192.168.x.x domain.com"
echo "** Formatting domains into a HOSTS file..."
cat $origin/$eventHorizon | awk '{sub(/\r$/,""); print "'"$piholeIP"'" $0}' > $origin/$accretionDisc
awk '{print "'"$piholeIP"'" $1}' $origin/$eventHorizon > $origin/$accretionDisc
# Copy the file over as /etc/pihole/gravity.list so dnsmasq can use it
sudo cp $origin/$accretionDisc $adList
kill -HUP $(pidof dnsmasq)
}
}
# Whitelist (if applicable) then remove duplicates and format for dnsmasq
if [[ -f $whitelist ]];then
if [[ -r $whitelist ]];then
# Remove whitelist entries
numberOf=$(cat $whitelist | sed '/^\s*$/d' | wc -l)
plural=; [[ "$numberOf" != "1" ]] && plural=s
echo "** Whitelisting $numberOf domain${plural}..."
# Append a "$" to the end, prepend a "^" to the beginning, and
# replace "." with "\." of each line to turn each entry into a
# regexp so it can be parsed out with grep -x
@ -164,6 +159,7 @@ do
echo "$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

Loading…
Cancel
Save