详解Java实现多种方式的http数据抓取

前言：

时下互联网第一波的浪潮已消逝，随着而来的基于万千数据的物联网时代，因而数据成为企业的重要战略资源之一。基于数据抓取技术，本文介绍了java相关抓取工具，并附上demo源码供感兴趣的朋友测试！

1）jdk自带http连接，获取页面或json

 

2） jdk自带url连接，获取页面或json

 

3）httpclient get工具，获取页面或json

 

 4）commons-io工具，获取页面或json

 

5） jsoup工具（通常用于html字段解析），获取页面,非json返回格式】

 

--------------------------------------------------------------------------------

完整代码：

package com.yeezhao.common.http;

import java.io.bufferedreader;
import java.io.inputstream;
import java.io.inputstreamreader;
import java.net.httpurlconnection;
import java.net.url;

import org.apache.commons.httpclient.httpclient;
import org.apache.commons.httpclient.httpmethod;
import org.apache.commons.httpclient.methods.getmethod;
import org.apache.commons.io.ioutils;
import org.jsoup.jsoup;

/**
 * http工具对比
 * 
 * @author administrator -> junhong
 *
 *     2016年12月27日
 */
public class httpfetchutil {
  
  /**
   * 获取访问的状态码
   * @param request
   * @return
   * @throws exception
   */
  public static int getresponsecode(string request) throws exception {
    url url = new url(request);
    httpurlconnection conn = (httpurlconnection) url.openconnection();
    return conn.getresponsecode();

  }
  /**
   * 1）jdk自带http连接，获取页面或json
   * @param request
   * @param charset
   * @return
   * @throws exception
   */
  public static string jdkfetch(string request, string charset) throws exception {
    url url = new url(request);
    httpurlconnection conn = (httpurlconnection) url.openconnection();
    //模拟浏览器参数
    conn.setrequestproperty("user-agent", "mozilla/5.0 (windows nt 6.1; wow64) applewebkit/537.36"
        + " (khtml, like gecko) chrome/45.0.2454.101 safari/537.36");
    if (conn.getresponsecode() == httpurlconnection.http_ok) {
      inputstream input = conn.getinputstream();
      stringbuffer sb = new stringbuffer();
      bufferedreader reader = new bufferedreader(new inputstreamreader(input, charset));
      string s;
      while ((s = reader.readline()) != null) {
        sb.append(s + "\n");
      }
      input.close();
      conn.disconnect();
      return sb.tostring();
    }
    return "";
  }
  /**
   * 2） jdk自带url连接，获取页面或json
   * @param request
   * @param charset
   * @return
   * @throws exception
   */
  public static string urlfetch(string request, string charset) throws exception {
    url url = new url(request);
    return ioutils.tostring(url.openstream());
  }

  /**
   * 3）httpclient get工具，获取页面或json
   * @param url
   * @param charset
   * @return
   * @throws exception
   */
  public static string httpclientfetch(string url, string charset) throws exception {
    // get
    httpclient httpclient = new httpclient();
    httpclient.getparams().setcontentcharset(charset);
    httpmethod method = new getmethod(url);
    httpclient.executemethod(method);
    return method.getresponsebodyasstring();
  }
  /**
   * 4）commons-io工具，获取页面或json
   * @param url
   * @param charset
   * @return
   * @throws exception
   */
  public static string commonsiofetch(string url, string charset) throws exception {
    return ioutils.tostring(new url(url), charset);
  }
  
  /**
   * 5） jsoup工具（通常用于html字段解析），获取页面,非json返回格式
   * @param url
   * @return
   * @throws exception
   */
  public static string jsoupfetch(string url) throws exception {
    return jsoup.parse(new url(url), 2 * 1000).html();
  }

}

测试代码：

package com.yeezhao.common.http;

import org.junit.after;
import org.junit.before;
import org.junit.test;
/**
 * 测试类
 * 3个测试链接：
 * 1）百科网页
 * 2）浏览器模拟获取接口数据
 * 3）获取普通接口数据
 * @author administrator -> junhong
 *
 * 2016年12月27日
 */
public class httpfetchutiltest {
  string seeds[] = {"http://baike.baidu.com/view/1.htm","http://m.ximalaya.com/tracks/26096131.json","http://remyapi.yeezhao.com/api/query?wd=%e5%91%a8%e6%98%9f%e9%a9%b0%e7%9a%84%e7%94%b5%e5%bd%b1"};
  final static string default_charset = "utf-8";
  @before
  public void setup() throws exception {
  }

  @after
  public void teardown() throws exception {
    system.out.println("--- down ---");
  }

  @test
  public void testgetresponsecode() throws exception{
    for(string seed:seeds){
      int responsecode = httpfetchutil.getresponsecode(seed);
      system.out.println("ret="+responsecode);
    }
  }

  @test
  public void testjdkfetch() throws exception{
    for(string seed:seeds){
      string ret = httpfetchutil.jdkfetch(seed, default_charset);
      system.out.println("ret="+ret);
    }
  }

  @test
  public void testurlfetch() throws exception{
    for(string seed:seeds){
      string ret = httpfetchutil.urlfetch(seed, default_charset);
      system.out.println("ret="+ret);
    }
  }

  @test
  public void testhttpclientfetch()throws exception {
    for(string seed:seeds){
      string ret = httpfetchutil.httpclientfetch(seed, default_charset);
      system.out.println("ret="+ret);
    }
  }

  @test
  public void testcommonsiofetch()throws exception {
    for(string seed:seeds){
      string ret = httpfetchutil.commonsiofetch(seed, default_charset);
      system.out.println("ret="+ret);
    }
  }

  @test
  public void testjsoupfetch() throws exception{
    for(string seed:seeds){
      string ret = httpfetchutil.jsoupfetch(seed);
      system.out.println("ret="+ret);
    }
  }

}

附：相关jar依赖

...
<dependency>
<groupid>org.jsoup</groupid>
<artifactid>jsoup</artifactid>
<version>1.7.3</version>
</dependency>

<dependency>
<groupid>commons-httpclient</groupid>
<artifactid>commons-httpclient</artifactid>
<version>3.1</version>
</dependency>

<dependency>
<groupid>commons-io</groupid>
<artifactid>commons-io</artifactid>
<version>2.4</version>
</dependency>
...

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。