urllib之cookie

urllib之cookie

cookies处理首先需要相关handler

获取cookie

import http.cookiejar

import urllib.request
# 声明一个cookiejar对象
cookie = http.Cookiejar.CookieJar()
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open("https://www.baidu.com")
print(cookie)
for item in cookie:
    print(item.name+"=" +item.value)

输出结果

IDUPSID=F1E1866953405375EB1EA5AE50CB1B35
PSTM=1563535868
BD_NOT_HTTPS=1

保存cookie到text文件

import urllib.request
from http import cookiejar

def save_cookie(url,file_name): 
    # cookie = cookiejar.MozillaCookieJar(file_name)保存为Mozilla型浏览器的Cookies格式
    # 保存为libwww-perl(LWP)格式的Cookies文件
    cookie = cookiejar.LWPCookieJar(file_name)
    handler = urllib.request.HTTPCookieProcessor(cookie)
    opener = urllib.request.build_opener(handler)
    opener.open(url)
    cookie.save()

if __name__ == '__main__':
    url = "https://www.baidu.com"
    file_name = "cookie_LWP.text"
    headers = {
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"
    }
    req = urllib.request.Request(url,headers=headers)
    save_cookie(req,file_name)

Mozilla格式

# Netscape HTTP Cookie File
# http://curl.haxx.se/rfc/cookie_spec.html
# This is a generated file!  Do not edit.

.baidu.com TRUE   /  FALSE  3710949608 BAIDUID    182A5E3788874CC39983E8533C99B495:FG=1
.baidu.com TRUE   /  FALSE  3710949608 BIDUPSID   182A5E3788874CC39983E8533C99B495
.baidu.com TRUE   /  FALSE  3710949608 PSTM   1563465961

LWP格式

#LWP-Cookies-2.0
Set-Cookie3: BAIDUID="3673AD9D161DE3CD2E5C7CE30F2C1DBC:FG=1"; path="/"; domain=".baidu.com"; path_spec; domain_dot; expires="2087-08-05 19:20:47Z"; version=0
Set-Cookie3: BIDUPSID=3673AD9D161DE3CD2E5C7CE30F2C1DBC; path="/"; domain=".baidu.com"; path_spec; domain_dot; expires="2087-08-05 19:20:47Z"; version=0
Set-Cookie3: PSTM=1563465999; path="/"; domain=".baidu.com"; path_spec; domain_dot; expires="2087-08-05 19:20:47Z"; version=0

读取cookie

from http import cookiejar
import urllib.request

def read_LWP_cookie(file_name):

    cookie = cookiejar.LWPCookieJar()
    # load方法读取本地cookie文件
    cookie.load(file_name,ignore_discard=True,ignore_expires=True)
    handler = urllib.request.HTTPCookieProcessor(cookie)
    opener = urllib.request.build_opener(handler)
    response = opener.open("http://www.baidu.com")
    print(response.read().decode("utf-8"))

if __name__ == '__main__':
    file_name = "cookie_LWP.text"
    read_LWP_cookie(file_name)