curl -s http://news.ycombinator.com/news | \ tidy -quiet -asxml -numeric -utf8 -file /dev/null | \ xmlstarlet sel \ -N x=http://www.w3.org/1999/xhtml \ -t -m "//x:tr[x:td[1][@class='title']]" \ -v "normalize-space(x:td[3][@class='title']/x:a)" -o ";" \ -v "x:td[3][@class='title']/x:a/@href" -o ";" \ -v "str:tokenize(following-sibling::x:tr[1]/x:td[2]/x:span[1], ' ')[1]" -o ";" \ -v "following-sibling::x:tr[1]/x:td[2]/x:a[1]" -n | \ xmlstarlet unesc