3

我需要解析一个 xml 文件以显示基于键值的属性。例如,在下面的文件中,我想为每个会话提取 realTimeIid 和电子邮件,但是我很难让我的代码工作,因为每个 varValue 有多个具有相同属性的元素。

<?xml version="1.0" encoding="UTF-8" ?> 
<Report account="7869" start_time="2012-02-23T00:00:00+00:00" end_time="2012-02-23T15:27:59+00:00" user="twilson" more_sessions="false">
 <Session id="ID742247692" realTimeID="4306650378">
  <VarValues>
   <varValue id="ID2051978" source="PreChat" sourceName="null" time="2012-02-23T00:07:07+00:00" name="identifier">Andy</varValue> 
   <varValue id="ID2051979" source="Internal" sourceName="null" time="2012-02-23T01:09:42+00:00" name="DisconnectedBy">VisitorClosedWindow</varValue> 
   <varValue id="ID2055925" source="PostChat" sourceName="null" time="2012-02-23T01:09:53+00:00" name="send_transcript">yes</varValue> 
   <varValue id="ID2055926" source="Operator" sourceName="null" time="2012-02-23T01:13:17+00:00" name="email">address1@myexample.com</varValue> 
   <varValue id="ID2073144" source="PreChat" sourceName="null" time="2012-02-23T00:07:07+00:00" name="survey0373014">a group, team or business</varValue> 
   <varValue id="ID2074007" source="Operator" sourceName="null" time="2012-02-23T01:13:17+00:00" name="survey99630314">Pricing</varValue> 
   <varValue id="ID2075240" source="Operator" sourceName="null" time="2012-02-23T01:13:17+00:00" name="survey99630317">No</varValue> 
   <varValue id="ID2075243" source="Operator" sourceName="null" time="2012-02-23T01:13:17+00:00" name="survey99630320">Dont Know</varValue> 
   <varValue id="ID2083900" source="PostChat" sourceName="null" time="2012-02-23T01:09:53+00:00" name="survey99630223">none of the above</varValue> 
   <varValue id="ID2119346" source="Internal" sourceName="null" time="2012-02-23T00:06:20+00:00" name="LP_Visitor_Category">0</varValue> 
   <varValue id="ID2329945" source="PreChat" sourceName="null" time="2012-02-23T00:07:07+00:00" name="survey23360124">55379</varValue> 
  </VarValues>
 </Session>
 <Session id="ID742247695" realTimeID="4306650379">
  <VarValues>
   <varValue id="ID2051978" source="PreChat" sourceName="null" time="2012-02-23T00:04:37+00:00" name="identifier">Aram</varValue> 
   <varValue id="ID2051979" source="Internal" sourceName="null" time="2012-02-23T00:26:39+00:00" name="DisconnectedBy">RepStoppedChat</varValue> 
   <varValue id="ID2055926" source="Operator" sourceName="null" time="2012-02-23T00:46:39+00:00" name="email">address2@myexample.com</varValue> 
   <varValue id="ID2073144" source="PreChat" sourceName="null" time="2012-02-23T00:04:37+00:00" name="survey0373014">a group, team or business</varValue> 
   <varValue id="ID2074007" source="Operator" sourceName="null" time="2012-02-23T00:46:39+00:00" name="survey99630314">Turn Time</varValue> 
   <varValue id="ID2075240" source="Operator" sourceName="null" time="2012-02-23T00:46:39+00:00" name="survey99630317">No</varValue> 
   <varValue id="ID2075243" source="Operator" sourceName="null" time="2012-02-23T00:46:39+00:00" name="survey99630320">Likely</varValue> 
   <varValue id="ID2119346" source="Internal" sourceName="null" time="2012-02-23T00:04:23+00:00" name="LP_Visitor_Category">0</varValue> 
   <varValue id="ID2329945" source="PreChat" sourceName="null" time="2012-02-23T00:04:37+00:00" name="survey23360124">07452</varValue> 
  </VarValues>
 </Session>
</Report>

这是我使用 DOMDocument 的代码。我想要的结果应该返回两行,如下所示。

Sessionid|email
4306650378 address1@myexample.com
4306650379 address2@myexample.com

我只想要电子邮件地址,而不是 varValue->getAttribute('name') 下的所有其他元素和属性。问题在于它返回所有属性,我不知道如何仅查找电子邮件并获取后续值。

  $doc = new DOMDocument();
  $doc->load( 'C:/Dev/report.xml' );

  $sessions = $doc->getElementsByTagName( "Session" );
  foreach( $sessions as $session )
  {

  $sessionid = $session->getAttribute( 'realTimeID' );

  $values = $session->getElementsByTagName( "VarValues" );
  foreach( $values as $value)

