michael@0: #! /bin/bash
michael@0: # This Source Code Form is subject to the terms of the Mozilla Public
michael@0: # License, v. 2.0. If a copy of the MPL was not distributed with this
michael@0: # file, You can obtain one at http://mozilla.org/MPL/2.0/.
michael@0: 
michael@0: 
michael@0: #original author: Alice Nodelman
michael@0: #contributor: Darin Fisher
michael@0: #
michael@0: #takes two inputs, $1 = file containing list of web pages of form http://pagename
michael@0: #                  $2 = output file where list of index files is dumped - useful for places list of links into scripts
michael@0: #
michael@0: # web pages are dropped in directories named for their urls
michael@0: 
michael@0: if [ $# != 2 ]; then
michael@0: 	echo 'missing command line arguments'
michael@0: 	echo
michael@0: 	echo 'usage: getpages.sh inputfile outputfile'
michael@0: 	echo '	inputfile: file containing one url per line of the form http://url'
michael@0: 	echo '	outputfile: file to be created during execution, contains a list of index files one per url'
michael@0: 	exit 
michael@0: fi
michael@0: 
michael@0: # generates the list of files to be cleansed (exclude image files)
michael@0: # disables any existing call-outs to the live web
michael@0: # provided by Darin Fisher
michael@0: cleanse_files() {
michael@0: 	  find "$1" -type f -a -print0 ! -iname \*.jpg -a ! -iname \*.gif -a ! -iname \*.png -a ! -name \*.bak | xargs -0 perl -pi -e 's/[a-zA-Z0-9_]*.writeln/void/g;' -e 's/[a-zA-Z0-9_]*.write/void/g;' -e 's/[a-zA-Z0-9_]*.open/void/g;' -e 's/"https/"httpsdisabled/gi;' -e 's/"http/"httpdisabled/gi;' -e 's/<object/<objectdisabled/gi;' -e 's/<embed/<embeddisabled/gi;' -e 's/load/loaddisabled/g;'
michael@0: }
michael@0: 
michael@0: mkdir testpages
michael@0: cd testpages
michael@0: for URL in $(cat ../$1); do
michael@0: 	#strip the leading http:// from the url
michael@0: 	CLEANURL=$(echo $URL | sed -e 's/http:\/\/\(.*\)/\1/')
michael@0: 	#create a directory with the cleaned url as the name
michael@0: 	echo "grabbing "$CLEANURL
michael@0: 	mkdir $CLEANURL
michael@0: 	cd $CLEANURL
michael@0: 	../../wget-1.10-css-parser/src/wget -p -k -H -E -erobots=off --no-check-certificate -U "Mozilla/5.0 (firefox)" --restrict-file-names=windows $URL -o outputlog.txt
michael@0: 	#figure out where/what the index file for this page is from the wget output log
michael@0: 	FILENAME=$(grep "saved" outputlog.txt | head -1 | sed -e "s/.*\`\(.*\)\'.*/\1/")
michael@0: 	rm outputlog.txt
michael@0: 	cd ..
michael@0: 
michael@0: 	#do the final cleanup of any dangling urls
michael@0: 	#with thanks to Darin Fisher for the code
michael@0: 	cleanse_files $CLEANURL
michael@0: 
michael@0: 	#add the index file link to the list of index files being generated
michael@0: 	echo $CLEANURL/$FILENAME >> $2
michael@0: done
michael@0: cd ..
michael@0: