程序師世界是廣大編程愛好者互助、分享、學習的平台,程序師世界有你更精彩!
首頁
編程語言
C語言|JAVA編程
Python編程
網頁編程
ASP編程|PHP編程
JSP編程
數據庫知識
MYSQL數據庫|SqlServer數據庫
Oracle數據庫|DB2數據庫
 程式師世界 >> 編程語言 >> JAVA編程 >> 關於JAVA >> Java准確抽取網頁宣布時光

Java准確抽取網頁宣布時光

編輯:關於JAVA

Java准確抽取網頁宣布時光。本站提示廣大學習愛好者:(Java准確抽取網頁宣布時光)文章只能為提供參考,不一定能成為您想要的結果。以下是Java准確抽取網頁宣布時光正文


對網頁中各類分歧格局的宣布時光停止抽取,將宣布時光以規整的“yyyy-MM-dd HH:mm:ss”格局表現出來,只能盡可能尋求准確,然則由於收集宣布時光的格局非常靈巧,所以做不到百分百地准確抽取

package whu.extract.pubtime.core;
 
import java.util.ArrayList;
import java.util.Calendar;
import java.util.Collections;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
 
import whu.utils.TimeUtil;
 
/**
 * Created On 2014年3月13日 下晝2:49:05
 * @description 獲得網頁的宣布時光 
 */
public class FetchPubTime {
  /** 表現url中持續的8位日期,例如http://www.百度.com/20140311/2356.html */
  private static String url_reg_whole= "([-|/|_]{1}20\\d{6})";
  /** 表現 用-或許/離隔的日期,豐年月日的,例如 http://www.百度.com/2014-3-11/2356.html */
  private static String url_reg_sep_ymd = "([-|/|_]{1}20\\d{2}[-|/|_]{1}\\d{1,2}[-|/|_]{1}\\d{1,2})";
  /** 表現 用-或許/離隔的日期,只要年和月份的,例如 http://www.百度.com/2014-3/2356.html */
  private static String url_reg_sep_ym = "([-|/|_]{1}20\\d{2}[-|/|_]{1}\\d{1,2})";
  private static Calendar current = Calendar.getInstance();
  /** 格局准確的時光正則表達式*/
  private static String rightTimeReg = "^((\\d{2}(([02468][048])|([13579][26]))[\\-\\/\\s]?((((0?[13578])|(1[02]))[\\-\\/\\s]?((0?[1-9])|([1-2][0-9])|(3[01])))|(((0?[469])|(11))[\\-\\/\\s]?((0?[1-9])|([1-2][0-9])|(30)))|(0?2[\\-\\/\\s]?((0?[1-9])|([1-2][0-9])))))|(\\d{2}(([02468][1235679])|([13579][01345789]))[\\-\\/\\s]?((((0?[13578])|(1[02]))[\\-\\/\\s]?((0?[1-9])|([1-2][0-9])|(3[01])))|(((0?[469])|(11))[\\-\\/\\s]?((0?[1-9])|([1-2][0-9])|(30)))|(0?2[\\-\\/\\s]?((0?[1-9])|(1[0-9])|(2[0-8]))))))(\\s(((0?[0-9])|([1-2][0-3]))\\:([0-5]?[0-9])((\\s)|(\\:([0-5]?[0-9])))))?$";
   
  /**
   * @param url
   * @param urlContent
   * @return
   */
  public static String getPubTimeVarious(String url,String urlContent) {
     
    String pubTime = getPubTimeFromUrl(url);
     
   //鏈接外面沒有,婚配文本中的
    if(pubTime == null)
    {
      if(urlContent!=null&&!urlContent.trim().equals(""))
        return extractPageDate(urlContent);
    }
     
    return pubTime;
  }
   
  /**從url外面抽掏出宣布時光,前往YYYY-MM-DD HH:mm:ss格局的字符串
   * @param url
   * @return
   */
  public static String getPubTimeFromUrl(String url)
  {
    Pattern p_whole = Pattern.compile(url_reg_whole);
    Matcher m_whole = p_whole.matcher(url);
    if(m_whole.find(0)&&m_whole.groupCount()>0)
    {
      String time = m_whole.group(0);
      time = time.substring(1,time.length());
      //每步都不克不及夠超越以後時光     
    if(current.compareTo(TimeUtil.strToCalendar(time, "yyyyMMdd"))>=0)
    {
 
      return time.substring(0,4)+"-"+time.substring(4,6)+"-"+
         time.substring(6,8)+" "+"00:00:00";
    }
    }
    
