<books> <book> <author>Jack Herrington</author> <title>PHP Hacks</title> <publisher>O'Reilly</publisher> </book> <book> <author>Jack Herrington</author> <title>Podcasting Hacks</title> <publisher>O'Reilly</publisher> </book> </books>
1.DOMDocument方法
<?php $doc = new DOMDocument(); $doc->load( 'books.xml' ); $books = $doc->getElementsByTagName( "book" ); foreach( $books as $book ) { $authors = $book->getElementsByTagName( "author" ); $author = $authors->item(0)->nodeValue; $publishers = $book->getElementsByTagName( "publisher" ); $publisher = $publishers->item(0)->nodeValue; $titles = $book->getElementsByTagName( "title" ); $title = $titles->item(0)->nodeValue; echo "$title - $author - $publisher\n"; echo "<br>"; } ?>
2.用 SAX 解析器读取 XML：
<?php $g_books = array(); $g_elem = null; function startElement( $parser, $name, $attrs ) { global $g_books, $g_elem; if ( $name == 'BOOK' ) $g_books []= array(); $g_elem = $name; } function endElement( $parser, $name ) { global $g_elem; $g_elem = null; } function textData( $parser, $text ) { global $g_books, $g_elem; if ( $g_elem == 'AUTHOR' || $g_elem == 'PUBLISHER' || $g_elem == 'TITLE' ) { $g_books[ count( $g_books ) - 1 ][ $g_elem ] = $text; } } $parser = xml_parser_create(); xml_set_element_handler( $parser, "startElement", "endElement" ); xml_set_character_data_handler( $parser, "textData" ); $f = fopen( 'books.xml', 'r' ); while( $data = fread( $f, 4096 ) ) { xml_parse( $parser, $data ); } xml_parser_free( $parser ); foreach( $g_books as $book ) { echo $book['TITLE']." - ".$book['AUTHOR']." - "; echo $book['PUBLISHER']."\n"; } ?>
3.用正则表达式解析 XML：
<?php $xml = ""; $f = fopen( 'books.xml', 'r' ); while( $data = fread( $f, 4096 ) ) { $xml .= $data; } fclose( $f ); preg_match_all( "/\<book\>(.*?)\<\/book\>/s", $xml, $bookblocks ); foreach( $bookblocks[1] as $block ) { preg_match_all( "/\<author\>(.*?)\<\/author\>/", $block, $author ); preg_match_all( "/\<title\>(.*?)\<\/title\>/", $block, $title ); preg_match_all( "/\<publisher\>(.*?)\<\/publisher\>/", $block, $publisher ); echo( $title[1][0]." - ".$author[1][0]." - ".$publisher[1][0]."\n" ); } ?>
4.解析XML到数组
<?php $data = "<root><line /><content language=\"gb2312\">简单的XML数据</content></root>"; $parser = xml_parser_create(); //创建解析器 xml_parse_into_struct($parser, $data, $values, $index); //解析到数组 xml_parser_free($parser); //释放资源 //显示数组结构 echo "\n索引数组\n"; print_r($index); echo "\n数据数组\n"; print_r($values); ?>
5.检查XML是否有效
<?php //创建XML解析器 $xml_parser = xml_parser_create(); //使用大小写折叠来保证能在元素数组中找到这些元素名称 xml_parser_set_option($xml_parser, XML_OPTION_CASE_FOLDING, true); //读取XML文件 $xmlfile = "bb.xml"; if (!($fp = fopen($xmlfile, "r"))) { die("无法读取XML文件$xmlfile"); } //解析XML文件 $has_error = false; //标志位 while ($data = fread($fp, 4096)) { //循环地读入XML文档，只到文档的EOF，同时停止解析 if (!xml_parse($xml_parser, $data, feof($fp))) { $has_error = true; break; } } if($has_error) { echo "该XML文档是错误的！<br />"; //输出错误行，列及其错误信息 $error_line = xml_get_current_line_number($xml_parser); $error_row = xml_get_current_column_number($xml_parser); $error_string = xml_error_string(xml_get_error_code($xml_parser)); $message = sprintf("［第%d行，%d列］：%s", $error_line, $error_row, $error_string); echo $message; } else { echo "该XML文档是结构良好的。"; } //关闭XML解析器指针，释放资源 xml_parser_free($xml_parser); ?>
6.可用于精确的读取XML
test.xml
<?xml version="1.0" encoding="UTF-8" ?> <SBMP_MO_MESSAGE> <CONNECT_ID>100</CONNECT_ID> <MO_MESSAGE_ID>123456</MO_MESSAGE_ID> <RECEIVE_DATE>20040605</RECEIVE_DATE> <RECEIVE_TIME>153020</RECEIVE_TIME> <GATEWAY_ID>1</GATEWAY_ID> <VALID>1</VALID> <CITY_CODE>010</CITY_CODE> <CITY_NAME>北京</CITY_NAME> <STATE_CODE>010</STATE_CODE> <STATE_NAME>北京</STATE_NAME> <TP_PID>0</TP_PID> <TP_UDHI>0</TP_UDHI> <MSISDN>15933626501</MSISDN> <MESSAGE_TYPE>8</MESSAGE_TYPE> <MESSAGE>5618常年供应苗木，品种有玉兰、黄叶杨等。联系人：张三，电话：1234567890。</MESSAGE> <LONG_CODE>100</LONG_CODE> <SERVICE_CODE>9588</SERVICE_CODE> </SBMP_MO_MESSAGE>
test.php: