HtmlUnit解析document时js不能拿到body对象问题解决
login.html
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=GBK" />
</head>
<script>
function getContent(){
var url= "result.html";
var xhr=new (window.XMLHttpRequest||window.ActiveXObject)("Microsoft.XMLHTTP");
xhr.onreadystatechange = function() {
if (xhr.readyState == 4 && xhr.status == 200) {
document.write(xhr.responseText);
document.close();
}
};
xhr.open("GET",url,false); xhr.send();
}
getContent();
</script>
</html>
result.html
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=GBK"/>
<title>login</title>
</head>
<body>
<script type="text/javascript">
var d = document, b = d.body;
var n = d.createElement("div");
n.innerHTML = "<div> I was appended... </div>";
b.appendChild(n);
</script>
</body>
</html>
Test.java
@Test public void testExecScript() throws Exception {
WebClient client = new WebClient(BrowserVersion.CHROME);
client.getOptions().setUseInsecureSSL(true);
client.getOptions().setJavaScriptEnabled(true);
client.getOptions().setCssEnabled(false);
client.getOptions().setThrowExceptionOnScriptError(false);
client.getOptions().setTimeout(10000);
String url = "http://localhost/login.html";
HtmlPage loginPage = client.getPage(url);
logger.info("{}\n{}", loginPage.getTitleText(), loginPage.asXml());
}
error output:
EcmaError: lineNumber=[1] column=[0] lineSource=[<no source>] name=[TypeError] sourceName=[script in http://localhost/login.html from (1, 1462) to (1, 1780)] message=[TypeError: Cannot call method "appendChild" of null (script in login.html from (1, 1462) to (1, 1780)#1)]com.gargoylesoftware.htmlunit.ScriptException: TypeError: Cannot call method "appendChild" of null (script in login.html from (1, 1462) to (1, 1780)#1)at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$HtmlUnitContextAction.run(JavaScriptEngine.java:847)at net.sourceforge.htmlunit.corejs.javascript.Context.call(Context.java:620)at net.sourceforge.htmlunit.corejs.javascript.ContextFactory.call(ContextFactory.java:513)at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.execute(JavaScriptEngine.java:733)at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.execute(JavaScriptEngine.java:708)at com.gargoylesoftware.htmlunit.html.HtmlPage.executeJavaScriptIfPossible(HtmlPage.java:982)at com.gargoylesoftware.htmlunit.html.HtmlScript.executeInlineScriptIfNeeded(HtmlScript.java:351)at com.gargoylesoftware.htmlunit.html.HtmlScript.executeScriptIfNeeded(HtmlScript.java:411)at com.gargoylesoftware.htmlunit.html.HtmlScript$3.execute(HtmlScript.java:276)at com.gargoylesoftware.htmlunit.html.HtmlScript.onAllChildrenAddedToPage(HtmlScript.java:290)at com.gargoylesoftware.htmlunit.html.HTMLParser$HtmlUnitDOMBuilder.endElement(HTMLParser.java:793)at org.apache.xerces.parsers.AbstractSAXParser.endElement(Unknown Source)at com.gargoylesoftware.htmlunit.html.HTMLParser$HtmlUnitDOMBuilder.endElement(HTMLParser.java:751)at org.cyberneko.html.HTMLTagBalancer.callEndElement(HTMLTagBalancer.java:1170)at org.cyberneko.html.HTMLTagBalancer.endElement(HTMLTagBalancer.java:1072)at org.cyberneko.html.filters.DefaultFilter.endElement(DefaultFilter.java:206)at org.cyberneko.html.filters.NamespaceBinder.endElement(NamespaceBinder.java:330)at org.cyberneko.html.HTMLScanner$ContentScanner.scanEndElement(HTMLScanner.java:3126)at org.cyberneko.html.HTMLScanner$ContentScanner.scan(HTMLScanner.java:2093)at org.cyberneko.html.HTMLScanner.evaluateInputSource(HTMLScanner.java:608)at org.cyberneko.html.HTMLConfiguration.evaluateInputSource(HTMLConfiguration.java:342)at com.gargoylesoftware.htmlunit.html.HTMLParser$HtmlUnitDOMBuilder.pushInputString(HTMLParser.java:420)at com.gargoylesoftware.htmlunit.html.HtmlPage.writeInParsedStream(HtmlPage.java:2375)at com.gargoylesoftware.htmlunit.javascript.host.html.HTMLDocument.write(HTMLDocument.java:683)at com.gargoylesoftware.htmlunit.javascript.host.html.HTMLDocument.write(HTMLDocument.java:569)at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)at