source: lab/trunk/Dev/pukiwikiplus/getsource.pl @ 121

#! /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: [-f] url_to_pukiwikiplus_page\n";
    exit;
}

my $file;
if ($ARGV[0] eq '-f') {
    $file = shift @ARGV;
}

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

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

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

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

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

if ($file) {
    print STDERR "saving: '$file'\n";
    open STDOUT, ">$file";
}
print encode('utf8', $text);


sub wikifile {
    my $pagename = shift @_;
    
    $pagename =~ s/%([0-9A-Fa-f][0-9A-Fa-f])/pack('H2', $1)/eg;
    return uc unpack("H*", $pagename);
}