全球主要大学数据格式化工具

主要应用于地理位置选择界面，网上有个19兆的包含23万条数据的txt学校地址及信息数据库，以下这个python脚本可以帮你把咋个庞大的txt数据库通过分类格式化为较小的文件，提高索引效率。

# -*- coding: utf-8 -*-
import sys,os,codecs
from urllib import quote
reload(sys)

sys.setdefaultencoding("utf-8");

edudatas = os.path.join(os.getcwd(),"edu")
if not os.path.exists(edudatas):
    os.mkdir(edudatas)

schoollist = os.path.join(edudatas,"schoollist")
if not os.path.exists(schoollist):
    os.mkdir(schoollist)

campus = os.path.join(schoollist,"campus")
if not os.path.exists(campus):
    os.mkdir(campus)

middleschool = os.path.join(schoollist,"middleschool")
if not os.path.exists(middleschool):
    os.mkdir(middleschool)

primaryschool = os.path.join(schoollist,"primaryschool")
if not os.path.exists(primaryschool):
    os.mkdir(primaryschool)

line_ttl = sum(1 for line in open("allschool.txt"))
line_count = 0

def main():
    for line in open("allschool.txt",'r').readlines():
        global line_count,line_ttl
        line_count += 1
        percentage = 100*float(line_count)/line_ttl
        sys.stdout.write("%%%2.2f"%percentage+"\r")
        row = line.split("\t")
        school_id = row[0]#学校id
        school_name_start_letter = row[1]#学校首字母起始
        school_name = row[2]#学校名字
        school_type = int(row[3])#学校类型 1 小学 2 中学 3 大学/中专
        campus_extype = row[4]# 0 专科 1 普通本科 2 重点本科
        country = row[5]#国家代码
        country_name = row[6]#国家名
        province = row[7]#省级代码
        province_name = row[8]#省级名
        city = row[9]#城市代码
        city_name = row[10]#城市名
        district = row[11]#县或镇代码
        district_name = row[12]#县或镇名
        
        file_name = "_".join([ quote(name) for name in [country_name,province_name,city_name] if name != "null"])+".list"
        file_path = None

        if school_type == 1:
            file_path = os.path.join(primaryschool,file_name)
        elif school_type == 2:
            file_path = os.path.join(middleschool,file_name)
        elif school_type == 3:
            file_path = os.path.join(campus,file_name)

        if not file_path:
            continue
        
        filehandler = codecs.open(file_path,"a+","utf-8")
        filehandler.write( ":".join((school_name,school_id,school_name_start_letter.upper()))+"," )
        filehandler.close()


if __name__ == "__main__":
    main()