foreach (@infiles) { my $data; my $address = $_; unless(open (FILE,"<$_")){ print STDERR "could not open $_: $!\n"; next;} local $/; $data=; my($html) = $data =~ /(

|<\/P>| |)/im; if (defined($html)){ $data =~ s/<[^>]+>/\n/g; $data =~ s/ //ig; $data =~ s/<//ig; $data =~ s/"/"/ig; $data =~ s/&/&/ig; $data =~ s/&#\d+;/&/ig; $data =~ s/&&/ &/ig; $data =~ s/(\w+)&(\d+)/$1 $2/ig; } my($block, $lines, $auditor, $auditorcity, $auditorstate, $date_audited, $keyword1, $keyword2, $keyword3, $keyword4, $block2,); ($keyword1) = $data =~ /(have(\s*|\n)audited [^a])/i; ($keyword2) = $data =~ /(our(\s+|\n)audits|consent to)/i; if (!defined($keyword1) && !defined($keyword2)) {($block) ="";} elsif (!defined($keyword1) && defined($keyword2)) {($block) = $data =~ /($keyword2(?:[^\n]*\n){1,350})/im;} elsif(defined($keyword1)) {($block) = $data =~ /($keyword1(?:[^\n]*\n){1,350})/im;} ($keyword3) = $block =~ /(((REPORT(\s+|\n)OF|CONSENT OF)|)\s*INDEPENDENT\s*(CERTIFIED|registered|registered CERTIFIED|)\s*PUBLIC\s*(ACCOUNTANTS|accounting(\s+|\n)firm)|REPORT OF INDEPENDENT ACCOUNTANTS|REPORT OF INDEPENDENT AUDITORS|)/im; if (defined($keyword3)) {($lines) = substr ($block,1,index($block,$keyword3)-1);} elsif (!defined($keyword3)){($lines) = $block;} ($auditor) = $lines =~ /^\s*((?:[A-Z]\w+|\/\w+|&\s*\w+).+?\s*(LLP|L\.L\.P\.|LLC|LTD|P.A.|P\.C\.|PC)(\.|))$/m; if(defined ($auditor)){ ($auditorcity) = $lines =~ /$auditor\s*(?:(?:.+?\s*(?:LLP|L\.L\.P\.|LLC|LTD|P.A.|P\.C\.|PC)(?:\.|))|\(.+\)|)\s*(.+?)(?