PHP读取XML

books.xml文件：

<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

 1 <?php
 2 $doc = new DOMDocument();
 3 $doc->load( 'books.xml' );
 4 $books = $doc->getElementsByTagName( "book" );
 5 foreach( $books as $book )
 6 {
 7 $authors = $book->getElementsByTagName( "author" );
 8 $author = $authors->item(0)->nodeValue;
 9 
10 $publishers = $book->getElementsByTagName( "publisher" );
11 $publisher = $publishers->item(0)->nodeValue;
12 
13 $titles = $book->getElementsByTagName( "title" );
14 $title = $titles->item(0)->nodeValue;
15 
16 echo "$title - $author - $publisher
";
17 echo "<br>";
18 }
19 ?> 

2.用 SAX 解析器读取 XML

 1 <?php
 2 $g_books = array();
 3 $g_elem = null;
 4 
 5 function startElement( $parser, $name, $attrs ) 
 6 {
 7 global $g_books, $g_elem;
 8 if ( $name == 'BOOK' ) $g_books []= array();
 9 $g_elem = $name;
10 }
11 
12 function endElement( $parser, $name ) 
13 {
14 global $g_elem;
15 $g_elem = null;
16 }
17 
18 function textData( $parser, $text )
19 {
20 global $g_books, $g_elem;
21 if ( $g_elem == 'AUTHOR' ||
22 $g_elem == 'PUBLISHER' ||
23 $g_elem == 'TITLE' )
24 {
25 $g_books[ count( $g_books ) - 1 ][ $g_elem ] = $text;
26 }
27 }
28 
29 $parser = xml_parser_create();
30 
31 xml_set_element_handler( $parser, "startElement", "endElement" );
32 xml_set_character_data_handler( $parser, "textData" );
33 
34 $f = fopen( 'books.xml', 'r' );
35 
36 while( $data = fread( $f, 4096 ) )
37 {
38 xml_parse( $parser, $data );
39 }
40 
41 xml_parser_free( $parser );
42 
43 foreach( $g_books as $book )
44 {
45 echo $book['TITLE']." - ".$book['AUTHOR']." - ";
46 echo $book['PUBLISHER']."
";
47 }
48 ?>

3.用正则表达式解析 XML

 1 <?php
 2 $xml = "";
 3 $f = fopen( 'books.xml', 'r' );
 4 while( $data = fread( $f, 4096 ) ) {
 5     $xml .= $data; 
 6 }
 7 fclose( $f );
 8 
 9 preg_match_all( "/<book>(.*?)</book>/s", $xml, $bookblocks );
10 
11 foreach( $bookblocks[1] as $block )
12 {
13 preg_match_all( "/<author>(.*?)</author>/", $block, $author );
14 preg_match_all( "/<title>(.*?)</title>/",   $block, $title );
15 preg_match_all( "/<publisher>(.*?)</publisher>/", $block, $publisher );
16 echo( $title[1][0]." - ".$author[1][0]." - ".$publisher[1][0]."
" );
17 }
18 ?>

4.解析XML到数 组

 1 <?php
 2     $data = "<root><line /><content language="gb2312">简单的XML数据</content></root>";
 3     $parser = xml_parser_create();                        //创建解析器
 4     xml_parse_into_struct($parser, $data, $values, $index);    //解析到数组
 5     xml_parser_free($parser);                            //释放资源
 6     
 7     //显示数组结构
 8     echo "
索引数组
";
 9     print_r($index);
10     echo "
数据数组
";
11     print_r($values);
12 ?>

