The requested URL was not found on this server.
Additionally, a 404 Not Found error was encountered while trying to use an ErrorDocument to handle the request.
/ 1lzjh eA "&Tţ mǃ_ ub &=LV[( 1 1package HTML::PullParser; require HTML::Parser; @ISA=qw(HTML::Parser); $VERSION = "3.57"; use strict; use Carp (); sub new { my($class, %cnf) = @_; # Construct argspecs for the various events my %argspec; for (qw(start end text declaration comment process default)) { my $tmp = delete $cnf{$_}; next unless defined $tmp; $argspec{$_} = $tmp; } Carp::croak("Info not collected for any events") unless %argspec; my $file = delete $cnf{file}; my $doc = delete $cnf{doc}; Carp::croak("Can't parse from both 'doc' and 'file' at the same time") if defined($file) && defined($doc); Carp::croak("No 'doc' or 'file' given to parse from") unless defined($file) || defined($doc); # Create object $cnf{api_version} = 3; my $self = $class->SUPER::new(%cnf); my $accum = $self->{pullparser_accum} = []; while (my($event, $argspec) = each %argspec) { $self->SUPER::handler($event => $accum, $argspec); } if (defined $doc) { $self->{pullparser_str_ref} = ref($doc) ? $doc : \$doc; $self->{pullparser_str_pos} = 0; } else { if (!ref($file) && ref(\$file) ne "GLOB") { require IO::File; $file = IO::File->new($file, "r") || return; } $self->{pullparser_file} = $file; } $self; } sub handler { Carp::croak("Can't set handlers for HTML::PullParser"); } sub get_token { my $self = shift; while (!@{$self->{pullparser_accum}} && !$self->{pullparser_eof}) { if (my $f = $self->{pullparser_file}) { # must try to parse more from the file my $buf; if (read($f, $buf, 512)) { $self->parse($buf); } else { $self->eof; $self->{pullparser_eof}++; delete $self->{pullparser_file}; } } elsif (my $sref = $self->{pullparser_str_ref}) { # must try to parse more from the scalar my $pos = $self->{pullparser_str_pos}; my $chunk = substr($$sref, $pos, 512); $self->parse($chunk); $pos += length($chunk); if ($pos < length($$sref)) { $self->{pullparser_str_pos} = $pos; } else { $self->eof; $self->{pullparser_eof}++; delete $self->{pullparser_str_ref}; delete $self->{pullparser_str_pos}; } } else { die; } } shift @{$self->{pullparser_accum}}; } sub unget_token { my $self = shift; unshift @{$self->{pullparser_accum}}, @_; $self; } 1; __END__ =head1 NAME HTML::PullParser - Alternative HTML::Parser interface =head1 SYNOPSIS use HTML::PullParser; $p = HTML::PullParser->new(file => "index.html", start => 'event, tagname, @attr', end => 'event, tagname', ignore_elements => [qw(script style)], ) || die "Can't open: $!"; while (my $token = $p->get_token) { #...do something with $token } =head1 DESCRIPTION The HTML::PullParser is an alternative interface to the HTML::Parser class. It basically turns the HTML::Parser inside out. You associate a file (or any IO::Handle object or string) with the parser at construction time and then repeatedly call $parser->get_token to obtain the tags and text found in the parsed document. The following methods are provided: =over 4 =item $p = HTML::PullParser->new( file => $file, %options ) =item $p = HTML::PullParser->new( doc => \$doc, %options ) A C