use Encode; require LWP::UserAgent; my $ua = LWP::UserAgent->new; my $response = $ua->get("$ARGV[0]"); $_=$response->content; $_=decode('utf-8',$_); $result=""; for $r (/
\s*(.*?)<\/div>/isg, /]*>(.*?)<\/td>/isg) { #($r)=/
\s*(.*?)<\/div>/is; $r=~s/.*?<\/sup>//gi; $r=~s/.*?<\/h[45]>/ /gi; $r=~s/<(.*?)>//g; $r=~s/ / /gi; $r=~s/\s*(.*?)\s*$/$1/s; $r=~s/\s+/ /g; $r=~s/([\x{0080}-\x{ffff}])/'\\u'.sprintf('%04x',ord($1))/ge; $result.= ($result?' ':'') . $r; }