#!/usr/bin/perl use strict; use warnings; use HTML::TableExtract; use YAML; my $te = HTML::TableExtract->new( attribs => { border => 0, bgcolor => '#EFEFEF', leftmargin => 15, topmargin => 5, }); $te->parse_file('kultus-bw.html'); my ($table) = $te->tables; for my $row ( $table->rows ) { cleanup(@$row); print "@$row\n"; } sub cleanup { for ( @_ ) { s/\s+//; s/[\xa0 ]+\z//; s/\s+/ /g; } }