## use HTML::TableExtract; my $te = HTML::TableExtract->new( keep_html=>1, headers =>[qw(RefSNP)]); my $file = "Reference SNP(refSNP) Cluster Report rs111.htm"; my $document = do { local $/ = undef; open my $fh, "<", $file or die "could not open $file: $!"; <$fh>; }; $te->parse( $document); for my $ts($te->tables) { print "Table(",join(',',$ts->coords),":\n"; for my $row ($ts->rows) { for my $cell (@$row) { next unless $cell; $cell =~ s/<\/B> //i; print $cell."\n"; } } }
RefSNP
Organism:human (Homo sapiens)