在项目中新建middlewares.py文件(./项目名/middlewares.py)
import base64
import sys
import random
PY3 = sys.version_info[0] >= 3
def base64ify(bytes_or_str):
if PY3 and isinstance(bytes_or_str, str):
input_bytes = bytes_or_str.encode('utf8')
else:
input_bytes = bytes_or_str
output_bytes = base64.urlsafe_b64encode(input_bytes)
if PY3:
return output_bytes.decode('ascii')
else:
return output_bytes
class ProxyMiddleware(object):
def process_request(self, request, spider):
# 代理服务器
proxyHost = "ip.hahado.cn"
proxyPort = "31111"
# 代理验证信息
proxyUser = "username"
proxyPass = "password"
# [版本>=2.6.2](https://docs.scrapy.org/en/latest/news.html?highlight=2.6.2#scrapy-2-6-2-2022-07-25)无需添加验证头,会自动在请求头中设置Proxy-Authorization
request.meta['proxy'] = "http://{0}:{1}@{2}:{3}".format(proxyUser,proxyPass,proxyHost,proxyPort)
# 版本<2.6.2 需要手动添加代理验证头
# request.meta['proxy'] = "http://{0}:{1}".format(proxyHost,proxyPort)
# request.headers['Proxy-Authorization'] = 'Basic ' + base64ify(proxyUser + ":" + proxyPass)
# 设置IP切换头(根据需求)
# tunnel = random.randint(1,10000)
# request.headers['Proxy-Tunnel'] = str(tunnel)
# 每次访问后关闭TCP链接,强制每次访问切换IP
request.header['Connection'] = "Close"
修改项目配置文件 (./项目名/settings.py)
DOWNLOADER_MIDDLEWARES = {
'项目名.middlewares.ProxyMiddleware': 100,
}