Re: how to use regular expressions read some string from a htm file

[reneeb]

You can use HTML::Parser:

#! /usr/bin/perl
use strict;
use warnings;
use HTML::Parser;

my @links;
my $string = qq~<a href="url1">linktext1</a> Ein anderer Text
                <a href="url2">linktext2</a> text~;

my $p = HTML::Parser->new();
$p->handler(start => \&start_handler,"tagname,attr,self");
$p->parse($string);

foreach my $link(@links){
  print "Linktext: ",$link->[1],"\tURL: ",$link->[0],"\n";
}

sub start_handler{
  return if(shift ne 'a');
  my ($class) = shift->{href};
  my $self = shift;
  my $text;
  $self->handler(text => sub{$text = shift;},"dtext");
  $self->handler(end => sub{push(@links,[$class,$text]) if(shift eq 'a
+')},"tagname");
}