第1.7章 scrapy之ip代理的使用

1 代理中间件

代码核心在于随机选择一条代理的ip和port，至于代理ip和port的来源，可以是购买的ip代理，也可以从网上爬取的。

# -*- coding: utf-8 -*-
'''
Created on 2017年6月14日

@author: dzm
'''
from eie.middlewares import udf_config
from eie.service.EieIpService import EieIpService

logger = udf_config.logger
eieIpService = EieIpService()

class ProxyMiddleware(object):
'''
ip代理中间件
'''

def process_request(self,request,spider):
'''
在请求上添加ip代理
'''
if request.url.startswith('http://'):
proxy = eieIpService.select_rand('HTTP')
if proxy:
proxies = 'http://{}:{}'.format(proxy['ip'],proxy['port'])
else:
raise Exception('没有找到合适的IP代理')
else:
proxy = eieIpService.select_rand('HTTPS')
if proxy:
proxies = 'https://{}:{}'.format(proxy['ip'],proxy['port'])
else:
raise Exception('没有找到合适的IP代理')
request.meta['proxy'] = proxies

2 settings配置

这里需要注意RetryMiddleware和ProxyMiddleware之间的顺序，否则会出现Python Scrapy不重试连接超时，scrapy会一致超时重连，我找遍QQ群，也没人回答我的问题。

中间件的顺序很重要，详细描述可以参考：SCRAPY中DOWNLOADER_MIDDLEWARES中间件的配置顺序

DOWNLOADER_MIDDLEWARES = {
'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware':None,
'eie.middlewares.random_user_agent.RandomUserAgent': 100,
'eie.middlewares.proxy_middleware.ProxyMiddleware': 110,
'scrapy.downloadermiddlewares.retry.RetryMiddleware':120,
'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware': 130,
}

可供参考的顺序

DOWNLOADER_MIDDLEWARES_BASE
{
'scrapy.contrib.downloadermiddleware.robotstxt.RobotsTxtMiddleware': 100,
'scrapy.contrib.downloadermiddleware.httpauth.HttpAuthMiddleware': 300,
'scrapy.contrib.downloadermiddleware.downloadtimeout.DownloadTimeoutMiddleware': 350,
'scrapy.contrib.downloadermiddleware.useragent.UserAgentMiddleware': 400,
'scrapy.contrib.downloadermiddleware.retry.RetryMiddleware': 500,
'scrapy.contrib.downloadermiddleware.defaultheaders.DefaultHeadersMiddleware': 550,
'scrapy.contrib.downloadermiddleware.redirect.MetaRefreshMiddleware': 580,
'scrapy.contrib.downloadermiddleware.httpcompression.HttpCompressionMiddleware': 590,
'scrapy.contrib.downloadermiddleware.redirect.RedirectMiddleware': 600,
'scrapy.contrib.downloadermiddleware.cookies.CookiesMiddleware': 700,
'scrapy.contrib.downloadermiddleware.httpproxy.HttpProxyMiddleware': 750,
'scrapy.contrib.downloadermiddleware.chunked.ChunkedTransferMiddleware': 830,
'scrapy.contrib.downloadermiddleware.stats.DownloaderStats': 850,
'scrapy.contrib.downloadermiddleware.httpcache.HttpCacheMiddleware': 900,
}

3 检查ip代理是否成功

从下图的response可以看出确实是采用了代理地址



4 代理的作用

ip代理及其作用与使用方法

使用代理IP的优缺点？

5 获取随机代理

def select_rand_zhimadaili(self):
'''
从芝麻代理中获取ip代理清单
@see: http://http.zhimadaili.com/index/api/newapi.html '''
try:
proxy_keys_list = self.redis.keys()
if proxy_keys_list:
key_list = range(1, len(proxy_keys_list))
key = key_list[random.choice(key_list)]
#                 proxy_list = json.load(self.redis.get(proxy_keys_list[key]))
strs = self.redis.get(proxy_keys_list[key])
return eval(strs)
else:
socket = urllib2.urlopen('http://http.zhimadaili.com/index/api/new_get_use_ips.html?num=20&type=2&pro=0&city=0&yys=0&port=1&time=1')
result = socket.read()
result = json.loads(result)
proxy_list = result['data']
for proxy in proxy_list:
name = '{}:{}'.format(proxy['ip'],proxy['port'])
self.redis.setex(name, proxy, 600)
socket.close()
key_list = range(1, len(proxy_list))
key = key_list[random.choice(key_list)]
return proxy_list[key]
except Exception,e:
logger.error('请求zhimadaili.com获取代理失败,失败原因:%s' % e)

下面的方式是从数据库中随机找一条,数据库是mysql

def select_rand_db(self,types=None):
if types:
sql = "select ip,port,types from eie_ip where types='{}' order by rand() limit 1".format(types)
else:
sql = "select ip,port,types from eie_ip order by rand() limit 1 "
df = pd.read_sql(sql,self.engine)
results = json.loads(df.to_json(orient='records'))
if results and len(results)==1:
return results[0]
return None