from urllib import request
import urllib
from http import cookiejar

# 定义文件名
filename = 'cookie.txt'

# 声明一个cookie,传入文件名
cookie = cookiejar.MozillaCookieJar(filename)

# 定义cookie处理
handler = request.HTTPCookieProcessor(cookie)

# 定义下载器,传入处理器
opener = request.build_opener(handler)

# 定义登录用的账号密码

postdata = urllib.parse.urlencode({

    'username': '账号',
    'password': '密码'
}).encode(encoding='UTF8')

# url
loginUrl = '网站'

# 模拟登录页面
resp = opener.open(loginUrl, postdata)

# 保存cookie到文件

cookie.save(ignore_discard=True, ignore_expires=True)

# 再次访问网站
url2 = "网站"

# 打开页面
try:
    result = opener.open(url2)
except request.HTTPError as e:
    if hasattr(e, "code"):
        print(e.code)
except request.URLError as e:
    if hasattr(e, "reason"):
        print(e.reason)
else:
    print(result.read())

import re

# 定义正则化规则=匹配模式,r表示原生字符串
rexg = re.compile(r'\d*\w*')
res = re.search(rexg, 'ddddddddddddd5')
print(res)

rexg1 = re.compile(r'\d+\w*')
res1 = re.search(rexg1, 'pppppddddddddddddd5')
print(res1)

rexg2 = re.compile(r'\d?dddddd')
res2 = re.search(rexg2, 'pppppddddddddddddd5')
print(res2)

# 电话号码
rexg3 = re.compile(r'1\d{10}')
res3 = re.search(rexg3, '')
print(res3)

# 定义邮箱
rexg4 = re.compile(r'\d{5,12}@\w{2}\.\w{3}')
res4 = re.search(rexg4, '1sdfsdfdsfdsdfs@qq.com')
print(res4)

rexg5 = re.compile(r'\d+')
res5 = re.search(rexg5, '11sdfsdfdsfdsdfs@qq.com')
print(res5)

rexg6 = re.compile(r'\d{5,12}? ?')
res6 = re.search(rexg6, '11sdfsdfdsfdsdfs6477d09191@qq.com')
print(res6)

# 边界匹配-匹配字符串开头
rexg7 = re.compile(r'\Aabc')
res7 = re.search(rexg7, 'abcqqqqqqqqqabccttttttttttt'
                        'abcctttttttttabc')
print(res7)

# 任意

rexg8 = re.compile(r'1\d{10}|\d{5,12}@\w{2}\.\w{3}')

res8 = re.search(rexg8, "sahsyhs1dgashgshasdag@qq.com")
print(res8)

# 分组

rexg9 = re.compile(r'(abc){3}')
res9 = re.search(rexg9, "zUJXHUJHXuabcabcabcosaojaodiabcosajosabc")
print(res9)

# 分组 + 别名
rexg10 = re.compile(r'(?Pabc)888(?P=tt)')
res10 = re.search(rexg10, "hasghsabc888abc")
print(res10)

# 分组 + 编号

rexg11 = re.compile(r'(\d{5})uu\1')

res11 = re.search(rexg11, "uu")
print(res11)