0 #ˆl–Ðz¾” *h¥² Aq ÜTÅ£¿ „À¿ÂÁ?÷=head1 NAME XML::LibXML::Parser - Parsing XML Data with XML::LibXML =head1 SYNOPSIS use XML::LibXML 1.70; # Parser constructor $parser = XML::LibXML->new(); $parser = XML::LibXML->new(option=>value, ...); $parser = XML::LibXML->new({option=>value, ...}); # Parsing XML $dom = XML::LibXML->load_xml( location => $file_or_url # parser options ... ); $dom = XML::LibXML->load_xml( string => $xml_string # parser options ... ); $dom = XML::LibXML->load_xml( string => (\$xml_string) # parser options ... ); $dom = XML::LibXML->load_xml({ IO => $perl_file_handle # parser options ... ); $dom = $parser->load_xml(...); # Parsing HTML $dom = XML::LibXML->load_html(...); $dom = $parser->load_html(...); # Parsing well-balanced XML chunks $fragment = $parser->parse_balanced_chunk( $wbxmlstring, $encoding ); # Processing XInclude $parser->process_xincludes( $doc ); $parser->processXIncludes( $doc ); # Old-style parser interfaces $doc = $parser->parse_file( $xmlfilename ); $doc = $parser->parse_fh( $io_fh ); $doc = $parser->parse_string( $xmlstring); $doc = $parser->parse_html_file( $htmlfile, \%opts ); $doc = $parser->parse_html_fh( $io_fh, \%opts ); $doc = $parser->parse_html_string( $htmlstring, \%opts ); # Push parser $parser->parse_chunk($string, $terminate); $parser->init_push(); $parser->push(@data); $doc = $parser->finish_push( $recover ); # Set/query parser options $parser->option_exists($name); $parser->get_option($name); $parser->set_option($name,$value); $parser->set_options({$name=>$value,...}); # XML catalogs $parser->load_catalog( $catalog_file ); =head1 PARSING An XML document is read into a data structure such as a DOM tree by a piece of software, called a parser. XML::LibXML currently provides four different parser interfaces: =over 4 =item * A DOM Pull-Parser =item * A DOM Push-Parser =item * A SAX Parser =item * A DOM based SAX Parser. =back =head2 Creating a Parser Instance XML::LibXML provides an OO interface to the libxml2 parser functions. Thus you have to create a parser instance before you can parse any XML data. =over 4 =item new $parser = XML::LibXML->new(); $parser = XML::LibXML->new(option=>value, ...); $parser = XML::LibXML->new({option=>value, ...}); Create a new XML and HTML parser instance. Each parser instance holds default values for various parser options. Optionally, one can pass a hash reference or a list of option => value pairs to set a different default set of options. Unless specified otherwise, the options C<<<<<< load_ext_dtd >>>>>>, and C<<<<<< expand_entities >>>>>> are set to 1. See L<<<<<< Parser Options >>>>>> for a list of libxml2 parser's options. =back =head2 DOM Parser One of the common parser interfaces of XML::LibXML is the DOM parser. This parser reads XML data into a DOM like data structure, so each tag can get accessed and transformed. XML::LibXML's DOM parser is not only capable to parse XML data, but also (strict) HTML files. There are three ways to parse documents - as a string, as a Perl filehandle, or as a filename/URL. The return value from each is a L<<<<<< XML::LibXML::Document >>>>>> object, which is a DOM object. All of the functions listed below will throw an exception if the document is invalid. To prevent this causing your program exiting, wrap the call in an eval{} block =over 4 =item load_xml $dom = XML::LibXML->load_xml( location => $file_or_url # parser options ... ); $dom = XML::LibXML->load_xml( string => $xml_string # parser options ... ); $dom = XML::LibXML->load_xml( string => (\$xml_string) # parser options ... ); $dom = XML::LibXML->load_xml({ IO => $perl_file_handle # parser options ... ); $dom = $parser->load_xml(...); This function is available since XML::LibXML 1.70. It provides easy to use interface to the XML parser th