private WebClient getAWebClient() {
WebClient webClient = new WebClient(BrowserVersion.FIREFOX_24);
webClient.getOptions().setTimeout(20000);
// webClient.getCookieManager().setCookiesEnabled(true);
webClient.getOptions().setThrowExceptionOnFailingStatusCode(false);
webClient.getOptions().setThrowExceptionOnScriptError(false);
webClient.getOptions().setCssEnabled(false);
webClient.getOptions().setJavaScriptEnabled(false);
webClient.addRequestHeader("Accept", "textml,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8");
webClient.addRequestHeader("Accept-Encoding", "gzip, deflate");
webClient.addRequestHeader("Accept-Language", "en-US,en;q=0.5");
webClient.addRequestHeader("Cache-Control", "max-age=0");
webClient.addRequestHeader("Connection", "keep-alive");
webClient.addRequestHeader("Host", "www.amazon.com");
webClient.addRequestHeader("User-Agent", "Mozilla/5.0 (X11; Linux x86_64; rv:24.0) Gecko/20100101 Firefox/24.0");
return webClient;
}
/**
* 采集网页
*/
public StringBuilder crawlPage(String url) {
StringBuilder builder = new StringBuilder();
logger.info(Thread.currentThread().getName() + " crawl " + url);
// mygetpage代码放在这里
webClient.getCookieManager().clearCookies();
logger.info(Thread.currentThread().getName() + " webClient.getCookieManager().clearCookies();");
File file = new File(cookiePathAppendRandom());
logger.info(Thread.currentThread().getName() + " File file = new File(cookiePathAppendRandom());");
if (file.exists()) {
FileInputStream fin = null;
try {
fin = new FileInputStream(file);
} catch (FileNotFoundException e1) {
e1.printStackTrace();
}
CookieStore cookieStore = null;
ObjectInputStream in;
try {
in = new ObjectInputStream(fin);
cookieStore = (CookieStore) in.readObject();
in.close();
} catch (IOException e) {
logger.error(e);
} catch (ClassNotFoundException e) {
logger.error(e);
}
List<org.apache.http.cookie.Cookie> l = cookieStore.getCookies();
for (org.apache.http.cookie.Cookie temp : l) {
Cookie cookie = new Cookie(temp.getDomain(), temp.getName(), temp.getValue(), temp.getPath(),
temp.getExpiryDate(), false);
webClient.getCookieManager().addCookie(cookie);
}
}
logger.info(Thread.currentThread().getName() + " MyGetPage start,url:" + url);
HtmlPage page = MyGetPage(new StringBuffer(url));
logger.info(Thread.currentThread().getName() + " MyGetPage end,url:" + url);
if (page == null) {
// 采集过程中出现异常的model,可以统一放在一个list中,发送给server重新加入到采集分配队列
logger.info("Page null!");
AmazonCrawlModel model=new AmazonCrawlModel(crawlId, crawlURLId, url, depth,ischange);
exceptionFun(model);
return (new StringBuilder("getNullPage"));
}
logger.info(Thread.currentThread().getName() + " builder.append(page.asXml());");
builder.append(page.asXml());
logger.info(Thread.currentThread().getName() + " return builder;");
logger.info(Thread.currentThread().getName() +" CrawlPage $Length="+builder.toString().length());
if(builder.toString().length()<=300){
AmazonCrawlModel model=new AmazonCrawlModel(crawlId, crawlURLId, url, depth,ischange);
exceptionFun(model);
return (new StringBuilder("getNullPage"));
}
return builder;
}
/***
* 自定义的getpage,遇到验证码页面识别直至成功
*
*/
private HtmlPage MyGetPage(StringBuffer URL) {
HtmlPage page = null;
boolean flag = true;
int TryTimeCnt = 1;
int UnknowHostTryTimeCnt = 1;
while (flag) {
flag = false;
try {
logger.info(Thread.currentThread().getName() + " webClient.getPage : " + URL + ",CrawlURL_id:"
+ crawlURLId);
page = webClient.getPage(URL.toString());
Document doc = Jsoup.parse(page.asXml());
int robotchecknum = 1;
while (doc.select("title").text().equals("Robot Check")) {
logger.info(Thread.currentThread().getName() + " " + dayformat1.format(System.currentTimeMillis())
+ " [Robot Check,URL:" + URL + "]");
