[perl]HTML::Parserを使う

HTML::Parserを使って、HTML内のタグを無視してテキストだけを抜き出す

--------

use HTML::Parser();

$flgInScript = 0;
sub proc_text
{
    my @a =@_;
    unless (  $flgInScript ){ 
        foreach  (@a){
            print $_;
        }
    }
}

sub incheck_script
{
    my @a =@_;

    foreach  (@a){
        if ( /script/i ){
            $flgInScript = 1;
        }
    }
}

sub outcheck_script
{
    if ( $flgInScript )
    {
        $flgInScript = 0;
    }

}


if ( $#ARGV <0  ){new(api_version => 3,
                       text_h => [\&proc_text , "dtext" ],
                       start_h => [\&incheck_script, "tagname"],
                       end_h => [\&outcheck_script,"tagname"]); 

$p->parse_file($ARGV[0]);