Scrapy 配置动态代理IP

Scrapy 配置动态代理IP

应用 Scrapy框架 ，配置动态IP处理反爬。

# settings 配置中间件
DOWNLOADER_MIDDLEWARES = {
'text.middlewares.TextDownloaderMiddleware': 543,
# 'text.middlewares.RandomUserAgentMiddleware': 544,
# 'text.middlewares.CheckUserAgentMiddleware': 545,
'text.middlewares.ProxyMiddleware': 546,
'text.middlewares.CheckProxyMiddleware': 547
}

# settings 配置可用动态IP
PROXIES = [
"http://101.231.104.82:80",
"http://39.137.69.6:8080",
"http://39.137.69.10:8080",
"http://39.137.69.7:80",
"http://39.137.77.66:8080",
"http://117.191.11.102:80",
"http://117.191.11.113:8080",
"http://117.191.11.113:80",
"http://120.210.219.103:8080",
"http://120.210.219.104:80",
"http://120.210.219.102:80",
"http://119.41.236.180:8010",
"http://117.191.11.80:8080"
]

# middlewares 配置中间件
import random

class ProxyMiddleware(object):

def process_request(self, request, spider):
ip = random.choice(spider.settings.get('PROXIES'))
print('测试IP:', ip)
request.meta['proxy'] = ip

class CheckProxyMiddleware(object):

def process_response(self, request, response, spider):
print('代理IP:', request.meta['proxy'])
return response