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;
在《Python爬虫代理池搭建》一文中我们已经使用Python的 requests 模块简单实现了一个IP代理池搭建,但是爬取速度较慢。由于西刺代理、快代理和云代理等网站需要爬取的IP代理列表页多达上千页,使用此种方法来爬取其实并不适合。
本文将以快代理网站的IP代理爬取为例,示例如何使用 Scrapy-Redis 来爬取代理IP。
三、搭建代理池
scrapy 项目的目录结构如下:
items.py
# -*- coding: utf-8 -*- import re import scrapy from proxy_pool.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 ProxyPoolItem(scrapy.Item): # define the fields for your item here like: # name = scrapy.Field() ''' { "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 "original":"西刺代理", "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 } ''' schema = scrapy.Field() ip = scrapy.Field() port = scrapy.Field() original = scrapy.Field() used_total = scrapy.Field() success_times = scrapy.Field() continuous_failed = scrapy.Field() created_time = scrapy.Field() # 检查IP代理的格式是否正确 def _check_format(self): 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 # 获取IP代理的url def _get_url(self): return PROXY_URL_FORMATTER % {'schema': self['schema'], 'ip': self['ip'], 'port': self['port']}
kuai_proxy.py
# -*- coding: utf-8 -*- import re import time import scrapy from proxy_pool.utils import strip, logger from proxy_pool.items import ProxyPoolItem class KuaiProxySpider(scrapy.Spider): name = 'kuai_proxy' allowed_domains = ['kuaidaili.com'] start_urls = ['https://www.kuaidaili.com/free/inha/1/', 'https://www.kuaidaili.com/free/intr/1/'] def parse(self, response): logger.info('正在爬取:< ' + response.request.url + ' >') tr_list = response.css("div#list>table>tbody tr") for tr in tr_list: ip = tr.css("td[data-title='IP']::text").get() port = tr.css("td[data-title='PORT']::text").get() schema = tr.css("td[data-title='类型']::text").get() if schema.lower() == "http" or schema.lower() == "https": item = ProxyPoolItem() item['schema'] = strip(schema).lower() item['ip'] = strip(ip) item['port'] = strip(port) item['original'] = '快代理' item['created_time'] = time.strftime('%Y-%m-%d', time.localtime(time.time())) if item._check_format(): yield item next_page = response.xpath("//a[@class='active']/../following-sibling::li/a/@href").get() if next_page is not None: next_url = 'https://www.kuaidaili.com' + next_page yield scrapy.Request(next_url)
middlewares.py
# -*- coding: utf-8 -*- import random from proxy_pool.utils import logger # 随机选择 IP 代理下载器中间件 class RandomProxyMiddleware(object): # 从 settings 的 PROXIES 列表中随机选择一个作为代理 def process_request(self, request, spider): proxy = random.choice(spider.settings['PROXIES']) request.meta['proxy'] = proxy return None # 随机选择 User-Agent 的下载器中间件 class RandomUserAgentMiddleware(object): def process_request(self, request, spider): # 从 settings 的 USER_AGENTS 列表中随机选择一个作为 User-Agent user_agent = random.choice(spider.settings['USER_AGENT_LIST']) request.headers['User-Agent'] = user_agent return None def process_response(self, request, response, spider): # 验证 User-Agent 设置是否生效 logger.info("headers ::> User-Agent = " + str(request.headers['User-Agent'], encoding="utf8")) return response
pipelines.py
# -*- coding: utf-8 -*- import json import redis from proxy_pool.settings import REDIS_HOST,REDIS_PORT,REDIS_PARAMS,PROXIES_UNCHECKED_LIST,PROXIES_UNCHECKED_SET server = redis.StrictRedis(host=REDIS_HOST, port=REDIS_PORT,password=REDIS_PARAMS['password']) class ProxyPoolPipeline(object): # 将可用的IP代理添加到代理池队列 def process_item(self, item, spider): if not self._is_existed(item): server.rpush(PROXIES_UNCHECKED_LIST, json.dumps(dict(item),ensure_ascii=False)) # 检查IP代理是否已经存在 def _is_existed(self,item): added = server.sadd(PROXIES_UNCHECKED_SET, item._get_url()) return added == 0
settings.py
