Python处理json数据--世界国家维度数据

1.准备国家的json数据

　　将准备好的json数据放在指定的目录下，此处可以重这里下载

2.测试编写python脚本处理json提取字段值

#coding:utf8
import time, re, os, sys, time,urllib2,shutil,string
import json,datetime

#设置utf-8编码格式
reload(sys)
sys.setdefaultencoding( "utf-8" )

#获取当前日期的前n天
def getbeforeDay(n=0):
    now_time = datetime.datetime.now()
    beforeday = now_time - datetime.timedelta(n)
    return beforeday.strftime("%Y%m%d")
    

scriptDir = os.getcwd()

if len(sys.argv) > 1 :
    job_date_id = sys.argv[1]
else :
    job_date_id = getbeforeDay(0)

print "当前脚本路径:%s,当前参数日期:%s" % (scriptDir,job_date_id)

srcdata='{"area":"390,580","code":"263","en":"Zimbabwe","cn":"津巴布韦","iso2":"ZW","iso3":"ZWE","population":"11,651,858"}'

jsondata = json.loads(srcdata)
print type(jsondata)

print "######遍历key,values######"
for key in jsondata.keys():
    print key,":",jsondata[key]

print "####或者指定key，返回结果####"
print jsondata['code'],jsondata['cn'],jsondata['en'],jsondata['area'],jsondata['population']

 

3.读取文本循环遍历提取字段值

#coding:utf8
import requests, json, time, re, os, sys, time,urllib2,shutil,string
import json,datetime

#设置utf-8编码格式
reload(sys)
sys.setdefaultencoding( "utf-8" )

#读取文件内容
def getLines(filename):
    file_object = open(filename,'rb')
    lines = file_object.readlines()
    return lines

#返回规范字符串
def getFormateContext(*name):
    format = ','
    context = name[0]
    for i in name[1:]:
        context = context + format + str(i)
    context = str(context).replace('（', '(').replace('）', ')').replace('，', ',').replace('：', ':')
    return context

def getbeforeDay(n=0):
    now_time = datetime.datetime.now()
    beforeday = now_time - datetime.timedelta(n)
    return beforeday.strftime("%Y%m%d")


#写文件
def Write(filename,context,model='a'):
    #去除首位空格
    filename = filename.strip()
    #读取目录名称
    path = os.path.dirname(filename)
    #如果目录不存在则创建目录
    if not os.path.exists(path):
        pass
    #读取文件名称
    name = os.path.basename(filename)
    fp = open(filename,model)
    fp.write(context+'\n')
    fp.close()

scriptDir = os.getcwd()

if len(sys.argv) > 1 :
    job_date_id = sys.argv[1]
else :
    job_date_id = getbeforeDay(10)

print "当前脚本路径:%s,当前参数日期:%s" % (scriptDir,job_date_id)

filename="%s\/jsondata\/country.json" % (scriptDir)

for line in getLines(filename):
    line = line.strip()
    line = line[1:]
    line = line[:-2]
    for value in line.split("},"):
        srcdata = value+"}"
        #print srcdata
        print srcdata
        jsondata = json.loads(srcdata)

        #国家代码
        code = jsondata['code']
        #国家中文名称
        cn = jsondata['cn']
        #国家英文名称
        en = jsondata['en']
        #面积
        area = jsondata['area'].replace(',','')
        #人口
        population = jsondata['population'].replace(',','')
        #iso2
        iso2 = jsondata['iso2']
        #iso3
        iso3 = jsondata['iso3']
        #print code,cn,en,area,population,iso2,iso3
        context = getFormateContext(code,cn,en,area,population,iso2,iso3)
        print context
        Write("country.csv", context, model='a')

4.最终处理数据结果

   CSV格式: 

   Excel格式: