对应代码如下
package hbase;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat;
import java.io.IOException;
import java.text.DateFormat;
import java.text.SimpleDateFormat;
import java.util.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
* Created by lcc on 2017/10/26.
*/
public class FromWeibo {
public static class ToHbaseMap extends Mapper<BytesWritable, MapWritable, ImmutableBytesWritable, Put>{
protected Date getPostDate(String down, String s){
Date postdate=null;
DateFormat downdf = new SimpleDateFormat("yyyy-MM-dd HH:mm");
try {
Date downd = downdf.parse(down);
String reg = "<p class=\"release_date\">(.*?)</p>";
Pattern pattern = Pattern.compile(reg);
Matcher matcher = pattern.matcher(s);
DateFormat df = new SimpleDateFormat("yyyy-MM-dd HH:mm");
DateFormat df2 = new SimpleDateFormat("MM月dd日 HH:mm");
if (matcher.find()) {
String out = matcher.group(1);
out = out.trim();
if (!out.equals("")) {
try {
postdate = df.parse(out);
} catch (Exception e) {
try {
postdate = df2.parse(out);
postdate.setYear(117);