<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<extendedinfo type="html">
<![CDATA[<table class="ResultTable" cellpadding=2 cellspacing=1 border=0><tr class="TableHeadingLine"><th bgcolor="#b3b3b3" align="left" colspan="6"><font face="arial, verdana, trebuchet, officina, sans-serif" size="+2"><B>Testcase: Init Testreport</B></font></th></tr><tr class="TableHeadingLine"><th class="TableHeadingCell" width="120px"></th><th class="TableHeadingCell" width="120px"></th><th class="TableHeadingCell" width="80px"></th><th class="TableHeadingCell" width="345px"></th><th class="TableHeadingCell" width="345px"></th><th class="TableHeadingCell" width="70px"></th></tr>]]>
</extendedinfo>
<extendedinfo type="html">
<![CDATA[<tr><td class="DefineCell">58.675124</td><td class="DefaultCell" colspan="5"><i><font color="#008000">Set_Temperature is set to 23</font></i><br>Set_Temperature = 23</td></tr>]]>
</extendedinfo>
我有一个由上述格式的工具生成的.XML文件,其中包含CDATA部分中的html数据。哪个解析器或以何种方式可以使用java从XML文件中检索html数据?
答案 0 :(得分:1)
只需将CDATA作为文字内容访问
import java.io.BufferedInputStream;
import java.io.FileInputStream;
import java.io.InputStream;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
public void getCDATAFromHardcodedPathWithDom() {
String yourSampleFile = "/path/toYour/sample/file.xml";
String cdataNode = "extendedinfo";
try (InputStream in =
new BufferedInputStream(new FileInputStream(yourSampleFile))) {
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
DocumentBuilder builder = factory.newDocumentBuilder();
Document doc = builder.parse(in);
NodeList elements = doc.getElementsByTagName(cdataNode);
for (int i = 0; i < elements.getLength(); i++) {
Node e = elements.item(i);
System.out.println(e.getTextContent());
}
} catch (Exception e) {
throw new RuntimeException(e);
}
}
import java.io.BufferedInputStream;
import java.io.FileInputStream;
import java.io.InputStream;
import javax.xml.stream.XMLInputFactory;
import javax.xml.stream.XMLStreamConstants;
import javax.xml.stream.XMLStreamReader;
public void getCDATAFromHardcodedPathWithStax() {
String yourSampleFile = "/path/toYour/sample/file.xml";
String cdataNode = "extendedinfo";
XMLStreamReader r = null;
try (InputStream in =
new BufferedInputStream(new FileInputStream(yourSampleFile));) {
XMLInputFactory factory = XMLInputFactory.newInstance();
r = factory.createXMLStreamReader(in);
while (r.hasNext()) {
switch (r.getEventType()) {
case XMLStreamConstants.START_ELEMENT:
if (cdataNode.equals(r.getName().getLocalPart())) {
System.out.println(r.getElementText());
}
break;
default:
break;
}
r.next();
}
} catch (Exception e) {
throw new RuntimeException(e);
} finally {
if (r != null) {
try {
r.close();
} catch (Exception e) {
throw new RuntimeException(e);
}
}
}
}
使用/path/toYour/sample/file.xml
<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<root>
<extendedinfo type="html">
<![CDATA[<table class="ResultTable" cellpadding=2 cellspacing=1 border=0><tr class="TableHeadingLine"><th bgcolor="#b3b3b3" align="left" colspan="6"><font face="arial, verdana, trebuchet, officina, sans-serif" size="+2"><B>Testcase: Init Testreport</B></font></th></tr><tr class="TableHeadingLine"><th class="TableHeadingCell" width="120px"></th><th class="TableHeadingCell" width="120px"></th><th class="TableHeadingCell" width="80px"></th><th class="TableHeadingCell" width="345px"></th><th class="TableHeadingCell" width="345px"></th><th class="TableHeadingCell" width="70px"></th></tr>]]>
</extendedinfo>
<extendedinfo type="html">
<![CDATA[<tr><td class="DefineCell">58.675124</td><td class="DefaultCell" colspan="5"><i><font color="#008000">Set_Temperature is set to 23</font></i><br>Set_Temperature = 23</td></tr>]]>
</extendedinfo>
</root>
它会给你
<table class="ResultTable" cellpadding=2 cellspacing=1 border=0><tr class="TableHeadingLine"><th bgcolor="#b3b3b3" align="left" colspan="6"><font face="arial, verdana, trebuchet, officina, sans-serif" size="+2"><B>Testcase: Init Testreport</B></font></th></tr><tr class="TableHeadingLine"><th class="TableHeadingCell" width="120px"></th><th class="TableHeadingCell" width="120px"></th><th class="TableHeadingCell" width="80px"></th><th class="TableHeadingCell" width="345px"></th><th class="TableHeadingCell" width="345px"></th><th class="TableHeadingCell" width="70px"></th></tr>
<tr><td class="DefineCell">58.675124</td><td class="DefaultCell" colspan="5"><i><font color="#008000">Set_Temperature is set to 23</font></i><br>Set_Temperature = 23</td></tr>
这里给出了一个使用JAXB的有趣替代方案:
这里给出了一个关于如何提取所有CDATA的示例: