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 {
 //儲存返回結果
 private LinkedHashMap<String,String> mapOfBaike;
 //獲取搜索信息
 public LinkedHashMap<String,String> getInfomationOfBaike(String infomationWords) throws IOException {
  mapOfBaike = getResult(infomationWords);
  return mapOfBaike;
 }
 //通過網絡鏈接獲取信息
 private static LinkedHashMap<String, String> getResult(String keywords) throws IOException {
  //搜索的url
  String keyUrl = "http://baike.baidu.com/search&#63;word=" + keywords;
  //搜索詞條的節點
  String startNode = "<dl class=\"search-list\">";
  //詞條的鏈接關鍵字
  String keyOfHref = "href=\"";
  //詞條的標題關鍵字
  String keyOfTitle = "target=\"_blank\">";
  String endNode = "</dl>";
  boolean isNode = false;
  String title;
  String href;
  String rLine;
  LinkedHashMap<String,String> keyMap = new LinkedHashMap<String,String>();
  //開始網絡請求
  URL url = new URL(keyUrl);
  HttpURLConnection urlConnection = (HttpURLConnection) url.openConnection();
  InputStreamReader inputStreamReader = new InputStreamReader(urlConnection.getInputStream(),"utf-8");
  BufferedReader bufferedReader = new BufferedReader(inputStreamReader);
  //讀取網頁內容
  while ((rLine = bufferedReader.readLine()) != null){
   //判斷目標節點是否出現
   if(rLine.contains(startNode)){
    isNode = true;
   }
   //若目標節點出現，則開始抓取數據
   if (isNode){
    //若目標結束節點出現，則結束讀取，節省讀取時間
    if (rLine.contains(endNode)) {
     //關閉讀取流
     bufferedReader.close();
     inputStreamReader.close();
     break;
    }
    //若值為空則不讀取
    if (((title = getName(rLine,keyOfTitle)) != "") && ((href = getHref(rLine,keyOfHref)) != "")){
     keyMap.put(title,href);
    }
   }
  }
  return keyMap;
 }
 //獲取詞條對應的url
 private static String getHref(String rLine,String keyOfHref){
  String baikeUrl = "http://baike.baidu.com";
  String result = "";
  if(rLine.contains(keyOfHref)){
   //獲取url
   for (int j = rLine.indexOf(keyOfHref) + keyOfHref.length();j < rLine.length()&&(rLine.charAt(j) != '\"');j ++){
    result += rLine.charAt(j);
   }
   //獲取的url中可能不含baikeUrl,如果沒有則在頭部添加一個
   if(!result.contains(baikeUrl)){
    result = baikeUrl + result;
   }
  }
  return result;
 }
 //獲取詞條對應的名稱
 private static String getName(String rLine,String keyOfTitle){
  String result = "";
  //獲取標題內容
  if(rLine.contains(keyOfTitle)){
   result = rLine.substring(rLine.indexOf(keyOfTitle) + keyOfTitle.length(),rLine.length());
   //將標題中的內容含有的標簽去掉
   result = result.replaceAll("<em>|</em>|</a>|<a>","");
  }
  return result;
 }
}