#!/usr/bin/perl -w
use strict;
use 5.018;

# find linkchecker error reports in html report, linkchecker-out20151120.html

$/ = '<table align="left" border="0" cellspacing="0" cellpadding="1"';

my ($fh, $item, @erritems);

my $trterminator = qr[</tr>\n</table></td></tr></table>];

# errmsg from file:  
# Result</td><td bgcolor="#db4930">Error: 404....</td> ( or 301 etc.)
# Result</td><td bgcolor="#db4930">Error: SSLError: [Errno 1] _ssl.c:504:....</td>

my $errmsg = qr[Result</td><td bgcolor=".{7}">Error:.*?(?=</td>)];

my $eot = qr[</small></body></html>];

open ($fh, "<", 'linkchecker-out20151120.html') or die "Can't open, $!";

while (<$fh> ) {
   if ( $_ =~ /$eot/ ) {
	last;
   } else {
   	$_ = <$fh>;
   	$item = $_;
	$item =~ s/\n//gs;
	$item .= "\n\n";
   }

  if ( $item =~ /$errmsg/ ) {
	push @erritems, $item;
  }
}

say "Errors id'ed in LinkChecker output, 'linkchecker-out20151120.html'\n";
for $_(@erritems) {
	print $/;
	say $_;
}