view release on metacpan or  search on metacpan

bin/html2plain  view on Meta::CPAN

    {
	my ($html_txt,$plain_txt,$header);

	if (exists($html_entries{$base_name}{htmlF}))
	{
	    my $html_txt;
	    if (!defined(open(F,"<$html_entries{$base_name}{htmlF}")))
	    {
		warn "Unable to open \"$html_entries{$base_name}{htmlF}\".\n";
		next;
	    }
	    while (my $l=<F>)
	    {
		$html_txt.=$l;
	    }
	    close(F);

	    ($plain_txt,$header)=$C->clean($html_txt);
	    if (!defined($plain_txt))
	    {
		warn "Getting the plain text for basename \"$base_name\" failed. " .
		    $C->errmsg() if 
		    $Warnings;
		$C->clearerr();
		next;
	    }
	}
	else
	{
	     warn "No HTML file for basename \"$base_name\".\n" if 
		$Warnings;
	     next;
	}

	if (!&_output_plain($plain_txt))
	{
	    warn "Outputting the Alvis records for base name \"$base_name\" failed. " . $C->errmsg() if 
		$Warnings;
	    $C->clearerr();
	    next;
	}
    }

    return 1;
}

sub _output_plain
{
    my $plain_txt=shift;

    my $out_f;
    my $dir=$ODir . '/' . 
	int($outputN / $NPerOurDir);
    if ($outputN % $NPerOurDir==0)
    {
	mkdir($dir);
    }
    $out_f=$dir . '/' . $outputN . '.' .
	$OutSuffix;
    
    if (!defined(open(OUT,">:utf8",$out_f)))
    {
	warn "Cannot open output file \"$out_f\".\n";
	return 0;
    }
    print OUT $plain_txt;
    close(OUT);
    
    $outputN++;
    print "$outputN\r";
}

__END__

=head1 NAME
    
    html2plain.pl - HTML to plain text converter
    
=head1 SYNOPSIS
    
    html2plain.pl [options] [source directory ...]

  Options:

    --html-ext                HTML file identifying filename extension
    --out-ext                 output filename extension
    --out-dir                 output directory
    --N-per-out-dir           # of records per output directory
    --source-encoding         the encoding of the HTML files
    --[no]assert-html         assert that the document is HTML
    --[no]symbolic-char-entities-to-chars
                              convert symbolic character entities to UTF-8
                              characters
    --[no]numerical-char-entities-to-chars
                              convert numerical character entities to UTF-8
                              characters
    --[no]clean-whitespace    remove redundant whitespace
    --[no]assert-assumptions  assert that the document is in UTF-8 and contains
                              before actually converting to plain text
    --help                    brief help message
    --man                     full documentation
    --[no]warnings            warnings output flag
    
=head1 OPTIONS
    
=over 8

=item B<--html-ext>

    Sets the HTML file identifying filename extension. 
    Default value: 'html'.

=item B<--out-ext>

    Sets the output filename extension. 
    Default value: 'plain'.

=item B<--out-dir>

    Sets the output directory. Default value: '.'.