java.lang.reflect.Method.invoke(Method.java:606)at net.sourceforge.htmlunit.corejs.javascript.MemberBox.invoke(MemberBox.java:153)at net.sourceforge.htmlunit.corejs.javascript.FunctionObject.call(FunctionObject.java:384)at net.sourceforge.htmlunit.corejs.javascript.Interpreter.interpretLoop(Interpreter.java:1531)at net.sourceforge.htmlunit.corejs.javascript.Interpreter.interpret(Interpreter.java:798)at net.sourceforge.htmlunit.corejs.javascript.InterpretedFunction.call(InterpretedFunction.java:105)at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$4.doRun(JavaScriptEngine.java:772)at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$HtmlUnitContextAction.run(JavaScriptEngine.java:832)at net.sourceforge.htmlunit.corejs.javascript.Context.call(Context.java:620)at net.sourceforge.htmlunit.corejs.javascript.ContextFactory.call(ContextFactory.java:513)at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.callFunction(JavaScriptEngine.java:779)at com.gargoylesoftware.htmlunit.javascript.host.xml.XMLHttpRequest.setState(XMLHttpRequest.java:218)at com.gargoylesoftware.htmlunit.javascript.host.xml.XMLHttpRequest.doSend(XMLHttpRequest.java:762)at com.gargoylesoftware.htmlunit.javascript.host.xml.XMLHttpRequest.send(XMLHttpRequest.java:598)at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)at java.lang.reflect.Method.invoke(Method.java:606)at net.sourceforge.htmlunit.corejs.javascript.MemberBox.invoke(MemberBox.java:153)at net.sourceforge.htmlunit.corejs.javascript.FunctionObject.call(FunctionObject.java:448)at net.sourceforge.htmlunit.corejs.javascript.Interpreter.interpretLoop(Interpreter.java:1531)at net.sourceforge.htmlunit.corejs.javascript.Interpreter.interpret(Interpreter.java:798)at net.sourceforge.htmlunit.corejs.javascript.InterpretedFunction.call(InterpretedFunction.java:105)at net.sourceforge.htmlunit.corejs.javascript.ContextFactory.doTopCall(ContextFactory.java:411)at com.gargoylesoftware.htmlunit.javascript.HtmlUnitContextFactory.doTopCall(HtmlUnitContextFactory.java:309)at net.sourceforge.htmlunit.corejs.javascript.ScriptRuntime.doTopCall(ScriptRuntime.java:3057)at net.sourceforge.htmlunit.corejs.javascript.InterpretedFunction.exec(InterpretedFunction.java:115)at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$3.doRun(JavaScriptEngine.java:724)at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$HtmlUnitContextAction.run(JavaScriptEngine.java:832)at net.sourceforge.htmlunit.corejs.javascript.Context.call(Context.java:620)at net.sourceforge.htmlunit.corejs.javascript.ContextFactory.call(ContextFactory.java:513)at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.execute(JavaScriptEngine.java:733)at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.execute(JavaScriptEngine.java:708)at com.gargoylesoftware.htmlunit.html.HtmlPage.executeJavaScriptIfPossible(HtmlPage.java:982)at com.gargoylesoftware.htmlunit.html.HtmlScript.executeInlineScriptIfNeeded(HtmlScript.java:351)at com.gargoylesoftware.htmlunit.html.HtmlScript.executeScriptIfNeeded(HtmlScript.java:411)at com.gargoylesoftware.htmlunit.html.HtmlScript$3.execute(HtmlScript.java:276)at com.gargoylesoftware.htmlunit.html.HtmlScript.onAllChildrenAddedToPage(HtmlScript.java:290)at com.gargoylesoftware.htmlunit.html.HTMLParser$HtmlUnitDOMBuilder.endElement(HTMLParser.java:793)at org.apache.xerces.parsers.AbstractSAXParser.endElement(Unknown Source)at com.gargoylesoftware.htmlunit.html.HTMLParser$HtmlUnitDOMBuilder.endElement(HTMLParser.java:751)at org.cyberneko.html.HTMLTagBalancer.callEndElement(HTMLTagBalancer.java:1170)at org.cyberneko.html.HTMLTagBalancer.endElement(HTMLTagBalancer.java:1072)at org.cyberneko.html.filters.DefaultFilter.endElement(DefaultFilter.java:206)at org.cyberneko.html.filters.NamespaceBinder.endElement(NamespaceBinder.java:330)at org.cyberneko.html.HTMLScanner$ContentScanner.scanEndElement(HTMLScanner.java:3126)at org.cyberneko.html.HTMLScanner$ContentScanner.scan(HTMLScanner.java:2093)at