天天好味道

有大量名字以序列号排序 内容如下面内容的文本文件

姓名:aaaa
性别:bbb
年龄:ccc
籍贯:ddd

冒号和内容中间有数量不等的空格,如何能批量导入这些文件进入一个数据库，比如access

形如下面的形式

姓名    性别    年龄    籍贯
aaaa1   bbb1    ccc1    ddd1
aaaa2   bbb2    ccc2    ddd2


其中某项空缺的时候，比如有一个文本文件里年龄空缺，怎么保证列表还能正确






下面是测试用的数据文件: http://dhxy.info/upload/CS/1134036281_1.rar

# -*- coding: cp936 -*-
#convert txt data file into csv file
import sys
import os.path

def output(cur):
 s = ""
 keys = ["名字","性别","年龄","籍贯"]
 for key in keys:
  if(cur.has_key(key)):
   s += cur[key]
  s += ","
 s+="\n"
 return s

def convertFile(filename):
 try:
  f = file(filename,'r')
  fout = file("result.csv",'a')
  #fout.writelines("name,sex,age,birthplace\n")
  cur = {}
  s=f.readline()
  tokens = ["名字","性别","年龄","籍贯"]
  
  while len(s) > 0:
   lv = s.split(":",2)
   if(len(lv)!=2):
    s=f.readline()
    continue
   token = lv[0].lower()
   value = lv[1]
   if cur.has_key(token) or len(cur)==len(tokens):
    result = output(cur)
    fout.writelines(result)
    cur = {}
   if token in tokens:
    cur[token] = value.lstrip().rstrip("\n")
   else:
    print "error line"
   s=f.readline()
  if len(cur) > 0:
   result = output(cur)
   fout.writelines(result)
  fout.close();
  f.close()  
 except IOError:
  print "data file not found!"

#main program
if len(sys.argv) != 2:
 print "Usage:python convert.py directory"   
 sys.exit()
  
dirname = sys.argv[1]
try:
 entryList = os.listdir(dirname)
 #remove the result file first and write the header
 fout = file("result.csv",'w+')
 fout.writelines("名字,性别,年龄,籍贯\n")
 fout.close()
 for entry in entryList:
  if os.path.isdir(dirname + "\\" + entry):
   pass
  else:
   convertFile(dirname + "\\" + entry) 
except WindowsError:
 print "Dir not found!" + dirname

#include <stdio.h>
#include <stdlib.h>
#include <ctype.h>
#include <string.h>

#define OUT_FILE  "result.csv"
#define RECORD_MAX_LEN  256
struct _record {
    char name[RECORD_MAX_LEN];
    char sex[RECORD_MAX_LEN];
    char age[RECORD_MAX_LEN];
    char birth[RECORD_MAX_LEN];
    int name_len;
    int sex_len;
    int age_len;
    int birth_len;
};
struct _record record;

static char *token[] = {
    "名字:",
    "性别:",
    "年龄:",
    "籍贯:"
};

static inline int out_record(FILE *out)
{   
    //fprintf(stdout, "%s,%s,%s,%s ", record.name, record.sex, record.age, re
cord.birth);
    fwrite(record.name, 1, record.name_len, out);
    fwrite(",", 1, 1, out);
    fwrite(record.sex, 1, record.sex_len, out);
    fwrite(",", 1, 1, out);
    fwrite(record.age, 1, record.age_len, out);
    fwrite(",", 1, 1, out);
    fwrite(record.birth, 1, record.birth_len, out);
    fwrite(" ", 1, 1, out);
    record.name[0] = '