htmlunit模拟登录

PS:我只用到了这一句

webClient.getOptions().setThrowExceptionOnScriptError(false);

htmlunit jar项目路径http://sourceforge.net/projects/htmlunit/files/htmlunit/

demo代码如下

public class AutoLogin {

/** 登录页面 */

private static final String LOGIN_URL = "http://website/login.aspx";

/** 任务列表页面 */

private static final String TASK_LIST_URL = "http://website/Banli.aspx";

/**

* @param args

* @throws Exception

public static void main(String[] args) throws Exception {

testHomePage();

}

public static void testHomePage() throws Exception {

final WebClient webClient = new WebClient(BrowserVersion.INTERNET_EXPLORER_8);

webClient.getOptions().setThrowExceptionOnScriptError(false); //此行必须要加

webClient.getOptions().setCssEnabled(false);

// webClient.getOptions().setJavaScriptEnabled(true);

// webClient.getOptions().setThrowExceptionOnFailingStatusCode(false);

webClient.getOptions().setTimeout(300000);

// 获取首页

HtmlPage page = (HtmlPage) webClient.getPage(LOGIN_URL);

// 根据form的名字获取页面表单，也可以通过索引来获取：page.getForms().get(0)

final HtmlForm form = page.getFormByName("form1");

// 用户名/密码

HtmlTextInput textUserName = form.getInputByName("txtUserName");

textUserName.setText("username");

HtmlPasswordInput txtPwd = form.getInputByName("txtPwd");

txtPwd.setText("pass");

//调用JS触发登录按钮

Page page1 = page.executeJavaScript("$('#btn').click()").getNewPage();

page1 = webClient.getPage(TASK_LIST_URL);

System.out.println("*************************************************************************************");

System.out.println(page1.getWebResponse().getContentAsString());

System.out.println("*************************************************************************************");

System.out.println("");

System.out.println("Cookies : " + webClient.getCookieManager().getCookies().toString());

}

搞不清ASP.NET内部什么逻辑，试了很多方法都不行，查看了无所网站，无意中看到一个这个配置http://stackoverflow.com/questions/20352284/scraping-aspx-page-using-htmlunit

import java.net.MalformedURLException;

import com.gargoylesoftware.htmlunit.BrowserVersion;

import com.gargoylesoftware.htmlunit.FailingHttpStatusCodeException;

import com.gargoylesoftware.htmlunit.WebClient;

import com.gargoylesoftware.htmlunit.html.HtmlElement;

import com.gargoylesoftware.htmlunit.html.HtmlPage;

public class teste {

public static void main(String args[]) throws FailingHttpStatusCodeException, MalformedURLException, IOException

{

HtmlPage page = null;

String url = "http://www.bmfbovespa.com.br/cias-listadas/empresas-listadas/BuscaEmpresaListada.aspx?Idioma=pt-br";

WebClient webClient = new WebClient(BrowserVersion.FIREFOX_17);

webClient.getOptions().setThrowExceptionOnScriptError(false);

webClient.getOptions().setCssEnabled(false);

webClient.getOptions().setJavaScriptEnabled(false);

webClient.getOptions().setThrowExceptionOnFailingStatusCode(false);

webClient.getOptions().setTimeout(30000);

page = webClient.getPage( url );

System.out.println("Current page: Empresas Listadas | BM&FBOVESPA");

HtmlElement theElement1 = (HtmlElement) page.getElementById("ctl00_contentPlaceHolderConteudo_BuscaNomeEmpresa1_btnTodas");

page = theElement1.click();

System.out.println(page.asText());

System.out.println("Test has completed successfully");

}

最后测试下来，如果不加 webClient.getOptions().setThrowExceptionOnScriptError(false);就一直报这个错误

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

Exception in thread "main" ======= EXCEPTION START ========

Exception class=[java.lang.RuntimeException]

com.gargoylesoftware.htmlunit.ScriptException: Exception invoking click

at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$HtmlUnitContextAction.run(JavaScriptEngine.java:954)

at net.sourceforge.htmlunit.corejs.javascript.Context.call(Context.java:628)

at net.sourceforge.htmlunit.corejs.javascript.ContextFactory.call(ContextFactory.java:513)

at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.execute(JavaScriptEngine.java:836)

at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.execute(JavaScriptEngine.java:812)

at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.execute(JavaScriptEngine.java:800)

at com.gargoylesoftware.htmlunit.html.HtmlPage.executeJavaScriptIfPossible(HtmlPage.java:910)

at com.gargoylesoftware.htmlunit.html.HtmlPage.executeJavaScript(HtmlPage.java:878)

at com.suypower.AutoLogin12345.testHomePage(AutoLogin12345.java:48)

at com.suypower.AutoLogin12345.main(AutoLogin12345.java:23)

Caused by: java.lang.RuntimeException: Exception invoking click

at net.sourceforge.htmlunit.corejs.javascript.MemberBox.invoke(MemberBox.java:181)

at net.sourceforge.htmlunit.corejs.javascript.FunctionObject.call(FunctionObject.java:449)

at net.sourceforge.htmlunit.corejs.javascript.Interpreter.interpretLoop(Interpreter.java:1536)

