Add README

README.md

@@ -0,0 +1,7 @@
+# wikiverse-analysis
+
+1. Visit this page in a web browser and save it to an HTML file:  http://search.fed.wiki.org:3030/#/find=sites&within=sites&match=and&query=
+2. Install [`pup`](https://github.com/EricChiang/pup)
+3. Run `./wikiverse-scan.sh`, optionally providing the path to the HTML file as
+   an argument
+4. Results will appear in `wikiverse-https-scan.csv`

wikiverse-scan.sh

@@ -1,3 +1,12 @@
+#!/bin/bash
+
+html_file="${1:-search.fed.wiki.org.html}"
+
+if [ -z $html_file ]; then
+	echo "HTML file '$html_file' does not exist"
+	exit 1;
+fi
+
 process_result() {
 	wiki=$1
 	farm=$(echo "$wiki" | xargs tldextract | cut -d' ' -f2,3 | sed 's/ /./g')
@@ -6,10 +15,10 @@ process_result() {
 	echo "$wiki,$farm,$status_http,$status_https"; 
 }
 
-echo "Wiki,Farm,HTTP?,HTTPS?" > ./wikiverse-https-scan.txt.csv
+echo "Wiki,Farm,HTTP?,HTTPS?" > ./wikiverse-https-scan.csv
 
-for wiki in $(pup '#results a attr{href}' < search.fed.wiki.org.html); do   
+for wiki in $(pup '#results a attr{href}' < "$html_file"); do   
 	process_result "$wiki" & 
-done >> wikiverse-https-scan.txt.csv
+done >> wikiverse-https-scan.csv
 
 wait $(jobs -p)