#!/usr/bin/perl -p0 s/]|<(?1)*>)*>//gs; s/<(?!div\b[^>]*\bclass\s*=\s*(['"])data\1)([^<>]|<(?2)*>)*>//gs; s/.*?<(?:[^'"]|(['"]).*?\1)*?\bid\s*=\s*(['"])(.*?)\2.*?>([^<]*)/$3=$4, /gs; s/&#(\w+);/chr $1/ge; s/[^\w=, ]|, $|(.)\1\1//g;