comparediffs seems to be working nicely

.gitignore

@@ -15,4 +15,4 @@ pdfparanoia.egg-info/
 /*.pdf
 
 # temporary pdfs in tests/diff/
-tests/diff/*.pdf
+tests/diff/pdf

tests/diff/comparediffs

@@ -1,23 +1,68 @@
-for url in `cat urls`; do
+if [ "$#" != "2" ]; then
-	echo "Retrieving $url";
+	echo "Please supply the addresses of two SOCKS proxies:"
-	# TODO allow customizing the proxies, or more generally the retrieval mechanisms
+	echo "compare host1:port1 host2:port2"
-	# TODO allow local caching
+	exit 1
-	curl --socks localhost:1080 $url > 1.pdf
+fi
-	curl --socks localhost:1083 $url > 2.pdf
+
-	# TODO verify that we actually obtained pdfs
+proxy1="$1"
-	if diff 1.pdf 2.pdf; then
+proxy2="$2"
-		echo "PDFs are identical already, no need to use pdfparanoia"
+
-	else
+curl -s --socks $proxy1 http://google.com | grep "The document has moved" > /dev/null
-		cat 1.pdf | pdfparanoia > 1.cleaned.pdf
+if [ "$?" != "0" ]; then
-		cat 2.pdf | pdfparanoia > 2.cleaned.pdf
+	echo "SOCKS proxy $proxy1 doesn't seem to be working."
-		if diff 1.cleaned.pdf 2.cleaned.pdf; then
+	exit 2
-			echo "pdfparanoia successful scrubbed the PDFs"
+fi
-		else
+curl -s --socks $proxy2 http://google.com | grep "The document has moved" > /dev/null
-			echo "pdfparanoia failed!"
+if [ "$?" != "0" ]; then
-		fi
+	echo "SOCKS proxy $proxy2 doesn't seem to be working."
-		rm 1.cleaned.pdf
+	exit 3
-		rm 2.cleaned.pdf
+fi
+
+echo "--------------------------------------------------------------------------------------------------------------------------------"
+echo "Comparing PDFs downloaded via '$proxy1' and '$proxy2'"
+echo "Please enter URLs, one per line."
+echo 
+echo "PDFs which still differ after pdfparanoia will be left in the pdf/ subdirectory, with suffixes .1.cleaned.pdf and .2.cleaned.pdf"
+echo "--------------------------------------------------------------------------------------------------------------------------------"
+echo
+
+mkdir -p pdf
+
+while read url; do
+	hash=`echo $url | openssl sha1 | cut -d ' ' -f 2`
+	echo "Retrieving $url, with hash $hash";
+	if [ ! -s pdf/$hash.1.pdf ]; then
+		curl --socks $proxy1 -L --cookie cookie.jar -A "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)" -H "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8" $url > pdf/$hash.1.pdf
 	fi
-	rm 1.pdf
+	if [ "`head -c 4 pdf/$hash.1.pdf`" == "%PDF" ]; then
-	rm 2.pdf
+		if [ ! -s pdf/$hash.2.pdf ]; then
+			curl --socks $proxy2 -L --cookie cookie.jar -A "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)" -H "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8" $url > pdf/$hash.2.pdf
+		fi
+		if [ "`head -c 4 pdf/$hash.2.pdf`" == "%PDF" ]; then
+			if cmp -s pdf/$hash.1.pdf pdf/$hash.2.pdf; then
+				echo "PDFs are identical already, no need to use pdfparanoia"
+			else
+				echo "PDFs differ, running pdfparanoia"
+				if [ ! -s pdf/$hash.1.cleaned.pdf ]; then
+					cat pdf/$hash.1.pdf | pdfparanoia > pdf/$hash.1.cleaned.pdf
+				fi
+				if [ ! -s pdf/$hash.2.cleaned.pdf ]; then
+					cat pdf/$hash.2.pdf | pdfparanoia > pdf/$hash.2.cleaned.pdf
+				fi
+				if cmp -s pdf/$hash.1.cleaned.pdf pdf/$hash.2.cleaned.pdf; then
+					echo "pdfparanoia successful scrubbed the PDFs"
+					rm pdf/$hash.*.cleaned.pdf
+				else
+					echo "pdfparanoia failed!"
+				fi
+			fi
+		else
+			echo "Download failed from source 2"
+			rm pdf/$hash.*.pdf
+		fi
+	else
+		echo "Download failed from source 1"
+		rm pdf/$hash.*.pdf
+	fi
+	echo
 done

tests/diff/urls

@@ -1,8 +1,6 @@
-http://link.springer.com/content/pdf/10.1007/s00440-011-0397-9
-http://msp.org/apde/2012/5-2/apde-v5-n2-p07-s.pdf
 http://annals.math.princeton.edu/wp-content/uploads/annals-v176-n2-p11-s.pdf
+http://www.ams.org/journals/mcom/2012-81-278/S0025-5718-2011-02542-1/S0025-5718-2011-02542-1.pdf
+http://nyjm.albany.edu/j/2009/15-14p.pdf
+http://link.springer.com/content/pdf/10.1007/s00440-011-0397-9
 http://www.worldscientific.com/doi/pdf/10.1142/S2010326311500018
 http://www.sciencedirect.com/science?_ob=MiamiImageURL&_cid=272585&_user=994540&_pii=S0001870812001806&_check=y&_origin=article&_zone=toolbar&_coverDate=10-Sep-2012&view=c&originContentFamily=serial&wchp=dGLzVlt-zSkWb&md5=bfeb5e0619d45362640529aff02baeda&pid=1-s2.0-S0001870812001806-main.pdf
-http://www.ams.org/journals/mcom/2012-81-278/S0025-5718-2011-02542-1/S0025-5718-2011-02542-1.pdf
-http://www.ems-ph.org/journals/show_pdf.php?issn=1661-7207&vol=5&iss=2&rank=6
-http://nyjm.albany.edu/j/2009/15-14p.pdf

tests/diff/urls.denied

@@ -0,0 +1,2 @@
+http://msp.org/apde/2012/5-2/apde-v5-n2-p07-s.pdf
+http://www.ems-ph.org/journals/show_pdf.php?issn=1661-7207&vol=5&iss=2&rank=6