西刺代理（用老师ip）爬取

import requests

# url
url = 'http://www.xicidaili.com'
# 添加 proxy
proxy = {
    'http': 'http://root:[email protected]:8118'
}
# 添加headers
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
}
# 调用requests, 得到response
response = requests.get(url, headers=headers, proxies=proxy)
# response.text = response.content.decode()
# response.text 类型是 str
# response.content 类型是 bytes
print(response.text)
# with open('xicidaili.html', 'wb') as f:
#     f.write(response.content)