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:3286)

at net.sourceforge.htmlunit.corejs.javascript.InterpretedFunction.exec(InterpretedFunction.java:115)

at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$3.doRun(JavaScriptEngine.java:827)

at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$HtmlUnitContextAction.run(JavaScriptEngine.java:939)

... 9 more

Caused by: com.gargoylesoftware.htmlunit.ScriptException: TypeError: Cannot read property "nodeName" from null (http://xxxx/305000772#7)

at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$HtmlUnitContextAction.run(JavaScriptEngine.java:954)

at net.sourceforge.htmlunit.corejs.javascript.Context.call(Context.java:628)

at net.sourceforge.htmlunit.corejs.javascript.ContextFactory.call(ContextFactory.java:513)

at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.execute(JavaScriptEngine.java:836)

at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.execute(JavaScriptEngine.java:812)

at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.execute(JavaScriptEngine.java:800)

at com.gargoylesoftware.htmlunit.html.HtmlPage.executeJavaScriptIfPossible(HtmlPage.java:910)

at com.gargoylesoftware.htmlunit.html.HtmlScript.executeInlineScriptIfNeeded(HtmlScript.java:354)

at com.gargoylesoftware.htmlunit.html.HtmlScript.executeScriptIfNeeded(HtmlScript.java:415)

at com.gargoylesoftware.htmlunit.html.HtmlScript$3.execute(HtmlScript.java:271)

at com.gargoylesoftware.htmlunit.html.HtmlScript.onAllChildrenAddedToPage(HtmlScript.java:293)

at com.gargoylesoftware.htmlunit.html.HTMLParser$HtmlUnitDOMBuilder.endElement(HTMLParser.java:799)

at org.apache.xerces.parsers.AbstractSAXParser.endElement(Unknown Source)

at com.gargoylesoftware.htmlunit.html.HTMLParser$HtmlUnitDOMBuilder.endElement(HTMLParser.java:756)

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:1039)

at com.gargoylesoftware.htmlunit.html.HTMLParser.parse(HTMLParser.java:252)

at com.gargoylesoftware.htmlunit.html.HTMLParser.parseHtml(HTMLParser.java:198)

at com.gargoylesoftware.htmlunit.DefaultPageCreator.createHtmlPage(DefaultPageCreator.java:271)

at com.gargoylesoftware.htmlunit.DefaultPageCreator.createPage(DefaultPageCreator.java:159)

at com.gargoylesoftware.htmlunit.WebClient.loadWebResponseInto(WebClient.java:478)

at com.gargoylesoftware.htmlunit.WebClient.getPage(WebClient.java:352)

at com.gargoylesoftware.htmlunit.html.BaseFrameElement.loadInnerPageIfPossible(BaseFrameElement.java:183)

at com.gargoylesoftware.htmlunit.html.BaseFrameElement.loadInnerPage(BaseFrameElement.java:121)

at com.gargoylesoftware.htmlunit.html.HtmlPage.loadFrames(HtmlPage.java:1893)

at com.gargoylesoftware.htmlunit.html.HtmlPage.initialize(HtmlPage.java:227)

at com.gargoylesoftware.htmlunit.WebClient.loadWebResponseInto(WebClient.java:485)

at com.gargoylesoftware.htmlunit.WebClient.loadDownloadedResponses(WebClient.java:2135)

at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.doProcessPostponedActions(JavaScriptEngine.java:982)

at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.processPostponedActions(JavaScriptEngine.java:1072)

at com.gargoylesoftware.htmlunit.html.DomElement.click(DomElement.java:789)

at com.gargoylesoftware.htmlunit.html.HtmlImageInput.click(HtmlImageInput.java:152)

at com.gargoylesoftware.htmlunit.javascript.host.html.HTMLInputElement.click(HTMLInputElement.java:477)

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)

... 19 more

Caused by: net.sourceforge.htmlunit.corejs.javascript.EcmaError: TypeError: Cannot read property "nodeName" from null (http://xxxx/305000772#7)

at net.sourceforge.htmlunit.corejs.javascript.ScriptRuntime.constructError(ScriptRuntime.java:3935)

at net.sourceforge.htmlunit.corejs.javascript.ScriptRuntime.constructError(ScriptRuntime.java:3919)

at net.sourceforge.htmlunit.corejs.javascript.ScriptRuntime.typeError(ScriptRuntime.java:3944)

at net.sourceforge.htmlunit.corejs.javascript.ScriptRuntime.typeError2(ScriptRuntime.java:3960)

at net.sourceforge.htmlunit.corejs.javascript.ScriptRuntime.undefReadError(ScriptRuntime.java:3971)

at net.sourceforge.htmlunit.corejs.javascript.ScriptRuntime.getObjectProp(ScriptRuntime.java:1519)

at net.sourceforge.htmlunit.corejs.javascript.Interpreter.interpretLoop(Interpreter.java:1243)

at net.sourceforge.htmlunit.corejs.javascript.Interpreter.interpret(Interpreter.java:798)

at net.sourceforge.htmlunit.corejs.javascript.InterpretedFunction.exec(InterpretedFunction.java:118)

at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$3.doRun(JavaScriptEngine.java:827)

at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$HtmlUnitContextAction.run(JavaScriptEngine.java:939)

... 65 more

Enclosed exception:

java.lang.RuntimeException: Exception invoking click