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

# test errmsg match

# sample (and partial; see the chunking in the next code) errmsgs 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 @data_sample = (
    '<tr><td bgcolor="#db4930">Result</td><td bgcolor="#db4930">Error: 404 Not Found</td></tr>',
    '<tr><td bgcolor="#db4930">Result</td><td bgcolor="#db4930">Error: SSLError: [Errno 1] _ssl.c:504: error:14090086:SSL routines:SSL3_GET_SERVER_CERTIFICATE:certificate verify failed</td></tr>',
    '<tr><td foo bar baz> abcde </td></tr>'
                 );

my $data_line;
for $data_line(@data_sample) {
	if ( $data_line =~ /$errmsg/ ) {
		say "\t FOUND IT: $data_line \n";
    } else {
		say "\t NO MATCH ON $data_line \n";
    }
}

##</code><code>##

C:\>test_err_finder.pl
         FOUND IT: <tr><td bgcolor="#db4930">Result</td><td bgcolor="#db4930">Error: 404 Not Found</td></tr>

         FOUND IT: <tr><td bgcolor="#db4930">Result</td><td bgcolor="#db4930">Error: SSLError: [Errno 1] _ssl.c:504: error:14090086:SSL routines:SSL3_GET_SERVER_CERTIFICATE:certificate
verify failed</td></tr>

         NO MATCH ON <tr><td foo bar baz> abcde </td></tr>
C:\>

##</code><code>##

#!/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 $_;
}