#!/usr/bin/perl use HTML::TokeParser; #use Data::Dump::Streamer; use strict; use Devel::Peek; local $/; my $lines = ; my $tok_par = HTML::TokeParser->new(\$lines); my $tok_inf = $tok_par->get_token ; my $tok_typ = shift @{$tok_inf}; my $title = $tok_par->get_text() || ""; Dump ($title); __DATA__ egrave: è : eacute: é : rsquo: ’ : lsquo: ‘ __END__ SV = PV(0x81b4290) at 0x81ed950 REFCNT = 1 FLAGS = (PADBUSY,PADMY,POK,pPOK,UTF8) PV = 0x8207b90 "egrave: \303\250 : eacute: \303\251 : rsquo: \342\200\231 : lsquo: \342\200\230"\0 [UTF8 "egrave: \x{e8} : eacute: \x{e9} : rsquo: \x{2019} : lsquo: \x{2018}"] CUR = 49 LEN = 52