5.检查XML是否有效

 1 <?php
 2     //创建XML解析器
 3     $xml_parser = xml_parser_create();
 4 
 5     //使用大小写折叠来保证能在元素数组中找到这些元素名称
 6     xml_parser_set_option($xml_parser, XML_OPTION_CASE_FOLDING, true);
 7 
 8     //读取XML文件
 9     $xmlfile = "bb.xml";
10     if (!($fp = fopen($xmlfile, "r")))
11     {
12         die("无法读取XML文件$xmlfile");
13     }
14 
15     //解析XML文件
16     $has_error = false;            //标志位
17     while ($data = fread($fp, 4096))
18     {
19         //循环地读入XML文档，只到文档的EOF，同时停止解析
20         if (!xml_parse($xml_parser, $data, feof($fp)))
21         {
22             $has_error = true;
23             break;
24         }
25     }
26 
27     if($has_error)
28     { 
29         echo "该XML文档是错误的！<br />";
30 
31         //输出错误行，列及其错误信息
32         $error_line   = xml_get_current_line_number($xml_parser);
33         $error_row   = xml_get_current_column_number($xml_parser);
34         $error_string = xml_error_string(xml_get_error_code($xml_parser));
35 
36         $message = sprintf("［第%d行，%d列］：%s", 
37                         $error_line,
38                         $error_row,
39                         $error_string);
40         echo $message;
41     }
42     else
43     {
44         echo "该XML文档是结构良好的。";
45     }
46     
47     //关闭XML解析器指针，释放资源
48     xml_parser_free($xml_parser);
49 ?>

6.可用于精确的读取XML
test.xml

 1 <?xml version="1.0" encoding="UTF-8" ?>
 2     <SBMP_MO_MESSAGE>
 3         <CONNECT_ID>100</CONNECT_ID>
 4         <MO_MESSAGE_ID>123456</MO_MESSAGE_ID>
 5         <RECEIVE_DATE>20040605</RECEIVE_DATE>
 6         <RECEIVE_TIME>153020</RECEIVE_TIME>
 7         <GATEWAY_ID>1</GATEWAY_ID>
 8         <VALID>1</VALID>
 9         <CITY_CODE>010</CITY_CODE>
10         <CITY_NAME>北京</CITY_NAME>
11         <STATE_CODE>010</STATE_CODE>
12         <STATE_NAME>北京</STATE_NAME>
13         <TP_PID>0</TP_PID>
14         <TP_UDHI>0</TP_UDHI>
15         <MSISDN>15933626501</MSISDN>
16         <MESSAGE_TYPE>8</MESSAGE_TYPE>
17         <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>
18         <LONG_CODE>100</LONG_CODE>
19         <SERVICE_CODE>9588</SERVICE_CODE>
20     </SBMP_MO_MESSAGE>
21 test.php:
22 <?php
23 $myData = array();
24 $file = file_get_contents("test.xml");
25 if(strpos($file, '<?xml') > -1) {
26         try {
27             //加载解析xml
28             $xml = simplexml_load_string($file);
29             if($xml) {
30                 //echo $this->result;
31                 //获取节点值
32                 $CONNECT_ID = $xml->CONNECT_ID;
33                 $MO_MESSAGE_ID = $xml->MO_MESSAGE_ID;
34                 $RECEIVE_DATE = $xml->RECEIVE_DATE;
35                 $RECEIVE_TIME = $xml->RECEIVE_TIME;
36                 $GATEWAY_ID = $xml->GATEWAY_ID;
37                 $VALID = $xml->VALID;
38                 $CITY_CODE = $xml->CITY_CODE;
39                 $CITY_NAME = $xml->CITY_NAME;
40                 $STATE_CODE = $xml->CITY_CODE;
41                 $STATE_NAME = $xml->STATE_NAME;
42                 $TP_PID = $xml->TP_PID;
43                 $TP_UDHI = $xml->TP_UDHI;
44                 $MSISDN = $xml->MSISDN;
45                 $MESSAGE_TYPE = $xml->MESSAGE_TYPE;
46                 $MESSAGE = $xml->MESSAGE;//短信
47                 $LONG_CODE = $xml->LONG_CODE;
48                 $SERVICE_CODE = $xml->SERVICE_CODE;
49                 preg_match("/(561)d{1,2}/", $MESSAGE, $code);
50                 switch($code[0]) {
51                     case 5618 :
52                         $myData[message] = $MESSAGE;
53                         break;
54                     default :
55                         $myData[] = '没有短消息。';
56                         break;
57                     }
58                     
59                 } else {
60                     echo "加载xml文件错误。";
61                 }
62             
63         } catch(exception $e){
64             print_r($e);
65         }
66 
67 } else {
68     echo "没有该XML文件。";
69 }
70 
71 echo "<pre>";
72 print_r($myData);
73 echo "<hr>";
74 echo $myData[message];
75 ?>