Thread HTML Parser - Inhalte nicht immer vollständig
(4 answers)
Opened by Gast at 2007-11-18 21:51
require HTML::Parse;
require HTML::FormatText; use LWP::UserAgent; my $ua = LWP::UserAgent->new; my $response = $ua->get($url); if ($response->is_success) { $doc=$response->content; } $khtmldata = HTML::Parse::parse_html($doc); $kformatter = new HTML::FormatText; $ktextdata = $kformatter->format($khtmldata); $ktextdata =~ s/<([^>]|\s)*>//gs; $ktextdata =~ s/[\[\]]+//g; $ktextdata =~ s/\*//g;; HTH. |