org.cyberneko.html.HTMLScanner.scanDocument(HTMLScanner.java:920)at org.cyberneko.html.HTMLConfiguration.parse(HTMLConfiguration.java:499)at org.cyberneko.html.HTMLConfiguration.parse(HTMLConfiguration.java:452)at org.apache.xerces.parsers.XMLParser.parse(Unknown Source)at com.gargoylesoftware.htmlunit.html.HTMLParser$HtmlUnitDOMBuilder.parse(HTMLParser.java:1017)at com.gargoylesoftware.htmlunit.html.HTMLParser.parse(HTMLParser.java:248)at com.gargoylesoftware.htmlunit.html.HTMLParser.parseHtml(HTMLParser.java:194)at com.gargoylesoftware.htmlunit.DefaultPageCreator.createHtmlPage(DefaultPageCreator.java:268)at com.gargoylesoftware.htmlunit.DefaultPageCreator.createPage(DefaultPageCreator.java:156)at com.gargoylesoftware.htmlunit.WebClient.loadWebResponseInto(WebClient.java:471)at com.gargoylesoftware.htmlunit.WebClient.getPage(WebClient.java:345)at com.gargoylesoftware.htmlunit.WebClient.getPage(WebClient.java:410)at com.gargoylesoftware.htmlunit.WebClient.getPage(WebClient.java:395)at com.aduan.study.test.web.crawler.HtmlUnitTest.testExecScript(HtmlUnitTest.java:186)at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)at java.lang.reflect.Method.invoke(Method.java:606)at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:47)at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:44)at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:271)at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:70)at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:50)at org.junit.runners.ParentRunner$3.run(ParentRunner.java:238)at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:63)at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:236)at org.junit.runners.ParentRunner.access$000(ParentRunner.java:53)at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:229)at org.junit.runners.ParentRunner.run(ParentRunner.java:309)at org.junit.runner.JUnitCore.run(JUnitCore.java:160)at com.intellij.junit4.JUnit4IdeaTestRunner.startRunnerWithArgs(JUnit4IdeaTestRunner.java:78)at com.intellij.rt.execution.junit.JUnitStarter.prepareStreamsAndStart(JUnitStarter.java:212)at com.intellij.rt.execution.junit.JUnitStarter.main(JUnitStarter.java:68)at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)at java.lang.reflect.Method.invoke(Method.java:606)at com.intellij.rt.execution.application.AppMain.main(AppMain.java:140)
解决方法1：
删掉result.html的head
<head> <meta http-equiv="Content-Type" content="text/html; charset=GBK"/> <title>login</title> </head>
或login.html添加body
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=GBK" /> </head><body><script>function getContent(){
var url= "result.html";
var xhr=new (window.XMLHttpRequest||window.ActiveXObject)("Microsoft.XMLHTTP");
xhr.onreadystatechange = function() {
if (xhr.readyState == 4 && xhr.status == 200) {
document.write(xhr.responseText);
document.close();
}
};
xhr.open("GET",url,false); xhr.send(); }getContent(); </script>
</head>
<body>
</body>
</html>
result.html javascript add
d.write("d:" + d + "<br/>");d.write("b:" + b + "<br/>");
ouput:
d:[object HTMLDocument]<br/>b:[object HTMLBodyElement]<br/><div> <div> I was appended... </div></div>
解决方法2：webclient处理返回信息，加上body
client.setWebConnection(
new WebConnectionWrapper(client) {
public WebResponse getResponse(WebRequest request) throws IOException {
WebResponse response = super.getResponse(request);
String content = response.getContentAsString("UTF-8");
if(content != null) {
if(!content.contains("<body>") && content.contains("</head>")) {
content = content.replace("</head>", "</head>\n<body>");
if(!content.contains("</body>") && content.contains("</html>")) {
content = content.replace("</html>", "</body>\n</html>");
}
}
}
logger.info("response: {}", content);
WebResponseData data = new WebResponseData(content.getBytes("UTF-8"),
response.getStatusCode(), response.getStatusMessage(), response.getResponseHeaders());
response = new WebResponse(data, request, response.getLoadTime());
return response;
}
});