java实现网页内容的抓取 java利用url实现网页内容的抓取

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.*;
/**
 * Created by chunmiao on 17-3-10.
 */
public class ReadBaiduSearch {
 //储存返回结果
 private LinkedHashMap<String,String> mapOfBaike;
 //获取搜索信息
 public LinkedHashMap<String,String> getInfomationOfBaike(String infomationWords) throws IOException {
  mapOfBaike = getResult(infomationWords);
  return mapOfBaike;
 }
 //通过网络链接获取信息
 private static LinkedHashMap<String, String> getResult(String keywords) throws IOException {
  //搜索的url
  String keyUrl = "http://baike.baidu.com/search?word=" + keywords;
  //搜索词条的节点
  String startNode = "<dl class=\"search-list\">";
  //词条的链接关键字
  String keyOfHref = "href=\"";
  //词条的标题关键字
  String keyOfTitle = "target=\"_blank\">";
  String endNode = "</dl>";
  boolean isNode = false;
  String title;
  String href;
  String rLine;
  LinkedHashMap<String,String> keyMap = new LinkedHashMap<String,String>();
  //开始网络请求
  URL url = new URL(keyUrl);
  HttpURLConnection urlConnection = (HttpURLConnection) url.openConnection();
  InputStreamReader inputStreamReader = new InputStreamReader(urlConnection.getInputStream(),"utf-8");
  BufferedReader bufferedReader = new BufferedReader(inputStreamReader);
  //读取网页内容
  while ((rLine = bufferedReader.readLine()) != null){
   //判断目标节点是否出现
   if(rLine.contains(startNode)){
    isNode = true;
   }
   //若目标节点出现，则开始抓取数据
   if (isNode){
    //若目标结束节点出现，则结束读取，节省读取时间
    if (rLine.contains(endNode)) {
     //关闭读取流
     bufferedReader.close();
     inputStreamReader.close();
     break;
    }
    //若值为空则不读取
    if (((title = getName(rLine,keyOfTitle)) != "") && ((href = getHref(rLine,keyOfHref)) != "")){
     keyMap.put(title,href);
    }
   }
  }
  return keyMap;
 }
 //获取词条对应的url
 private static String getHref(String rLine,String keyOfHref){
  String baikeUrl = "http://baike.baidu.com";
  String result = "";
  if(rLine.contains(keyOfHref)){
   //获取url
   for (int j = rLine.indexOf(keyOfHref) + keyOfHref.length();j < rLine.length()&&(rLine.charAt(j) != '\"');j ++){
    result += rLine.charAt(j);
   }
   //获取的url中可能不含baikeUrl,如果没有则在头部添加一个
   if(!result.contains(baikeUrl)){
    result = baikeUrl + result;
   }
  }
  return result;
 }
 //获取词条对应的名称
 private static String getName(String rLine,String keyOfTitle){
  String result = "";
  //获取标题内容
  if(rLine.contains(keyOfTitle)){
   result = rLine.substring(rLine.indexOf(keyOfTitle) + keyOfTitle.length(),rLine.length());
   //将标题中的内容含有的标签去掉
   result = result.replaceAll("<em>|</em>|</a>|<a>","");
  }
  return result;
 }
}