#!/bin/bash

# getlinks--Given a URL, returns all of its relative and 
#   absolute links. Has three options: -d to generate the primary 
#   domains of every link, -i to list just those links that are 
#   internal to the site (that is, other pages on the same site), and
#   -x to produce external links only (the opposite of –i).

if test $Argc -eq 0  {
  echo "Usage: $0 [-d|-i|-x] url"  > !2
  echo "-d=domains only, -i=internal refs only, -x=external only" > !2
  exit 1
}

if test $Argc -gt 1  {
  match $1 {
    with -d setglobal lastcmd = '"cut -d/ -f3 | sort | uniq'"
        shift
        
    with -r setglobal basedomain = ""http://$[echo $2 | cut -d/ -f3]/""
        setglobal lastcmd = ""grep \"^$basedomain\" | sed \"s|$basedomain||g\" | sort |\
	     uniq""
        shift
        
    with -a setglobal basedomain = ""http://$[echo $2 | cut -d/ -f3]/""
        setglobal lastcmd = ""grep -v \"^$basedomain\" | sort | uniq""
        shift
        
     with * echo "$0: unknown option specified: $1" > !2; exit 1
  }
} else {
  setglobal lastcmd = '"sort | uniq'"
}

lynx -dump $1 | \
sed -n '/^References$/,$p' | \
  grep -E '[[:digit:]]+\.' | \
  awk '{print $2}' | \
  cut -d'?' -f1 | \
eval $lastcmd

exit 0