my %freq;

while (<FILE>) {
    s/<.+?>/ /g;   # replace tags with spaces
    tr/A-Z0-9?!.,:;()*"`'-/a-z /s;  # convert upper- to lower-case, and
                                 # also convert digits, punct to space

# NOTE: check your output to see whether any other punctuation or
# non-word characters are getting through, and add those to the tr///
# as needed; also: hyphens might need to be treated differently from
# other punctuation (keep as-is, or delete, instead of converting to space?)

    s/$stopregex//g;  # remove any/all stop words

# at this point, line should contain only word tokens, but 
# use grep, just in case:

    for my $token (  grep /[a-z]/, split ) {  # only count tokens with letters
        $freq{$token}++;
    }
}