04126159 http://www.kultusportal-bw.de/servlet/PB/menu/1188427/index.html?COMPLETEHREF=http://www.kultus-bw.de/did_abfrage/detail.php?id=04133309
|
Schnellsuche | Erweiterte Suche | Hilfe Allgemeine Daten der Schule / Behörde:
|
##
#!/usr/bin/perl
use strict; #
use warnings; #
use diagnostics; #
use LWP::Simple; #
use HTML::TokeParser; #
my $url = ' ';
# Just an example: the URL where we have to count up in order to get all the pages we have to count the URL from somewhat 041000000 to 04999999 or even better to 06000000
use LWP::Simple;
my $content = get $url;
die "Couldn't get $url" unless defined $content;
# Then go do things with $content, like this:
# start a new Parser-job with
my $p = HTML::TokeParser->new($url) or die "Can't open $url: ($!)";
#find the tags 'xyz'
while (my $tag = $p->get_tag('div', '/html'))
# my output... !!
my $out_file='./output.xml';