Java尽量精确地抽取网页的发布时间

更新时间:2016-07-15 15:21:15 点击次数:2309次
对网页中各种不同格式的发布时间进行抽取,将发布时间以规整的“yyyy-MM-dd HH:mm:ss”格式表示出来,只能尽量追求精确,但是因为网络发布时间的格式十分灵活,所以做不到百分百地正确抽取
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
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 下午2:49:05
 * @description 获取网页的发布时间
 */
public class FetchPubTime {
    /** 表示url中连续的8位日期,例如http://www.baidu.com/20140311/2356.html */
    private static String url_reg_whole= "([-|/|_]{1}20\\d{6})";
    /** 表示 用-或者/隔开的日期,有年月日的,例如 http://www.baidu.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})";
    /** 表示 用-或者/隔开的日期,只有年和月份的,例如 http://www.baidu.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();
    /** 格式正确的时间正则表达式*/
    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);
         
      //链接里面没有,匹配文本中的
        if(pubTime == null)
        {
            if(urlContent!=null&&!urlContent.trim().equals(""))
                return extractPageDate(urlContent);
        }
         
        return pubTime;
    }
     
    /**从url里面抽取出发布时间,返回YYYY-MM-DD HH:mm:ss格式的字符串
     * @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());
           //每一步都不能够超出当前时间         
        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;
    }
     
 
    /** 从网页源码中取出发布时间
     *  java中正则表达式提取字符串中日期实现代码
     *  2013年12月19日15:58:42
     *  读取出2013-12-19 15:48:33或者2013-12-19或者2012/3/05形式的时间
     * @param text 待提取的字符串
     * @return 返回日期
     * @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);
            //如果是仅仅抽取年月日,则按照上面的,如果是抽取年月日-时分秒,则按照下面的
            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();
                    //取出个值
                    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;
    }
}

本站文章版权归原作者及原出处所有 。内容为作者个人观点, 并不代表本站赞同其观点和对其真实性负责,本站只提供参考并不构成任何投资及应用建议。本站是一个个人学习交流的平台,网站上部分文章为转载,并不用于任何商业目的,我们已经尽可能的对作者和来源进行了通告,但是能力有限或疏忽,造成漏登,请及时联系我们,我们将根据著作权人的要求,立即更正或者删除有关内容。本站拥有对此声明的最终解释权。

回到顶部
嘿,我来帮您!