#c:/Perl/bin -w

use File::Find;
use strict;

# PURPOSE:  find_http.pl finds ALL links in which "http" appears inside "<a href.../a>" 
# in all w3c 4.01 compliant *.ht* files in the ARGV[0] directory and its subdirs; in other 
# words, finds absolute links, including both offsite  links and those local links written
# in absolute notation, prepended in output by # the line number in which the link is found.
#
# ACKNOWLEDGEMENTS: thanks to ikegami, Joost, holli, Scooterm, zaxo, corion and other PM, 
# for their tutelage (but who bear NO responsibility for non-idiomatic constructs or errors).
# Readers should also note that holli warns emphatically NOT to use regex 
# to parse html ("because it is fatally error-prone, unneccesary (there is HTML::Parser)..." and that he says "fatally error-prone" especially when applied "to ill-formed html."  The warning's been taken to heart, but was laid aside for 
# the purposes this drill (schodckwm 1/22/05)

use vars qw( $dirname $file @filenames $input @input $linecounter $part @parts $href $offsite $link @found $subdir );

$linecounter = "0";
$href      = qr/<a /i;          # Any link with begin "<a " (sub gethtml, Line 71)
$offsite = qr%http:[\/]{2}%i;   # find links which include "http" (Line 79)

if (@ARGV == 1) {       # Get the name of the directory to scan
   $dirname = $ARGV[0]; 
} else { 
   print STDERR ("\tUsage: $0 dirname > outfile.txt\n\twhere dirname can be a relative or absolute path\n\tEven under MS Windows, use of *nix-style '/' forward slashes in path is recommended.\n\ti.e., from d:, 'd:\/foo' or '.\/foo' \(or '.\/long\/path\/to\/target'\)"); exit(1); 
}

# call &process_file for each file in the directory (& subdirs) in $ARGV[0]

find \&process_file, "$dirname";
&gethtml;
exit();

####

sub process_file {

  if ($_ =~ /(.+)(ht[ml]{1,2})/ ) {
      $subdir = $File::Find::dir . "/";    # see below at # 1:
      push @filenames, $subdir . $_;
   } else {
   return (@filenames);
   }
}

# 1: (from c:/Perl/lib/file/find.pm)
#    $File::Find::dir  is the current directory name,
#    also from find.pm:  
#    $_ is the current filename within that directory

####

sub gethtml {

print "\n\t Files found:\n";

foreach $file(@filenames) {
   print "\n\t found: $file";
   open INFILE, "$file" or warn "\tCan't open $file: $! ";
   push @found, "\n\n\t" . $file ."\n";

   @input = <INFILE>;         # slurp the whole file to @input
   $linecounter = 0;          # reset linecounter for next file
      foreach $input(@input) {
         $linecounter++;
         @parts = split m!(</a>)!i, $input;
         foreach $part(@parts) {
         if ( $part =~ m%
            (                 # CAPTURE to $1
            $href             # START ON '<a href="' OR '<a href="mailto:', etc
            .+                # one or more of anything not a newline 
                              # NB: the close tag already eaten by split
            )                 # close capture 
            %gix              # end match (g not necessary)
         )                    # end paren of 'if' test
         
         { my $link_a = $1;   # store the match of (any) link
           if ( $link_a =~ m%($offsite)% ) {   # check for http://  NB: This regex
                                               # does NOT constrain the position
                                               # of $offsite in the <a href...</a>
                                               # because the link may be formatted, for 
                                               # example, <a name="foo" href="http....                                                   
              $link = $link_a . "</a>";        # add the close tag
              push @found, $linecounter;
              push @found , $link;
           }                               # end  if $link_a...
         }                                 # end if $part...
      }                                    # end foreach #part(@parts)
    }                                      #end foreach $input(@input)
    close INFILE;
    }                                      # end foreach $file(@filenames)
&print (@found);
}
                                          # end sub gethtml
#####

sub print {
   print "\n\n\t Found these \"http\" Links \n";
   foreach $link(@found) {
      my $out = $link . " ";
        if ( $link !~ /^\d*$/) {
         $out = $out . "\n";
      }
   print $out;
   }
}

#ENDNOTES:   With ActiveState perl 5.8.4, this extracts all "http" links from a 
# local mirror (Xitami on E:) of a ~1600 page website and writes them to a 
# local ATA drive (F: on a P4, 2.4GHz, w2k box) in ~16 seconds. 
# The pages searched range from trivial to ~2400 lines of 4.01 html
#
# It would be non-trivial to output to html. However, reformatting
# "Line_number <a href="whatever">rendered link</a>" to be displayed properly by 
# a browser beyond the scope of this exercise