java爬虫
模拟登陆CSDN
- 抓包得到post请求的5个参数:
username:139******[email protected]
password:*******()
lt:LT-243423-zaxybu6QLbPZfJSXCBOfBkstaiCKml
execution:e3s1
_eventId:submit
Cookie：uuid_tt_dd=5955540397292079753_20170815; UM_distinctid=15e" +
"502c8a4d5b5-0ebe367e3c65d5-e313761-e1000-15e502c8a4eaa4; __utma=17226283.1282527090.15082" +
"48516.1508248516.1508248516.1; __utmz=17226283.1508248516.1.1.utmcsr=(direct)|utmccn=(direct)" +
"|utmcmd=(none); __message_sys_msg_id=0; __message_gu_msg_id=0; __message_cnel_msg_id=0; __message_district_code=420000; __message_in_school=0; UN=qq_37976565; UE="[email protected]"; BT=1508662667082; JSESSIONID=C2ED5A9B0A01ADD063B0219B5A4953F1.tomcat2; LSSC=LSSC-513836-NbJPY2BrWFZud9WPdsjOlzU2RyQrOe-passport.csdn.net; dc_tos=oy82pe; dc_session_id=1508499845140_0.037202" +
"744870221016; Hm_lvt_6bcd52f51e9b3dce32bec4a3997715ac=1508593384,1508659648,1508659652,1508671911" +
";"+
Hm_lpvt_6bcd52f51e9b3dce32bec4a3997715ac=1508671925"
步骤
- 1.首先发送一个get请求得到登陆页面及后3个请求参数
- 2.发送post请求登陆到请求地址
- 3.分析post得到的结果判断是否登陆成功
用到的API
- HttpClient
- Jsoup
sendGet函数
public static String sendGet(String url){
HttpResponse response;
String content=null;
try {
HttpGet get=new HttpGet(url);
response=httpClient.execute(get);
HttpEntity entity=response.getEntity();
content= EntityUtils.toString(entity);//用content辅助分析
EntityUtils.consume(entity);
return content;
}
catch (Exception e) {
e.printStackTrace();
}
return content;
}
sendPost函数
public static String sendPost(String url, List nvps){
HttpResponse response;
String content=null; //为了结果分析
try {
//HttpClient中的Post请求包装类
HttpPost post=new HttpPost(url);
//nvps是包装请求参数的list
if (nvps!=null){
post.setEntity(new UrlEncodedFormEntity(nvps,"UTF-8"));
}
//执行请求用execution方法
response=httpClient.execute(post);
HttpEntity entity=response.getEntity();
content=EntityUtils.toString(entity);
EntityUtils.consume(entity);
return content;
}catch (Exception e){
e.printStackTrace();
}
return content;
}
setPost()函数
HttpResponse response;
String content=null;
try {
HttpPost post=new HttpPost(url);
if (nvps!=null){
post.setEntity(new UrlEncodedFormEntity(nvps,"UTF-8"));
post.setHeader("Cookie","uuid_tt_dd=5955540397292079753_20170815; UM_distinctid=15e" +
"502c8a4d5b5-0ebe367e3c65d5-e313761-e1000-15e502c8a4eaa4; __utma=17226283.1282527090.15082" +
"48516.1508248516.1508248516.1; __utmz=17226283.1508248516.1.1.utmcsr=(direct)|utmccn=(direct)" +
"|utmcmd=(none); __message_sys_msg_id=0; __message_gu_msg_id=0; __message_cnel_msg_id=0; __message_district_code=420000; __message_in_school=0; UN=qq_37976565; UE=\"[email protected]\"; BT=1508662667082; JSESSIONID=C2ED5A9B0A01ADD063B0219B5A4953F1.tomcat2; LSSC=LSSC-513836-NbJPY2BrWFZud9WPdsjOlzU2RyQrOe-passport.csdn.net; dc_tos=oy82pe; dc_session_id=1508499845140_0.037202" +
"744870221016; Hm_lvt_6bcd52f51e9b3dce32bec4a3997715ac=1508593384,1508659648,1508659652,1508671911" +
"; Hm_lpvt_6bcd52f51e9b3dce32bec4a3997715ac=1508671925");
}
response=httpClient.execute(post);
HttpEntity entity=response.getEntity();
content=EntityUtils.toString(entity);
EntityUtils.consume(entity);
if (content.indexOf("redirect_back")>-1){
System.out.println("登陆成功....");
// result=true;
}
else if(content.indexOf("登陆太频繁")>-1){
System.out.println("登陆太频繁");
}else {
System.out.println("登陆失败");
}
HttpGet get=new HttpGet("http://ask.csdn.net/");//验证Cookie是否设置成功
String c = setCookie(response);
//将cookie注入到get请求头当中
get.setHeader("Cookie",c);
HttpResponse r = httpClient.execute(get);
String content1 = EntityUtils.toString(r.getEntity());
return content1;
}catch (Exception e){
e.printStackTrace();
}
return content;
}
主函数Main()
public class Main {
private static String Login_url="HTTPS://passport.csdn.net/account/login";
// private static String Login_url="://www.zhihu.com/login/phone_num";
public static void main(String[] args)throws Exception {
// write your code here
Logger logger=Logger.getLogger("cyc");
String username=" ";//账号
String password=" ";//密码
// String captcha_type;
//String _xsrf;
String it=null;
String execution=null;
String _eventId=null;
logger.info("获取必要的登陆信息.....");
String html= Zhihu.sendGet(Login_url);
Document doc= Jsoup.parse(html);
Element from=doc.select(".user-pass").get(0);
System.out.println(html);
it=from.select("input[name=lt]").get(0).val();
execution=from.select("input[name=execution]").get(0).val();
_eventId=from.select("input[name=_eventId]").get(0).val();
//_xsrf=from.select("input[name=_xsrf]").get(0).val();
//captcha_type=from.select("input[name=captcha_type]").get(0).val();
System.out.println(it);
System.out.println(execution);
System.out.println(_eventId);
// System.out.println(captcha_type);
// System.out.println(_xsrf);
System.out.println("");
logger.info("获取成功.....");
logger.info("开始登录.....");
// boolean result=false;
List nvps=new ArrayList();
nvps.add(new BasicNameValuePair("username",username));
nvps.add(new BasicNameValuePair("password",password));
nvps.add(new BasicNameValuePair("lt",it));
nvps.add(new BasicNameValuePair("execution",execution));
nvps.add(new BasicNameValuePair("_eventId",_eventId));
String ret=Zhihu.sendPost(Login_url,nvps);
System.out.println(ret);
}
}
登陆成功的结果打印
登陆
编程技术问答-CSDN问答频道
········
/现在要去取消关注
do_unfollow_url = 'http://my.csdn.net/index.php/follow/do_unfollow?username='+now_item_name+'&jsonpcallback=?';
$.ajax({
type: "get",
url: do_unfollow_url,
dataType:"jsonp",
success: function(data){
if(parseInt(data.succ)==1)
{
$(item).removeClass('focus_cancel');
//$(item).html(''+''+' 关注');
//$(item).removeAttr("style");
//$(item)[0].onmouseover = null;
//$(item)[0].onmouseout = null;
}
btn_state=1;
}
});
}
}
}
});
}
else
{
$(item)[0].onclick = function(){
window.location.href="https://passport.csdn.net/";
}
}
});
}
showConcern();