Reverse dumping lynx links
9 Jun 2010
Another boring code snippet for me to remember. How to get lynx references back into hyperlinked format.
lynx -dump URL > filename.txt
for i in $(egrep ^" *[0-9]*\." filename.txt | sed -e 's/^ *//g' | cut -f1 -d ".");
do egrep ^" *\[*$i(\.|\])" filename.txt | tac | perl -p -i -e 's/\n//g' | perl -p -i -e 's/ [0-9]*\. /\n<a href="/g' | tr -s " " | perl -p -i -e 's/ \[[0-9]*\]/">/g' | sed '/^ *$/d' | sed -e 's/$/<\/a><br \/>\n/g' >> filename-clean.html;
done
