package action;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.LinkedHashMap;
import java.util.Map;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class WebCrawlerDemo {
 public static void main(String[] args) {
    WebCrawlerDemo webCrawlerDemo = new WebCrawlerDemo();
    webCrawlerDemo.myPrint("http://www.zifangsky.cn");
  }
 
  public void myPrint(String baseUrl) {
    Map<String, Boolean> oldMap = new LinkedHashMap<String, Boolean>(); // 存儲鏈接-是否被遍歷
                                      // 鍵值對
    String oldLinkHost = ""; //host
 
    Pattern p = Pattern.compile("(https?://)?[^/\\s]*"); //比如：http://www.zifangsky.cn
    Matcher m = p.matcher(baseUrl);
    if (m.find()) {
      oldLinkHost = m.group();
    }
 
    oldMap.put(baseUrl, false);
    oldMap = crawlLinks(oldLinkHost, oldMap);
    for (Map.Entry<String, Boolean> mapping : oldMap.entrySet()) {
      System.out.println("鏈接：" + mapping.getKey());
 
    }
 
  }
 
  /**
   * 抓取一個(gè)網(wǎng)站所有可以抓取的網(wǎng)頁鏈接，在思路上使用了廣度優(yōu)先算法
   * 對未遍歷過的新鏈接不斷發(fā)起GET請求，一直到遍歷完整個(gè)集合都沒能發(fā)現(xiàn)新的鏈接
   * 則表示不能發(fā)現(xiàn)新的鏈接了，任務(wù)結(jié)束
   * 
   * @param oldLinkHost 域名，如：http://www.zifangsky.cn
   * @param oldMap 待遍歷的鏈接集合
   * 
   * @return 返回所有抓取到的鏈接集合
   * */
  private Map<String, Boolean> crawlLinks(String oldLinkHost,
      Map<String, Boolean> oldMap) {
    Map<String, Boolean> newMap = new LinkedHashMap<String, Boolean>();
    String oldLink = "";
 
    for (Map.Entry<String, Boolean> mapping : oldMap.entrySet()) {
      System.out.println("link:" + mapping.getKey() + "--------check:"
          + mapping.getValue());
      // 如果沒有被遍歷過
      if (!mapping.getValue()) {
        oldLink = mapping.getKey();
        // 發(fā)起GET請求
        try {
          URL url = new URL(oldLink);
          HttpURLConnection connection = (HttpURLConnection) url
              .openConnection();
          connection.setRequestMethod("GET");
          connection.setConnectTimeout(2000);
          connection.setReadTimeout(2000);
 
          if (connection.getResponseCode() == 200) {
            InputStream inputStream = connection.getInputStream();
            BufferedReader reader = new BufferedReader(
                new InputStreamReader(inputStream, "UTF-8"));
            String line = "";
            Pattern pattern = Pattern
                .compile("<a.*?href=[\"']?((https?://)?/?[^\"']+)[\"']?.*?>(.+)</a>");
            Matcher matcher = null;
            while ((line = reader.readLine()) != null) {
              matcher = pattern.matcher(line);
              if (matcher.find()) {
                String newLink = matcher.group(1).trim(); // 鏈接
                // String title = matcher.group(3).trim(); //標(biāo)題
                // 判斷獲取到的鏈接是否以http開頭
                if (!newLink.startsWith("http")) {
                  if (newLink.startsWith("/"))
                    newLink = oldLinkHost + newLink;
                  else
                    newLink = oldLinkHost + "/" + newLink;
                }
                //去除鏈接末尾的 /
                if(newLink.endsWith("/"))
                  newLink = newLink.substring(0, newLink.length() - 1);
                //去重，并且丟棄其他網(wǎng)站的鏈接
                if (!oldMap.containsKey(newLink)
                    && !newMap.containsKey(newLink)
                    && newLink.startsWith(oldLinkHost)) {
                  // System.out.println("temp2: " + newLink);
                  newMap.put(newLink, false);
                }
              }
            }
          }
        } catch (MalformedURLException e) {
          e.printStackTrace();
        } catch (IOException e) {
          e.printStackTrace();
        }
 
        try {
          Thread.sleep(1000);
        } catch (InterruptedException e) {
          e.printStackTrace();
        }
        oldMap.replace(oldLink, false, true);
      }
    }
    //有新鏈接，繼續(xù)遍歷
    if (!newMap.isEmpty()) {
      oldMap.putAll(newMap);
      oldMap.putAll(crawlLinks(oldLinkHost, oldMap)); //由于Map的特性，不會導(dǎo)致出現(xiàn)重復(fù)的鍵值對
    }
    return oldMap;
  }
}