# -*- coding: utf-8 -*- BOT_NAME = 'proxy_pool' SPIDER_MODULES = ['proxy_pool.spiders'] NEWSPIDER_MODULE = 'proxy_pool.spiders' # 保存未检验代理的Redis key PROXIES_UNCHECKED_LIST = 'proxies:unchecked:list' # 已经存在的未检验HTTP代理和HTTPS代理集合 PROXIES_UNCHECKED_SET = 'proxies:unchecked:set' # 代理地址的格式化字符串 PROXY_URL_FORMATTER = '%(schema)s://%(ip)s:%(port)s' # 通用请求头字段 DEFAULT_REQUEST_HEADERS = { 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8', 'Accept-Encoding': 'gzip, deflate, br', 'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,zh-TW;q=0.7', 'Connection': 'keep-alive' } # 请求太频繁会导致 503 ,在此设置 5 秒请求一次 DOWNLOAD_DELAY = 5 # 250 ms of delay 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" ] # Obey robots.txt rules ROBOTSTXT_OBEY = False # Enable or disable downloader middlewares # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html DOWNLOADER_MIDDLEWARES = { 'proxy_pool.middlewares.RandomUserAgentMiddleware': 543, # 'proxy_pool.middlewares.RandomProxyMiddleware': 544, } ITEM_PIPELINES = { 'proxy_pool.pipelines.ProxyPoolPipeline': 300, } PROXIES = [ "https://171.13.92.212:9797", "https://164.163.234.210:8080", "https://143.202.73.219:8080", "https://103.75.166.15:8080" ] ###################################################### ##############下面是Scrapy-Redis相关配置################ ###################################################### # 指定Redis的主机名和端口 REDIS_HOST = '172.16.250.238' REDIS_PORT = 6379 REDIS_PARAMS = {'password': '123456'} # 调度器启用Redis存储Requests队列 SCHEDULER = "scrapy_redis.scheduler.Scheduler" # 确保所有的爬虫实例使用Redis进行重复过滤 DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter" # 将Requests队列持久化到Redis,可支持暂停或重启爬虫 SCHEDULER_PERSIST = True # Requests的调度策略,默认优先级队列 SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.PriorityQueue'
utils.py
# -*- coding: utf-8 -*- import logging # 设置日志输出格式 logging.basicConfig(level=logging.INFO, format='[%(asctime)-15s] [%(levelname)8s] [%(name)10s ] - %(message)s (%(filename)s:%(lineno)s)', datefmt='%Y-%m-%d %T' ) logger = logging.getLogger(__name__) # Truncate header and tailer blanks def strip(data): if data is not None: return data.strip() return data
《魔兽世界》大逃杀!60人新游玩模式《强袭风暴》3月21日上线
暴雪近日发布了《魔兽世界》10.2.6 更新内容,新游玩模式《强袭风暴》即将于3月21 日在亚服上线,届时玩家将前往阿拉希高地展开一场 60 人大逃杀对战。
艾泽拉斯的冒险者已经征服了艾泽拉斯的大地及遥远的彼岸。他们在对抗世界上最致命的敌人时展现出过人的手腕,并且成功阻止终结宇宙等级的威胁。当他们在为即将于《魔兽世界》资料片《地心之战》中来袭的萨拉塔斯势力做战斗准备时,他们还需要在熟悉的阿拉希高地面对一个全新的敌人──那就是彼此。在《巨龙崛起》10.2.6 更新的《强袭风暴》中,玩家将会进入一个全新的海盗主题大逃杀式限时活动,其中包含极高的风险和史诗级的奖励。
《强袭风暴》不是普通的战场,作为一个独立于主游戏之外的活动,玩家可以用大逃杀的风格来体验《魔兽世界》,不分职业、不分装备(除了你在赛局中捡到的),光是技巧和战略的强弱之分就能决定出谁才是能坚持到最后的赢家。本次活动将会开放单人和双人模式,玩家在加入海盗主题的预赛大厅区域前,可以从强袭风暴角色画面新增好友。游玩游戏将可以累计名望轨迹,《巨龙崛起》和《魔兽世界:巫妖王之怒 经典版》的玩家都可以获得奖励。
更新动态
- 凤飞飞《我们的主题曲》飞跃制作[正版原抓WAV+CUE]
- 刘嘉亮《亮情歌2》[WAV+CUE][1G]
- 红馆40·谭咏麟《歌者恋歌浓情30年演唱会》3CD[低速原抓WAV+CUE][1.8G]
- 刘纬武《睡眠宝宝竖琴童谣 吉卜力工作室 白噪音安抚》[320K/MP3][193.25MB]
- 【轻音乐】曼托凡尼乐团《精选辑》2CD.1998[FLAC+CUE整轨]
- 邝美云《心中有爱》1989年香港DMIJP版1MTO东芝首版[WAV+CUE]
- 群星《情叹-发烧女声DSD》天籁女声发烧碟[WAV+CUE]
- 刘纬武《睡眠宝宝竖琴童谣 吉卜力工作室 白噪音安抚》[FLAC/分轨][748.03MB]
- 理想混蛋《Origin Sessions》[320K/MP3][37.47MB]
- 公馆青少年《我其实一点都不酷》[320K/MP3][78.78MB]
- 群星《情叹-发烧男声DSD》最值得珍藏的完美男声[WAV+CUE]
- 群星《国韵飘香·贵妃醉酒HQCD黑胶王》2CD[WAV]
- 卫兰《DAUGHTER》【低速原抓WAV+CUE】
- 公馆青少年《我其实一点都不酷》[FLAC/分轨][398.22MB]
- ZWEI《迟暮的花 (Explicit)》[320K/MP3][57.16MB]