user-agent设置

from urllib.request import Request,urlopen

url='https://www.cnblogs.com/wsonepiece/p/3965906.html'

# header={
#     'user-agent':' Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3880.400 QQBrowser/10.8.4554.400',
# }
#用户代理User-Agent列表
# header_list = [
#     "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
#     "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
#     "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
# ]
# choice(header_list)  #加模块random.choice,建立一个header列表，每次随机选择一个header
# pip install fake-useragent  #Terminal里安装第三方模块

# from fake_useragent import UserAgent
# print(1)
# ua=UserAgent()
# # https://fake-useragent.herokuapp.com/browsers/0.1.11
# # 本来会调用这个网站的文件，里面放置着一些假的user-agent，但是现在无法登录这个网站获取文件
# print(ua)
# print(1)

# print(UserAgent().random)  #随机生成请求头
# print(UserAgent().chrome)  #随机生成谷歌请求头
# print(UserAgent().ie)      #随机生成IE请求头
# print(UserAgent().firefox) #随机生成火狐请求头

# https://blog.csdn.net/weixin_51852924/article/details/120019488?spm=1001.2101.3001.6650.3&utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-3-120019488-blog-116074445.pc_relevant_multi_platform_whitelistv3&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-3-120019488-blog-116074445.pc_relevant_multi_platform_whitelistv3&utm_relevant_index=6
# 第三方库的fake_useragent里的网站失效，改用my_fake_useragent可以完成任务获取请求头
from my_fake_useragent import UserAgent

ua = UserAgent()
# ua = UserAgent(family='chrome')   #获取谷歌请求头
header={
    'user-agent':ua.random(),
}
req=Request(url,headers=header)
resp=urlopen(req)
print(resp.read().decode())