private Document doHttp(String url) throws IOException {

         //构造一个webClient 模拟Chrome 浏览器
        WebClient webClient = new WebClient(BrowserVersion.CHROME);
        //支持JavaScript
        webClient.getOptions().setJavaScriptEnabled(true);
        webClient.getOptions().setCssEnabled(false);
        webClient.getOptions().setActiveXNative(false);
        webClient.getOptions().setCssEnabled(false);
        webClient.getOptions().setThrowExceptionOnScriptError(false);
        webClient.getOptions().setThrowExceptionOnFailingStatusCode(false);
        webClient.getOptions().setTimeout(8000);
        HtmlPage rootPage = webClient.getPage(url);
        //设置一个运行JavaScript的时间
        webClient.waitForBackgroundJavaScript(6000);
        String html = rootPage.asXml();
        Document doc = Jsoup.parse(html);
        webClient.close();
        return doc;
    }

pom部分 

        <dependency>
            <groupId>org.jsoup</groupId>
            <artifactId>jsoup</artifactId>
            <version>1.11.3</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.47</version>
        </dependency>
        <dependency>
            <groupId>net.sourceforge.htmlunit</groupId>
            <artifactId>htmlunit</artifactId>
            <version>2.29</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.httpcomponents</groupId>
            <artifactId>httpclient</artifactId>
            <version>4.5.2</version>
        </dependency>
        <dependency>
            <groupId>xml-apis</groupId>
            <artifactId>xml-apis</artifactId>
            <version>1.4.01</version>
        </dependency>

        <dependency>
            <groupId>xerces</groupId>
            <artifactId>xercesImpl</artifactId>
            <version>2.11.0</version>
        </dependency>

 

参考文章：【Jsoup】配合 htmlunit 爬取异步加载的网页

导包报错处理

httpUnit模拟点击事件