    p_whole = null;
    m_whole = null;
    Pattern p_sep = Pattern.compile(url_reg_sep_ymd);
    Matcher m_sep = p_sep.matcher(url);
    if(m_sep.find(0)&&m_sep.groupCount()>0)
    {
       String time = m_sep.group(0);
       time = time.substring(1,time.length());
       String[] seg = time.split("[-|/|_]{1}");
       Calendar theTime = Calendar.getInstance();
       theTime.set(Calendar.YEAR,Integer.parseInt(seg[0]));
       theTime.set(Calendar.MONTH, Integer.parseInt(seg[1]));
       theTime.set(Calendar.DAY_OF_MONTH, Integer.parseInt(seg[2]));
       if(current.compareTo(theTime)>=0)
        {
       
      return seg[0]+"-"+seg[1]+"-"+seg[2]+" "+"00:00:00";
        }
    }
    p_sep = null;
    m_sep = null;
    Pattern p_sep_ym = Pattern.compile(url_reg_sep_ym);
    Matcher m_sep_ym = p_sep_ym.matcher(url);
    if(m_sep_ym.find(0)&&m_sep_ym.groupCount()>0)
    {
       String time = m_sep_ym.group(0);
       time = time.substring(1,time.length());
       Calendar theTime = Calendar.getInstance();
       String[] seg = time.split("[-|/|_]{1}");
       theTime.set(Calendar.YEAR,Integer.parseInt(seg[0]));
       theTime.set(Calendar.MONTH, Integer.parseInt(seg[1]));
       theTime.set(Calendar.DAY_OF_MONTH, 1);
       if(current.compareTo(theTime)>=0)
      {
       
      return seg[0]+"-"+seg[1]+"-"+"01"+" "+"00:00:00";
      }
    }
     
    return null;
  }
   
 
  /** 從網頁源碼中掏出宣布時光
   * java中正則表達式提取字符串中日期完成代碼
   * 2013年12月19日15:58:42
   * 讀掏出2013-12-19 15:48:33或許2013-12-19或許2012/3/05情勢的時光
   * @param text 待提取的字符串
   * @return 前往日期
   * @author: oschina
   * @Createtime: Jan 21, 2013
   */
  public static String extractPageDate(String text) { 
    boolean containsHMS =false;
    String dateStr = text.replaceAll("r?n", " ");
    try { 
      List matches = null; 
      Pattern p_detail = Pattern.compile("(20\\d{2}[-/]\\d{1,2}[-/]\\d{1,2} \\d{1,2}:\\d{1,2}:\\d{1,2})|(20\\d{2}年\\d{1,2}月\\d{1,2}日)", Pattern.CASE_INSENSITIVE|Pattern.MULTILINE); 
      //假如是僅僅抽取年代日,則依照下面的,假如是抽取年代日-時分秒,則依照上面的
      Pattern p = Pattern.compile("(20\\d{2}[-/]\\d{1,2}[-/]\\d{1,2})|(20\\d{2}年\\d{1,2}月\\d{1,2}日)", Pattern.CASE_INSENSITIVE|Pattern.MULTILINE);
      //Matcher matcher = p.matcher(dateStr);
      Matcher matcher_detail = p_detail.matcher(dateStr);
       
      if(!(matcher_detail.find(0) && matcher_detail.groupCount() >= 1)) 
      {
        matcher_detail = p.matcher(dateStr);
        containsHMS = true;
      }else
        matcher_detail = p_detail.matcher(dateStr);
      if (matcher_detail.find() && matcher_detail.groupCount() >= 1) { 
        matches = new ArrayList(); 
        for (int i = 1; i <= matcher_detail.groupCount(); i++) { 
          String temp = matcher_detail.group(i); 
          matches.add(temp); 
        } 
      } else { 
        matches = Collections.EMPTY_LIST; 
      }      
 
      if (matches.size() > 0) { 
        for(int i=0;i<matches.size();i++)
        {
          String pubTime = matches.get(i).toString().trim();
          //掏出第一個值
          pubTime = pubTime.replace("/", "-").replace("年", "-").replace("月", "-").replace("日", "-");
          if(current.compareTo(TimeUtil.strToCalendar(pubTime, "yyyy-MM-dd"))>=0)
          {
            if(containsHMS)
              pubTime+=" "+"00:00:00";
            if(pubTime.matches(rightTimeReg))
            {
              return pubTime; 
            }
          }
        }
      } else { 
        return null; 
      } 
       
    } catch (Exception e) { 
      return null; 
    } 
    return null;
  }
}

以上就是本文的全體內容,願望對年夜家進修java法式設計有所贊助。

  1. 上一頁:
  2. 下一頁:
Copyright © 程式師世界 All Rights Reserved