String captcha_str = AmazonGetCaptcha.GetCaptcha(new StringBuilder(doc.toString()));
logger.info(Thread.currentThread().getName() + " " + dayformat1.format(System.currentTimeMillis())
+ " end AmazonGetCaptcha.GetCaptcha");
logger.info(dayformat1.format(new Date()) + " " + Thread.currentThread().getName() + " : "
+ captcha_str); HtmlForm form = null; logger.info(Thread.currentThread().getName() + " page.getForms().get(0) Start");
form = page.getForms().get(0);
logger.info(Thread.currentThread().getName() + " page.getForms().get(0) End"); HtmlButton button = null; logger.info(Thread.currentThread().getName() + " form.getElementsByTagName(button).get(0) Start");
button = (HtmlButton) form.getElementsByTagName("button").get(0);
logger.info(Thread.currentThread().getName() + " form.getElementsByTagName(button).get(0) End"); logger.info(Thread.currentThread().getName() + " setValueAttribute Start");
form.getInputByName("field-keywords").setValueAttribute(captcha_str);
logger.info(Thread.currentThread().getName() + " setValueAttribute End"); logger.info(Thread.currentThread().getName() + " button.click Start");
boolean click_flag = false;
while (!click_flag) {
try {
click_flag = true;
page = button.click();
} catch (Exception e1) {
logger.error(Thread.currentThread().getName() + " button.click出错了: " + e1);
//e1.printStackTrace();
click_flag = false;
}
}
logger.info(Thread.currentThread().getName() + " button.click end");
while (page.asXml() == null) {
logger.info(Thread.currentThread().getName() + " page xml null");
logger.info(Thread.currentThread().getName() +" "+ page.asXml());
page.refresh();
logger.info(Thread.currentThread().getName() + " refresh End!");
}
logger.info(Thread.currentThread().getName() + " button.click End"); logger.info(Thread.currentThread().getName() + " Start ParsePage!");
doc = Jsoup.parse(page.asXml());
if (!doc.select("title").text().equals("Robot Check")) {
logger.info(Thread.currentThread().getName() + " " + doc.select("title").text());
logger.info(Thread.currentThread().getName() + " "
+ dayformat1.format(System.currentTimeMillis()) + " [Robot Check,captcha success:"
+ captcha_str + ",try num:" + robotchecknum + "]");
}
robotchecknum++;
} } catch (FailingHttpStatusCodeException e) {
logger.error(Thread.currentThread().getName() +" "+ e);
flag = true;
} catch (MalformedURLException e) {
logger.error(Thread.currentThread().getName() +" "+ e);
flag = true;
}catch(UnknownHostException e) {
logger.error(Thread.currentThread().getName() +" "+ e);
flag = true;
logger.info("found UnknownHostException,start sleep 20 min");
try {
Thread.sleep(1000*60*Integer.parseInt(Configuration.getProperties("unknowhost_sleeptime")));
} catch (InterruptedException e1) {
logger.error(Thread.currentThread().getName() +" "+ e1);
}
logger.info("found UnknownHostException,end sleep 20 min");
UnknowHostTryTimeCnt++;// 访问异常数加一
logger.info(Thread.currentThread().getName() + " " + dayformat1.format(System.currentTimeMillis())
+ " [UnknowHostTryTimeCnt:" + UnknowHostTryTimeCnt + "]");
if (UnknowHostTryTimeCnt > Integer.parseInt(Configuration.getProperties("unknowhost_maxtrytime"))) {
return null;
}
}catch (Exception eq) {
logger.error(Thread.currentThread().getName() + " "+eq);
TryTimeCnt++;// 访问异常数加一
logger.info(Thread.currentThread().getName() + " " + dayformat1.format(System.currentTimeMillis())
+ " [TryTimeCnt:" + TryTimeCnt + "]");
if (TryTimeCnt > 5) {
return null;
}
try {
Thread.sleep(1000);
} catch (InterruptedException e) {
e.printStackTrace();
logger.error(Thread.currentThread().getName() + e);
}
flag = true;
}
try {
Thread.sleep(random.nextInt(500) + 1500);
} catch (InterruptedException e) {
logger.error(Thread.currentThread().getName() + e);
flag = true;
}
}
return page;
}

