perl: HTML::Parser from command line

perl-html-parser-snippets-01.sh

#!/usr/bin/env bash
# HTML::Parser has a convenient option to strip Declarations 
# by adding a handler.
# (from Stackoverflow q 16358962)
perl -MHTML::Parser -we '
    $p = HTML::Parser->new(default_h => [sub {print @_},"text"] ); 
    $p->handler(declaration => ""); 
    $p->parse_file(shift) or die "Cannot parse: $!"; ' infile.html

# HTML::TreeBuilder module is also useful to remove elements and attributes