一、为什么要搭建爬虫代理池
在众多的网站防爬措施中,有一种是根据ip的访问频率进行限制,即在某一时间段内,当某个ip的访问次数达到一定的阀值时,该ip就会被拉黑、在一段时间内禁止访问。
应对的方法有两种:
1. 降低爬虫的爬取频率,避免IP被限制访问,缺点显而易见:会大大降低爬取的效率。
2. 搭建一个IP代理池,使用不同的IP轮流进行爬取。
二、搭建思路
1、从代理网站(如:西刺代理、快代理、云代理、无忧代理)爬取代理IP;
2、验证代理IP的可用性(使用代理IP去请求指定URL,根据响应验证代理IP是否生效);
3、将可用的代理IP保存到数据库;
常用代理网站:西刺代理 、云代理 、IP海 、无忧代理 、飞蚁代理 、快代理
三、代码实现
工程结构如下:
ipproxy.py
IPProxy代理类定义了要爬取的IP代理的字段信息和一些基础方法。
# -*- coding: utf-8 -*- import re import time from settings import PROXY_URL_FORMATTER schema_pattern = re.compile(r'http|https$', re.I) ip_pattern = re.compile(r'^([0-9]{1,3}.){3}[0-9]{1,3}$', re.I) port_pattern = re.compile(r'^[0-9]{2,5}$', re.I) class IPProxy: ''' { "schema": "http", # 代理的类型 "ip": "127.0.0.1", # 代理的IP地址 "port": "8050", # 代理的端口号 "used_total": 11, # 代理的使用次数 "success_times": 5, # 代理请求成功的次数 "continuous_failed": 3, # 使用代理发送请求,连续失败的次数 "created_time": "2018-05-02" # 代理的爬取时间 } ''' def __init__(self, schema, ip, port, used_total=0, success_times=0, continuous_failed=0, created_time=None): """Initialize the proxy instance""" if schema == "" or schema is None: schema = "http" self.schema = schema.lower() self.ip = ip self.port = port self.used_total = used_total self.success_times = success_times self.continuous_failed = continuous_failed if created_time is None: created_time = time.strftime('%Y-%m-%d', time.localtime(time.time())) self.created_time = created_time def _get_url(self): ''' Return the proxy url''' return PROXY_URL_FORMATTER % {'schema': self.schema, 'ip': self.ip, 'port': self.port} def _check_format(self): ''' Return True if the proxy fields are well-formed,otherwise return False''' if self.schema is not None and self.ip is not None and self.port is not None: if schema_pattern.match(self.schema) and ip_pattern.match(self.ip) and port_pattern.match(self.port): return True return False def _is_https(self): ''' Return True if the proxy is https,otherwise return False''' return self.schema == 'https' def _update(self, successed=False): ''' Update proxy based on the result of the request's response''' self.used_total = self.used_total + 1 if successed: self.continuous_failed = 0 self.success_times = self.success_times + 1 else: print(self.continuous_failed) self.continuous_failed = self.continuous_failed + 1 if __name__ == '__main__': proxy = IPProxy('HTTPS', '192.168.2.25', "8080") print(proxy._get_url()) <strong>本文来源gaodaima#com搞(代@码$网6</strong> print(proxy._check_format()) print(proxy._is_https())
settings.py
settings.py中汇聚了工程所需要的配置信息。
# 指定Redis的主机名和端口 REDIS_HOST = 'localhost' REDIS_PORT = 6379 # 代理保存到Redis key 格式化字符串 PROXIES_REDIS_FORMATTER = 'proxies::{}' # 已经存在的HTTP代理和HTTPS代理集合 PROXIES_REDIS_EXISTED = 'proxies::existed' # 最多连续失败几次 MAX_CONTINUOUS_TIMES = 3 # 代理地址的格式化字符串 PROXY_URL_FORMATTER = '%(schema)s://%(ip)s:%(port)s' USER_AGENT_LIST = [ "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1", "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6", "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1", "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5", "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3", "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24", "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24" ] # 爬取到的代理保存前先检验是否可用,默认True PROXY_CHECK_BEFOREADD = True # 检验代理可用性的请求地址,支持多个 PROXY_CHECK_URLS = {'https':['https://icanhazip.com'],'http':['http://icanhazip.com']}