Java WebClient 总结的更多相关文章

  1. Spark案例分析

    一.需求:计算网页访问量前三名 import org.apache.spark.rdd.RDD import org.apache.spark.{SparkConf, SparkContext} /* ...

  2. C#调用JAVA接口WSSE方式用WebClient方式

    C#读取JAVA的WSSE接口的调用代码: 用webclient 方式: /// <summary> /// 调用java cxf ws_security加密的服务wcf客户端对应的加密类 ...

  3. websocket通信 实现java模拟一个client与webclient通信

    发文原由: 熟悉socket通信的同学,对于socket模拟server与client,实现相互通信, 或者使用websocket与java模拟的websocket服务器通信(比如一个聊天室),对于这 ...

  4. Java调用Http/Https接口(7,end)--WebClient调用Http/Https接口

    WebClient是Spring提供的非阻塞.响应式的Http客户端,提供同步及异步的API,将会代替RestTemplate及AsyncRestTemplate.文中所使用到的软件版本:Java 1 ...

  5. java.lang.UnsupportedClassVersionError: com/gargoylesoftware/htmlunit/WebClient : Unsupported major.minor version 52.0 (unable to load class com.gargoylesoftware.htmlunit.WebClient)

    java.lang.UnsupportedClassVersionError: com/gargoylesoftware/htmlunit/WebClient : Unsupported major. ...

  6. htmlunit学习之java.lang.NoSuchMethodError: com.gargoylesoftware.htmlunit.WebClient.getOptions()Lcom/gargoylesoftware/htmlunit/WebClientOptions;

    运行到这里就报错 java.lang.NoSuchMethodError: com.gargoylesoftware.htmlunit.WebClient.getOptions()Lcom/gargo ...

  7. webClient请求JAVA超时解决方案

    private class MyWebClient: WebClient { protected override WebRequest GetWebRequest(Uri uri) { WebReq ...

  8. C#、JAVA操作Hadoop(HDFS、Map/Reduce)真实过程概述。组件、源码下载。无法解决:Response status code does not indicate success: 500。

    一.Hadoop环境配置概述 三台虚拟机,操作系统为:Ubuntu 16.04. Hadoop版本:2.7.2 NameNode:192.168.72.132 DataNode:192.168.72. ...

  9. Atitit.http httpclient实践java c# .net php attilax总结

    Atitit.http httpclient实践java c# .net php attilax总结 1. Navtree>> net .http1 2. Httpclient理论1 2. ...

随机推荐

  1. Visual Studio CLR Profiler

    http://blogs.msdn.com/b/dotnet/archive/2013/04/04/net-memory-allocation-profiling-with-visual-studio ...

  2. FBX Transformation

    2010: http://download.autodesk.com/us/fbx/20102/FBX_SDK_Help/index.html?url=WS1a9193826455f5ff3913a1 ...

  3. Exercise16_22.java

    import javax.swing.*;import java.awt.*;import java.awt.event.*; public class Exercise16_22 extends J ...

  4. Servlet的配置

    让 Servlet 能响应用户请求,必须将 Servlet 配置在 Web 应用中. Servlet 3.0 中有两中配置方式:        1. 在 Servlet 类中使用 @WebServle ...

  5. 黄永成-thinkphp讲解-个人博客讲解26集

    如果是要导入 前后台分组都公用的 第三方类库, 就将类库(*.class.php文件) 放在 App下的Class文件夹中. 导入方法是: import('Class.Image', APP_PATH ...

  6. 关于PHP位运算的简单权限设计

    写在最前面 最近想写一个简单的关于权限处理的东西,之前我也了解过用二进制数的位运算可以出色地完成这个任务.关于二进制数 的位运算,常见的就是“或.与.非”这三种简单运算了,当然,我也查看了下PHP手册 ...

  7. PostgreSQL中的时间操作总结

    取当前日期的函数: (1)       取当前时间:select now() (2)       取当前时间的日期: select current_date (3)       取当前具体时间(不含日 ...

  8. js中的换算小技巧

    之前自己一直使用~~运算符来把‘112222’字符型的数值换算成整型的数值 但今天调试程序发现了一些问题 ~~'999'=>999 ~~'111111999'=>111111999 这些都 ...

  9. H5移动端知识点总结

    H5移动端知识点总结 阅读目录 移动开发基本知识点 calc基本用法 box-sizing的理解及使用 理解display:box的布局 理解flex布局 Flex布局兼容知识点总结 回到顶部 移动开 ...

  10. Form表单中method为get和post的区别

    序,form表单中的方法分为get和post,但你都知道他们之间的区别吗? Form表单中method为get和post的区别: 例子如下,有个Form表单. <form action=&quo ...