本文转自:https://blog.csdn.net/qq_42415326/article/details/95044280
使用的主要模块:
- requests,lxml,pymongo,Flask
代理池工作流程
image.png文字描述
- 代理IP采集模块:抓取代理IP—>校验代理IP的可用性—>可用存储数据库
- 校验模块:读取数据库的代理IP—>校验代理IP可用性—>更新或删除代理IP
- 带来API模块:从数据库中获取稳定可用的代理IP,供其他爬虫使用
代理池项目结构:
image.png- mongo_pool模块:代理IP增删改查模块
- proxy_spider包:采集代理IP
- httpbin_validator模块:检测代理的可用性—speed,协议类型,匿名程度(原因: 网站上所标注的协议类型和匿名类型是不准确的)
- proxy_api模块:提供爬虫或稳定可用代理IP和指定不可用域名的接口
- proxy_test模块:获取数据库中代理IP,定期检测可用性
- dbmodle模块:代理IP数据模型
- main模块:程序入口
- http模块:提供随机User-Agent的请求头
- log模块:记录日志
- settings模块:项目配置文件
项目实现思路
先实现不依赖其他模块的基础模块,然后在实现具体功能模块
1. 实现代理IP的数据模型类(dbmodle.py)
'''
代理ip数据模型模块
定义一个类, 继承object
实现init方法, 负责初始化, 包含如下字段:
ip: 代理的IP地址
port: 代理IP的端口号
protocol: 代理IP支持的协议类型,http是0, https是1, https和http都支持是2
nick_type: 代理IP的匿名程度, 高匿:0, 匿名: 1, 透明:2
speed: 代理IP的响应速度, 单位s
area: 代理IP所在地区
score: 代理IP的评分, 默认分值可以通过配置文件进行配置. 在进行代理可用性检查的时候, 每遇到一次请求失败就减1份, 减到0的时候从池中删除. 如果检查代理可用, 就恢复默认分值
disable_domains: 不可用域名列表, 有些代理IP在某些域名下不可用, 但是在其他域名下可用
创建配置文件: settings.py; 定义MAX_SCORE = 50,
'''
from settings import MAX_SCORE
class Proxy(object):
def __init__(self,ip,port,protocol=-1,nick_type=-1,speed=-1,area=None,score=MAX_SCORE,disuseble_dommains=[]):
#代理ip的地址
self.ip = ip
#代理ip的端口号
self.port = port
#代理ip支持协议类型:支持http为0,支持https为1,都支持为2
self.protocol = protocol
#代理ip的匿名程度:高匿为0,匿名为1,透明为2
self.nick_type =nick_type
#代理ip的响应速度
self.speed = speed
#代理ip所在地区
self.area = area
#代理ip的评分,衡量代理ip的可用性
self.score =score
#代理ip的不可用域名列表
self.disuseble_dommains =disuseble_dommains
def __str__(self):
#返回数据字符串
return str(self.__dict)
2. 实现日志记录模块(log.py)
目的:
能够方便的对程序进行调试
能够记录程序的运行状态
记录错误信息
实现:日志模块在网上有很多现成的实现, 我们开发的时候, 通常不会再自己写; 而是使用拿来主义,拿来用就完了。
把日志模块中的相关配置信息放到配置文件中
修改日志模块代码,使用配置文件中的配置信息
'''
记录日志的模块
'''
import sys,os
#Python的标准日志模块:logging
import logging
#将上级目录添加到搜索路径中
sys.path.append("../")
from settings import LOG_LEVEL,LOG_FMT ,LOG_DATEFMT,LOG_FILENAME
class Logger(object):
def __init__(self):
#获取一个logger对象
self._logger = logging.getLogger()
#设置format对象
self.formatter = logging.Formatter(fmt=LOG_FMT,datefmt=LOG_DATEFMT)
#设置日志输出——文件日志模式
self._logger.addHandler(self._get_file_handler(LOG_FILENAME))
#设置日志输出——终端日志模式
self._logger.addHandler(self._get_console_handler())
# 4. 设置日志等级
self._logger.setLevel(LOG_LEVEL)
def _get_file_handler(self, filename):
'''
返回一个文件日志handler
'''
# 获取一个输出为文件日志的handler
filehandler = logging.FileHandler(filename=filename,encoding="utf-8")
# 设置日志格式
filehandler.setFormatter(self.formatter)
# 返回
return filehandler
def _get_console_handler(self):
'''
返回一个输出到终端日志handler
'''
#获取一个输出到终端的日志handler
console_handler = logging.StreamHandler(sys.stdout)
#设置日志格式
console_handler.setFormatter(self.formatter)
# 返回handler
return console_handler
#属性装饰器,返回一个logger对象
@property
def logger(self):
return self._logger
# 初始化并配一个logger对象,达到单例
# 使用时,直接导入logger就可以使用
logger = Logger().logger
if __name__ == '__main__':
print(logger)
logger.debug("调试信息")
logger.info("状态信息")
logger.warning("警告信息")
logger.error("错误信息")
logger.critical("严重错误信息")
3.校验代理IP的协议类型、匿名程度,速度(httpbin_validator.py)
'''
代理IP速度检查: 就是发送请求到获取响应的时间间隔
匿名程度检查:
对 http://httpbin.org/get 或 https://httpbin.org/get 发送请求
if : origin 中有','分割的两个IP就是透明代理IP
if : headers 中包含 Proxy-Connection 说明是匿名代理IP
else : 就是高匿代理IP
检查代理IP协议类型:
如果 http://httpbin.org/get 发送请求可以成功, 说明支持http协议
如果 https://httpbin.org/get 发送请求可以成功, 说明支持https协议
'''
import sys
import time
import requests
import json
sys.path.append("..")
