view release on metacpan or  search on metacpan

lib/App/FetchwareX/HTMLPageSync.pm  view on Meta::CPAN

        msg <<EOM;
Uninstalling this HTMLPageSync package by deleting your destination directory.
EOM

    ###BUGALERT### Before release go though all of Fetchware's API, and subifiy
    #each main component like lookup and download were, the later ones were not
    #done this way. That way I can put say chdir_to_build_path() here instead of
    #basicaly copying and pasting the code like I do below. Also
    #chdir_to_build_path() can be put in :OVERRIDE_UNINSTALL!!! Which I can use
    #here.
        chdir $build_path or die <<EOD;
App-FetchwareX-HTMLPageSync: Failed to uninstall the specified package and specifically to change
working directory to [$build_path] before running make uninstall or the
uninstall_commands provided in the package's Fetchwarefile. Os error [$!].
EOD

        if ( defined config('destination_directory')) {
            # Use File::Path's remove_tree() to delete the destination_directory
            # thereby "uninstalling" this package. Will throw an exception that I'll
            # let the main eval in bin/fetchware catch, print, and exit 1.
            vmsg <<EOM;
Deleting entire destination directory [@{[config('destination_directory')]}].
EOM
            remove_tree(config('destination_directory'));
        } else {
            die <<EOD;
App-FetchwareX-HTMLPageSync: Failed to uninstall the specified App::FetchwareX::HTMLPageSync
package, because no destination_directory is specified in its Fetchwarefile.
This configuration option is required and must be specified.
EOD
        }
    # keep_destination_directory was set, so don't delete destination directory.
    } else {
        msg <<EOM;
Uninstalling this HTMLPageSync package but keeping your destination directory.
EOM

    }

    return 'True for success.';
}




sub upgrade {
    my $download_path = shift; # $fetchware_package_path is not used in HTMLPageSync.

    # Get the listing of already downloaded file names.
    my @installed_downloads = glob(config('destination_directory'));

    # Preprocess both @$download_path and @installed_downloads to ensure that
    # URL crap or differing full paths won't screw up the "comparisons". The
    # clever delete hashslice does the "comparisons" if you will.
    my @download_path_filenames = map { ( uri_split($_) )[2] } @$download_path;
    my @installed_downloads_filenames = map { ( splitpath($_) ) [2] }
        @installed_downloads;

    # Determine what files are in @$download_path, but not in
    # @installed_downloads.
    # Algo based on code from Perl Cookbook pg. 126.
    my %seen;
    @seen{@$download_path} = ();
    delete @seen{@installed_downloads};

    my @new_urls_to_download = keys %seen;

    if (@new_urls_to_download > 0) {
        # Alter $download_path to only list @new_urls_to_download. That way
        # download() only downloads the new URLs not the already downloaded ones
        # again.
        $download_path = [@new_urls_to_download];

        return 'New URLs Found.';
    } else {
        return;
    }
}


1;

=pod

=head1 NAME

App::FetchwareX::HTMLPageSync - An App::Fetchware extension that downloads files based on an HTML page.

=head1 VERSION

version 1.016

=head1 SYNOPSIS

=head2 Example App::FetchwareX::HTMLPageSync Fetchwarefile.

    page_name 'Cool Wallpapers';

    html_page_url 'http://some-html-page-with-cool.urls';

    destination_directory 'wallpapers';

    # pretend to be firefox
    user_agent 'Mozilla/5.0 (X11; Linux x86_64; rv:15.0) Gecko/20100101 Firefox/15.0.1';

    # Customize the callbacks.
    html_treebuilder_callback sub {
        # Get one HTML::Element.
        my $h = shift;

        # Return true or false to indicate if this HTML::Element shoudd be a
        # download link.
        if (something) {
            return 'True';
        } else {
            return undef;
        }
    };

    download_links_callback sub {
        my @download_urls = @_;