testing awk

scripts/domains_to_dnsmasq.py

@@ -0,0 +1,9 @@
+# This script converts domains.txt into dnsmasq's blocking syntax.
+#	python domains_to_dnsmasq.py > dnsmasq.txt
+
+text_file = open("domains.txt", "r")
+lines = text_file.readlines()
+text_file.close()
+
+for line in lines:
+	print('address=/' + line.strip() + '/')

scripts/domains_to_hosts.py

@@ -7,4 +7,5 @@
 text_file.close()
 
 for line in lines:
-	print('0.0.0.0 ' + line.strip() + ' www.'+ line.strip())
+	print('0.0.0.0 ' + line.strip())
+	print('0.0.0.0 www.'+ line.strip())

scripts/domains_to_hosts_ipv6.py

@@ -7,4 +7,5 @@
 text_file.close()
 
 for line in lines:
-	print('::1 ' + line.strip() + ' www.'+ line.strip())
+	print('::1 ' + line.strip())
+	print('::1 www.'+ line.strip())

scripts/update.sh

@@ -9,7 +9,7 @@
 find ./sources -type f -name "*.txt" -exec sed -i 's/^www\.//i' {} \;
 ## Remove duplicates from each source file. (TO DO: keep "duplicate" line jumps and comments)
 find ./sources -type f -name "*.txt" -exec bash -c '
-    cat -n "$0" | sort -uk2 | sort -nk1 | cut -f2- > "$0_temp.txt";
+    awk "!NF || !seen[\$0]++" "$0" > "$0_temp.txt";
     mv "$0_temp.txt" "$0";
 ' {} \;
 
@@ -26,8 +26,9 @@ mv domains_temp.txt domains.txt
 # Generate blocklists:
 ## From the domain list.
 python scripts/domains_to_hosts.py > hosts.txt
+cp hosts.txt etc_hosts.txt # Previous filename for PiHole installations still subscribed to the old url.
 python scripts/domains_to_hosts_ipv6.py > hosts.txt.ipv6
-python scripts/domains_to_regex.py > regex.txt
+python scripts/domains_to_dnsmasq.py > dnsmasq.txt
 
 ## For browser extensions.
 python scripts/domains_to_netsane.py > netsane.txt

sources/Cults/Falun Gong.txt

@@ -17,6 +17,8 @@ learnfalungong.in
 learnfalungong.org.au
 es-learnfalungong.com
 faluninfo.net
+
+
 # The Epoch Times
 theepochtimes.com
 epochtimes.com
@@ -42,16 +44,36 @@ theepochtimes.gr
 epochtimes.co.kr
 epochtimesbusiness.it
 theepochtimes.es
+falundafa.org
+falundafa.hr
+falundafa.ca
+falundafa.at
+falungong.rs
+falungong.se
 epochtimes.es
 es.theepochtimes.com
 kr.theepochtimes.com
 subscribe.theepochtimes.com
+
 # Shen Yun
 shenyun.com
+falundafa.org
+falundafa.hr
+falundafa.ca
+falundafa.at
+falungong.rs
+falungong.se
 shenyunperformingarts.org
 shenyuncollections.com
 shenyundancer.com
+
 # Minghui
+falundafa.org
+falundafa.hr
+falundafa.ca
+falundafa.at
+falungong.rs
+falungong.se
 minghui.org
 mhpublishing.org
 tiantibooks.org