正则中国邮政

#-*-coding:utf-8-*-
import  re,json,requests
url="http://www.ip138.com/post/"
headers = {  # 伪装成浏览器，防止反爬,通用
    'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.26 Safari/537.36 Core/1.63.5558.400 QQBrowser/10.1.1695.400'}
# response=requests.get(url=url,headers=headers).content.decode("gbk")
# with open("中国邮编首页.html",'w',encoding='utf-8')as  fq:
#     fq.write(response)
with open("中国邮编首页.html",'r',encoding='utf-8')as  fq:
    response=fq.read()
p=re.compile(r'<a href="/(.*?)/" target="_blank">(.*?)</a></td>')#列表套元组
province=p.findall(response)
print(province)
print(len(province))
dictall={}
m=0
for i in province:
    print(i)
    dictcity = {}
    # url = f"http://www.ip138.com/{i[0]}"
    # response=requests.get(url=url,headers=headers).content.decode("gbk")
    # with open(f"各省邮编/{i[1]}.html",'w',encoding='utf-8')as  fq:
    #     fq.write(response)
    with open(f"各省邮编/{i[1]}.html",'r',encoding='utf-8')as  fq:
        response=fq.read()
    bigcities=[""]
    # p=re.compile(r'<tr bgcolor="#ffffff"><td>(.*?)</td><td><a href="/.*?/">(.*?)</a></td>')
    # xian=p.findall(response)
    # print(len(xian),xian)
    p2=re.compile(r'<tr bgcolor="#ffffff">(.*?)<tr><td colspan="6"></td></tr>',re.S)#把省的地区分出来
    cities=p2.findall(response)
    if cities==[]:#直辖市和港澳
        #p4 = re.compile(r'<tr bgcolor="#ffffff"><td>(.*?)</td><td><a href="/.*?/">(.*?)</a>', re.S)
        p4 = re.compile(r'<td>(.*?)</td><td><a href="/.*?/">(.*?)</a></td><td><a href="/.*?/">.*?</a></td>', re.S)
        bigcitylist= p4.findall(response)
        for  bigcity in bigcitylist:
            dictcity[bigcity[0]]=bigcity[1]
            m+=1
        dictall[i[1]] = dictcity
        continue
    print('cities',cities)
    for  city  in cities:
        print(city)
        p3=re.compile(r'<td><a href=".*?/"><b>(.*?)</a></b></td><td><a href="/.*?/">(.*?)</a></td>',re.S)
        area=p3.findall(city)[0]
        #p4=re.compile(r'<tr bgcolor="#ffffff"><td>(.*?)</td><td><a href="/.*?/">(.*?)</a></td>.*?<td>(.*?)</td><td><a href="/.*?/">(.*?)</a></td></tr><tr><td colspan="6"></td></tr>',re.S)
        p4 = re.compile(r'<td>(.*?)</td><td><a href="/.*?/">(.*?)</a></td><td><a href="/.*?/">.*?</a></td>', re.S)
        xians=p4.findall(city)[1:]
        if xians==[]:
            dictcity[area[0]]=area[1]
            m+=1
        else:
            dictxian={}
            dictxian[area[0]] = area[1]
            m+=1
            for xian in xians:
                dictxian[xian[0]]=xian[1]
                m+=1
                #dictxian[xian[2]] = xian[3]
            dictcity[area[0]]=dictxian
        print(area,xians)
    dictall[i[1]]=dictcity
strall= json.dump(dictall, open(f'中国邮编正则7.json', 'w', encoding="utf-8"), ensure_ascii=False)
print(m)