tries to extract links from htmlcontent (hint: use with htmldompath)

htmlgreplinks.bash

# tries to extract links from htmlcontent (hint: use with htmldompath)
# @param htmlinput (piped)
# usage: curl "http://foo.com" | htmlgreplinks | sort | uniq

htmlgreplinks(){
  cat - | grep -E "(href|src|action)=[\"']*[\"']" | \
  sed "s/.*href=['\"]//g"   | \
  sed "s/.*action=['\"]//g" | \
  sed "s/.*src=['\"]//g"   | \
  sed "s/['\"].*//g"        | while read line; do [[ ! "$line" == "#" ]] && echo "$line"; done
}