  {   

  $varValues = $value->getElementsByTagName( "varValue" );
  foreach( $varValues as $other )

  {

  $email = $other->getAttribute('name');

  echo "$sessionid- $email\n"; 
  }}}
4

2 回答 2

2

我一直发现SimpleXML非常易于使用:

<?php

$xml_string = <<<XML
<?xml version="1.0" encoding="UTF-8" ?> 
<Report account="7869" start_time="2012-02-23T00:00:00+00:00" end_time="2012-02-23T15:27:59+00:00" user="twilson" more_sessions="false">
 <Session id="ID742247692" realTimeID="4306650378">
  <VarValues>
   <varValue id="ID2051978" source="PreChat" sourceName="null" time="2012-02-23T00:07:07+00:00" name="identifier">Andy</varValue> 
   <varValue id="ID2051979" source="Internal" sourceName="null" time="2012-02-23T01:09:42+00:00" name="DisconnectedBy">VisitorClosedWindow</varValue> 
   <varValue id="ID2055925" source="PostChat" sourceName="null" time="2012-02-23T01:09:53+00:00" name="send_transcript">yes</varValue> 
   <varValue id="ID2055926" source="Operator" sourceName="null" time="2012-02-23T01:13:17+00:00" name="email">address1@myexample.com</varValue> 
   <varValue id="ID2073144" source="PreChat" sourceName="null" time="2012-02-23T00:07:07+00:00" name="survey0373014">a group, team or business</varValue> 
   <varValue id="ID2074007" source="Operator" sourceName="null" time="2012-02-23T01:13:17+00:00" name="survey99630314">Pricing</varValue> 
   <varValue id="ID2075240" source="Operator" sourceName="null" time="2012-02-23T01:13:17+00:00" name="survey99630317">No</varValue> 
   <varValue id="ID2075243" source="Operator" sourceName="null" time="2012-02-23T01:13:17+00:00" name="survey99630320">Dont Know</varValue> 
   <varValue id="ID2083900" source="PostChat" sourceName="null" time="2012-02-23T01:09:53+00:00" name="survey99630223">none of the above</varValue> 
   <varValue id="ID2119346" source="Internal" sourceName="null" time="2012-02-23T00:06:20+00:00" name="LP_Visitor_Category">0</varValue> 
   <varValue id="ID2329945" source="PreChat" sourceName="null" time="2012-02-23T00:07:07+00:00" name="survey23360124">55379</varValue> 
  </VarValues>
 </Session>
 <Session id="ID742247695" realTimeID="4306650379">
  <VarValues>
   <varValue id="ID2051978" source="PreChat" sourceName="null" time="2012-02-23T00:04:37+00:00" name="identifier">Aram</varValue> 
   <varValue id="ID2051979" source="Internal" sourceName="null" time="2012-02-23T00:26:39+00:00" name="DisconnectedBy">RepStoppedChat</varValue> 
   <varValue id="ID2055926" source="Operator" sourceName="null" time="2012-02-23T00:46:39+00:00" name="email">address2@myexample.com</varValue> 
   <varValue id="ID2073144" source="PreChat" sourceName="null" time="2012-02-23T00:04:37+00:00" name="survey0373014">a group, team or business</varValue> 
   <varValue id="ID2074007" source="Operator" sourceName="null" time="2012-02-23T00:46:39+00:00" name="survey99630314">Turn Time</varValue> 
   <varValue id="ID2075240" source="Operator" sourceName="null" time="2012-02-23T00:46:39+00:00" name="survey99630317">No</varValue> 
   <varValue id="ID2075243" source="Operator" sourceName="null" time="2012-02-23T00:46:39+00:00" name="survey99630320">Likely</varValue> 
   <varValue id="ID2119346" source="Internal" sourceName="null" time="2012-02-23T00:04:23+00:00" name="LP_Visitor_Category">0</varValue> 
   <varValue id="ID2329945" source="PreChat" sourceName="null" time="2012-02-23T00:04:37+00:00" name="survey23360124">07452</varValue> 
  </VarValues>
 </Session>
</Report>
XML;

$xml_object = simplexml_load_string($xml_string);

foreach($xml_object->Session as $session) {
    $sessionid = $session['realTimeID'];
    foreach($session->VarValues->varValue as $varValue) {
        if($varValue['name'] == 'email') {
            $email = (string) $varValue;
            echo $sessionid.'- '.$email."\n";
            break;
        }
    }
}

?>
于 2012-05-24T18:42:53.417 回答
0

使用 xpath 可能是一个更简单的解决方案。例如,请参阅下面的此链接

点击这里

谢谢。

于 2012-05-24T18:35:04.250 回答