获取百度贴吧的里QQ号

import urllib.request

import re as gg

import os,string,sys

import easygui as g

result = []

#urllib.urlopen(url)  获取网页源码函数

#urllib.urlretrieve(url,‘存储名字‘)  将网页资源下载到本地函数

def getyuanma(_url):

page = urllib.request.urlopen(_url).read()

page1 = page.decode(‘UTF-8‘)  ##转换编码

f = open(r‘C:\Users\Administrator\Desktop\python\爬虫\源码1.txt‘,‘w‘,encoding=‘utf-8‘)

f.write(str(page1))

f.close()

def getQQnum(file_url):

f1 = open(file_url,‘r‘,encoding=‘utf-8‘)

for i in f1:

p = gg.findall(r‘([0-9]{8,11}\@[0-9a-zA-Z]{0,10}.{0,4})‘,i)

if len(p) != 0:

print(p)

def getyeshu(file_url):

f2 = open(file_url,‘r‘,encoding=‘utf-8‘)

for i in f2:

p = gg.findall(r‘pn=([0-9]{1,3})\">尾页‘,i)

if len(p) != 0:

_num = p[0]

return _num

break

def main():

_url1 = g.enterbox("请输入链接地址：","输入地址")

getyuanma(_url1)

print(_url1)

_num = getyeshu(r‘C:\Users\Administrator\Desktop\python\爬虫\源码1.txt‘)

if _num != None:

for i in range(1,int(_num)+1):

print(i)

getyuanma(_url1+r‘?pn=‘+str(i))

getQQnum(r‘C:\Users\Administrator\Desktop\python\爬虫\源码1.txt‘)

main()