#!/bin/bash

# Add %@% to the end of every line, turn newline into space,
# and add newlines at the very beginning and end of each HTML tag.
# Then we'll get each tag on one line while we READ line by line.
sed 's/$/%@%/' | tr '\n' ' ' | sed 's/</\n</g;s/>/>\n/g' |
while IFS="" read LINE
do
        case "${LINE:0:2}" in
        "</")
#               echo "<!-- Close tag -->"
                echo "${LINE}"
                ;;
        "<"*)
                read TAGTYPE G <<< "${LINE:1}"

                # Feed different things into sed depending on what tag we got
                case "${TAGTYPE}" in
                [iI][mM][gG])
                        REPLACE="[sS][rR][cC]"
                        WITH="src"
                        ;;
                [aA])
                        REPLACE="[hH][rR][eE][fF]"
                        WITH="href"
                        ;;
                *)
                        REPLACE=""
                        ;;
                esac

                if [ -z "${REPLACE}" ]
                then
                        #echo "<!-- No substitution -->"
                        echo "${LINE}"
                else
                        echo "${LINE}" | sed "s#${REPLACE}=['\"][^'\"]*['\"]#${WITH}=''#"
                fi

                ;;
        *)
                #echo "<!-- Raw text -->"
                echo "${LINE}"
                ;;
        esac
# Delete all newlines, then change %@% back into newlines
done | tr -d '\n' | sed 's/%@%/\n/g'