62,614
社区成员
发帖
与我相关
我的任务
分享
package httpunit;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.net.MalformedURLException;
import java.util.List;
import com.gargoylesoftware.htmlunit.FailingHttpStatusCodeException;
import com.gargoylesoftware.htmlunit.NicelyResynchronizingAjaxController;
import com.gargoylesoftware.htmlunit.ScriptResult;
import com.gargoylesoftware.htmlunit.WebClient;
import com.gargoylesoftware.htmlunit.html.HtmlOption;
import com.gargoylesoftware.htmlunit.html.HtmlPage;
import com.gargoylesoftware.htmlunit.html.HtmlSelect;
public class WorldBankCrawl {
private static String TARGET_URL = "http://odds.500wan.com/fenxi/yazhi_same.php?cid=5&cp=平手/半球&id=384285&s1=0.800&s2=0.960";
public static void main(String[] args)
throws FailingHttpStatusCodeException, MalformedURLException,
IOException {
// 模拟一个浏览器
WebClient webClient = new WebClient();
// 设置webClient的相关参数
webClient.setJavaScriptEnabled(true);
webClient.setCssEnabled(false);
webClient.setAjaxController(new NicelyResynchronizingAjaxController());
webClient.setTimeout(35000);
webClient.setThrowExceptionOnScriptError(false);
// 模拟浏览器打开一个目标网址
HtmlPage rootPage = webClient.getPage(TARGET_URL);
rootPage.save(new File("/home/share/Test"));
}
}
将文件html存储在本地 然后在解析 就OK 了