Python3爬虫学习之应对网站反爬虫机制的方法分析

from urllib import request
url = 'http://www.baidu.com'
# page = request.Request(url)
# page.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36')
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'}
page = request.Request(url, headers=headers)
page_info = request.urlopen(page).read().decode('utf-8')
print(page_info)

urllib.request.Request()
urllib.request.Request(url, data=None, headers={}, origin_req_host=None, unverifiable=False, method=None)