source: lab.git/Dev/pukiwikiplus/getsource.pl @ 74f778c

#! /usr/bin/perl

use strict;
use warnings;
use utf8;

use Web::Scraper;
use URI;
use Data::Validate::URI qw(is_uri);
use Encode;

if (@ARGV < 1) {
    print "$0: url_to_pukiwikiplus_page\n";
    exit;
}

my $url = $ARGV[0];
die "$0: '$url' is not URI" unless is_uri($url);

if ($url !~ /cmd=source/ ) {
    $url =~ s#\?(.+)#\?cmd=source&page=$1#;
}

print STDERR "getting: '$url'\n";

my $source = scraper {
    process "pre#source", "source" => "TEXT";
    result "source";
};

my $text = $source->scrape( URI->new($url) );

print encode('utf8', $text);