use strict; use LWP::UserAgent; use XML::LibXML; # Or http://www.cboe.com/Chinese/ my $url = 'http://www.cboe.com/Spanish/'; my $ua = 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0)'; my $browser = LWP::UserAgent->new(); # Uncomment this line to crash libxml's parser # $browser->agent($ua); my $response = $browser->get($url); my $content = $response->content; my $type = $response->content_type; print "Cleaning $url ($type)...\n"; clean_html($content); sub clean_html { my $input = shift; my $parser = XML::LibXML->new(); $parser->recover(1); my $cleaned = $parser->parse_html_string($input)->toStringHTML; } #### output conversion failed due to conv error Bytes: 0xE4 0xE5 0xE6 0xE8 xmlOutputBufferWrite: encoder error output conversion failed due to conv error Bytes: 0xE5 0xE6 0xE8 0x26 xmlOutputBufferWrite: encoder error ...