from proxy_utils import random_headers
from settings import CHECK_TIMEOUT
from proxy_utils.log import logger
from dbmodle import Proxy
def check_proxy(proxy):
'''
分别判断http和https是否请求成功
'''
#代理ip
proxies = {
'http':'http://{}:{}'.format(proxy.ip,proxy.port),
'https':'https://{}:{}'.format(proxy.ip,proxy.port),
}
http,http_nick_type,http_speed = http_check_proxies(proxies)
https,https_nick_type,https_speed = http_check_proxies(proxies,False)
if http and https:
proxy.protocol = 2 #支持https和http
proxy.nick_type =http_nick_type
proxy.speed = http_speed
elif http:
proxy.protocol = 0 #只支持http
proxy.nick_type =http_nick_type
proxy.speed = http_speed
elif https:
proxy.protocol = 1 #只支持https
proxy.nick_type =https_nick_type
proxy.speed = https_speed
else:
proxy.protocol = -1
proxy.nick_type = -1
proxy.speed = -1
#logger.debug(proxy)
return proxy
def http_check_proxies(proxies,isHttp = True):
'''
代理ip请求校验ip
'''
nick_type = -1 #匿名程度变量
speed = -1 #响应速度变量
if isHttp:
test_url = 'http://httpbin.org/get'
else:
test_url = 'https://httpbin.org/get'
#requests库请求test_url
try:
#响应时间
start_time = time.time()
res = requests.get(test_url,headers = random_headers.get_request_headers(),proxies = proxies,timeout = TCHECK_TIMEOUT)
end_time = time.time()
cost_time =end_time-start_time
if res.status_code == 200:
#响应速度
speed = round(cost_time,2)
#转换为字典
res_dict = json.loads(res.text)
#获取请求来源ip
origin_ip = res_dict['origin']
#获取响应请求头中'Proxy-Connection',若有,说明是匿名代理
proxy_connection = res_dict['headers'].get('Proxy-Conntion',None)
if "," in origin_ip:
#如果响应内容中的源ip中有‘,’分割的两个ip的话及时透明代理ip
nick_type = 2 #透明
elif proxy_connection:
#'Proxy-Connection'存在说明是匿名ip
nick_type = 1 #匿名
else:
nick_type =0 #高匿
return True,nick_type,speed
else:
return False,nick_type,speed
except Exception as e:
#logger.exception(e)
return False,nick_type,speed
if __name__ == '__main__':
proxy = Proxy('60.13.42.94','9999')
result = check_proxy(proxy)
print(result)
4. 实现数据库模块(增删改查功能和api功能——mongo_pool.py)
定义MongoPool类, 继承object
- 在
init
中, 建立数据连接, 获取要操作的集合, 在del
方法中关闭数据库连接 - 提供基础的增删改查功能
- 实现插入功能
- 实现修改该功能
- 实现删除代理: 根据代理的IP删除代理
- 查询所有代理IP的功能
- 提供代理API模块使用的功能
- 实现查询功能: 根据条件进行查询, 可以指定查询数量, 先分数降序, 速度升序排, 保证优质的代理IP在上面.
- 实现根据协议类型 和 要访问网站的域名, 获取代理IP列表
- 实现根据协议类型 和 要访问网站的域名, 随机获取一个代理IP
- 实现把指定域名添加到指定IP的disable_domain列表中.
