mediawiki-extract



#!/usr/bin/perl

# extract and decode mediawiki content from HTML source view

use warnings;
use strict;

use Path::Tiny;
use HTML::Entities;

my $infile = shift;
my $outfile = shift || $infile;

$_ = path($infile)->slurp_utf8;

s!.*<textarea[^>]*>!!s;
s!</textarea.*!!s;
decode_entities($_);

path($outfile)->spew_utf8($_);

1;