#!/usr/bin/awk -f BEGIN { in_item = 0 pub_date = "" title = "" link = "" } # Start of item // { in_item = 1 pub_date = "" title = "" link = "" } # End of item - print collected data /<\/item>/ { if (in_item && title != "") { print "" print title "" print "---" if (pub_date != "") { print "
Published: " pub_date "
" } print "" } in_item = 0 } # Extract title in_item && // { gsub(/<title>/, "") gsub(/<\/title>/, "") gsub(/^[ \t]+|[ \t]+$/, "") # trim whitespace title = $0 } in_item && /<link>/ { gsub(/<link>/, "") gsub(/<\/link>/, "") gsub(/^[ \t]+|[ \t]+$/, "") # trim whitespace link = $0 } # Extract publication date in_item && /<pubDate>/ { gsub(/<pubDate>/, "") gsub(/<\/pubDate>/, "") gsub(/^[ \t]+|[ \t]+$/, "") # trim whitespace pub_date = $0 }