Urllib库添加Headers的方法

方法一：借助build_opener和addheaders完成

import urllib.request
import os,sys,io 
#解决编码问题，修改默认编码为gb18030
sys.stdout = io.TextIOWrapper(sys.stdout.buffer,encoding='gb18030')
url="https://www.jianshu.com/"
#注意：在urllib 中headers是元组
headers=("User-Agent","UMozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.87 Safari/537.36")
opener=urllib.request.build_opener()
opener.addheaders=[headers]
data=opener.open(url)
print(data.read().decode())

方法二：用add_headers（）来添加headers

import urllib.request
import os,sys,io 
#解决编码问题，修改默认编码为gb18030
sys.stdout = io.TextIOWrapper(sys.stdout.buffer,encoding='gb18030')
try:
    url="https://www.jianshu.com/"
    req=urllib.request.Request(url=url)
    req.add_header("User-Agent","UMozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.87 Safari/537.36")
    file=urllib.request.urlopen(req,timeout=10.1)
    print(file.read().decode("utf-8",'ignore'))
except Exception as e:
    print("时间超时",str(e))