Hi,
I am trying to extract the following text from HTML page using the following code, but my code fails..
Budget - $25,000,00
Gross(worldwide) - $58,500,00
#!/usr/bin/perl
use HTML::TokeParser;
my $content = <<HTML;
<h5>Budget</h5>
$25,000,000 (estimated)<br/>
<br/>
<h5>Opening Weekend</h5>
$727,327 (USA) (<a href="/date/09-25/">25 September</a> <a href="/year
+/1994/">1994</a>) (33 Screens)<br/>
<br/>
<h5>Gross</h5>
$28,341,469 (USA) (<a href="/date/08-05/">5 August</a> <a href="/year/
+2012/">2012</a>)<br/>£2,344,349 (UK) (<a href="/date/05-18/">18
+May</a> <a href="/year/1995/">1995</a>)<br/>£1,732,123 (UK) (<a
+href="/date/04-16/">16 April</a> <a href="/year/1995/">1995</a>)<br/>
+$58,500,000 (Worldwide)<br/>$555,480 (Belgium)<br/>ESP 637,291,985 (S
+pain)<br/>
<br/>
<h5>Admissions</h5>
82,890 (Belgium)<br/>163,594 (France) (<a href="/date/03-28/">28 March
+</a> <a href="/year/1995/">1995</a>)<br/>410,811 (Germany) (<a href="
+/date/12-31/">31 December</a> <a href="/year/1995/">1995</a>)<br/>1,2
+45,604 (Spain)<br/>
<br/>
<h5>Filming Dates</h5>
<a href="/date/06-16/">16 June</a> <a href="/year/1993/">1993</a> 
+;- <a href="/date/09-10/">10 September</a> <a href="/year/1993/"
+>1993</a><br/>
<br/>
HTML
my $description = "";
my $parser = HTML::TokeParser->new(\$content) || die "Can't open: $!";
while (my $token = $tp->get_tag("h5")) {
my $text = $parser->get_text();
last if $text =~ /budget/i;
}