爬虫第二课---urllib

import urllib.request

'''
普通请求，不设置headers
'''
# url = 'http://httpbin.org/get'#或post
# #urlopen    发起请求
# # req = urllib.request.urlopen(url)#get
# req = urllib.request.urlopen(url,data='username=huo'.encode(),timeout=2)#参数data就是post请求，timeout设置超时
# print(req.read().decode())

'''
设置headers
'''
urls = 'https://www.jianshu.com'
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36"
}
req = urllib.request.Request(urls,headers=headers)
r = urllib.request.urlopen(req)
print(r.read().decode())

​
import urllib.request
from http import cookiejar
#创建一个cookie对象
cookie = cookiejar.CookieJar()
filename = 'cookie.txt'
# cookie = cookiej