or download this
#!/usr/bin/perl
use HTML::TokeParser;
...
PV = 0x8207b90 "egrave: \303\250 : eacute: \303\251 : rsquo: \342\20
+0\231 : lsquo: \342\200\230"\0 [UTF8 "egrave: \x{e8} : eacute: \x{e9}
+ : rsquo: \x{2019} : lsquo: \x{2018}"]
CUR = 49
LEN = 52