介绍下3种python获取cookie的方法。
(1)借助handler
这种方法也是网上介绍最多的一种方法,但是用起来比较麻烦
from http import cookiejar from urllib import request class Craw(): def __init__(self): self.url = '' self.headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 6.3; Win64; x64) ' \ 'AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.162 Safari/537.36' self.headers['Content-Type'] = 'application/x-www-form-urlencoded' def getCookies(self): cookie = cookiejar.CookieJar() handler = request.HTTPCookieProcessor(cookie) opener = request.build_opener(handler) response = opener.open(self.url) cookieValue = '' for item in cookie: cookieValue += item.name + '=' + item.value + ';' self.headers['Cookie'] = cookieValue response = requests.get(url=self.url) def getVerificationCode(self): img_url = '' imgResponse = requests.get(url=img_url,headers = self.headers) #直接使用headers即可 base64_jpg = base64.b64encode(imgResponse.content) return base64_jpg
(2)使用response headers的set_cookie
import requests import re class Crawler(): def getCookie(self): response = requests.post(self.url) set_cookie = response.headers['Set-Cookie'] array = re.split('[;,]',set_cookie) cookieValue = '' for arr in array: if arr.find('DZSW_SESSIONID') >= 0 or arr.find('bl0gm1HBTB') >= 0: cookieValue += arr + ';'
(3)使用response的cookies属性获取
只写getCookies方法,代码如下:
import requests class Crawler(): def getCookie(self): response = requests.get(self.url) cookie_value = '' for key,value in response.cookies.items(): cookie_value += key + '=' + value + ';' self.headers['Cookie'] = cookie_value