python爬虫使用Cookie的两种方法

1、直接将Cookie写在header头部

import requests
from bs4 import BeautifulSoup
cookie = '''cisession=19dfd70a27ec0eecf1fe3fc2e48b7f91c7c83c60;CNZZDATA1000201968=181584
6425-1478580135-https%253A%252F%252Fwww.baidu.com%252F%7C1483922031;Hm_lvt_f805f7762a9a2
37a0deac37015e9f6d9=1482722012,1483926313;Hm_lpvt_f805f7762a9a237a0deac37015e9f6d9=14839
26368'''
header = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Geck
o) Chrome/53.0.2785.143 Safari/537.36',
'Connection': 'keep-alive',
'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Cookie': cookie}
url = 'https://kankandou.com/book/view/22353.html'
wbdata = requests.get(url,headers=header).text
soup = BeautifulSoup(wbdata,'lxml')
print(soup)

2、使用requests插入Cookie

import requests
from bs4 import BeautifulSoup
cookie = {
"cisession":"19dfd70a27ec0eecf1fe3fc2e48b7f91c7c83c60",
"CNZZDATA100020196":"1815846425-1478580135-https%253A%252F%252Fwww.baidu.com%252F%7C1483
922031",
"Hm_lvt_f805f7762a9a237a0deac37015e9f6d9":"1482722012,1483926313",
"Hm_lpvt_f805f7762a9a237a0deac37015e9f6d9":"1483926368"
}
url = 'https://kankandou.com/book/view/22353.html'
wbdata = requests.get(url,cookies=cookie).text
soup = BeautifulSoup(wbdata,'lxml')
print(soup)

这样我们就轻松的使用Cookie获取到了需要登录验证后才能浏览的网页和资源了。上面的Cookie是从自己浏览的网页中复制粘贴得到的。