'''
针对proxies集合进行数据库的增删改查的操作,并提供代理api使用
'''
import random
import pymongo
import sys
sys.path.append("..")
from settings import MONGO_URL
from proxy_utils.log import logger
from dbmodle import Proxy
class MongoPool(object):
def __init__(self):
#连接数据库
self.client = pymongo.MongoClient(MONGO_URL)
#获取操作字典集
self.proxies = self.client['proxy_pool']['proxies']
def __del__(self):
#关闭数据库连接
self.client.close()
def insert(self,proxy):
'''
代理ip插入方法
'''
count = self.proxies.count_documents({'_id':proxy.ip})
if count == 0:
#Proxy对象转换为字典
proxy_dict = proxy.__dict__
#主键
proxy_dict['_id'] = proxy.ip
#向proxies字典集中插入代理ip
self.proxies.insert_one(proxy_dict)
logger.info('插入新的代理:{}'.format(proxy))
else:
logger.warning('已经存在的代理{}'.format(proxy))
def update(self,proxy):
'''
修改更新数据库中代理ip
'''
self.proxies.update_one({'_id':proxy.ip},{'$set':proxy.__dict__})
logger.info('更新代理ip:{}'.format(proxy))
def delete(self,proxy):
'''
删除数据库中代理ip
'''
self.proxies.delete_one({'_id':proxy.ip})
logger.info('删除代理ip:{}'.format(proxy))
def find_all(self):
'''
查询数据库中所有的代理ip
'''
cursor = self.proxies.find()
for item in cursor:
#删除_id键值对
item.pop('_id')
proxy = Proxy(**item)
#生成器yield
yield proxy
def limit_find(self,conditions = {},count = 0):
'''根据条件进行查询,
可以指定查询数量, 先分数降序, 速度升序排,
保证优质的代理IP在上面'''
cursor = self.proxies.find(conditions,limit = count).sort([
('score',pymongo.DESCENDING),('speed',pymongo.ASCENDING)])
#接受查询所得代理IP
proxy_list = []
for item in cursor:
itme.pop('_id')
proxy = Proxy(**item)
proxy_list.append(proxy)
return proxy_list
def get_proxies(self,protocol =None,domain = None,nick_type =0,count = 0):
'''
实现根据协议类型和要访问网站的域名, 获取代理IP列表
'''
conditions = {'nike_type':nick_type}
if protocol is None:
conditions['protocol'] = 2
elif protocol.lower() == 'http':
conditions['protocol'] ={'$in':[0,2]}
else:
conditons['protocol'] ={'$in':[1,2]}
if domain:
conditons['disable_domains'] = {'$nin':[domain]}
return self.limit_find(conditions,count = count)
def random_proxy(self,protocol = None,domain =None,count = 0,nick_type =0):
'''
根据协议类型 和 要访问网站的域名, 随机获取一个代理IP
'''
proxy_list = self.get_proxies(protocol =protocol,domain = domain ,count = count ,nick_type =nick_type)
return random.choice(proxy_list)
def add_disable_domain(self,ip,domain):
'''
把指定域名添加到指定IP的disable_domain列表中,没有才添加
'''
count = self.proxies.count_documents({'_id':ip,'disable_domains':domain})
if count == 0:
self.proxies.update_one({'_id':ip},{'$push':{'disable_domains':domain}})
if __name__ == '__main__':
mongo = MongoPool()
#插入测试
#proxy = Proxy('202.104.113.32','53281')
#mongo.insert(proxy)
#更新测试
#proxy = Proxy('202.104.113.32','8888')
#mongo.update(proxy)
#删除测试
#proxy = Proxy('202.104.113.32','8888')
#mongo.delete(proxy)
#查询所有测试
#for proxy in mongo.find_all():
#print(proxy)
5.实现随机获取User-Agent 的请求头模块(random_headers.py)
'''
获取随机User-Agent的请求头
'''
import random
#用户代理User-Agent列表
USER_AGENTS = [
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
"Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
"Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
"Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
"Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
"Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
"Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
"Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
"Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
"Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
"Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
"Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
"Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
"UCWEB7.0.2.37/28/999",
"NOKIA5700/ UCWEB7.0.2.37/28/999",
"Openwave/ UCWEB7.0.2.37/28/999",
"Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",
# iPhone 6:
"Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25",
]
#随机获取一个用户代理User-Agent的请求头
def get_request_headers():
headers = {
'User-Agent':random.choice(USER_AGENTS),
'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3',
'Accept-language':'zh-CN,zh;q=0.9,en;q=0.8',
'Referer':'https://www.baidu.com',
'Accept-Encoding':'gzip, deflate,br',
'Connection':'keep-alive',
}
return headers
if __name__ == '__main__':
#测试随机与否
print(get_request_headers())
print("------------"*20)
print(get_request_headers())
6.实现通用爬虫,作为具体爬虫的父类(base_poxies.py)
'''
通用爬虫:通过指定URL列表, 分组XPATH和组内XPATH, 来提取不同网站的代理IP
定义一个BaseSpider类, 继承object
- 提供三个类成员变量:urls, group_xpath, detail_xpath: ip, port, area
- 提供初始方法, 传入爬虫URL列表, 分组XPATH, 详情(组内)XPATH
- 对外提供一个获取代理IP的方法
'''
import requests
import sys
import time,random
from lxml import etree
sys.path.append('..')
from proxies_utils.random_headers import get_request_headers
from dbmodle import Proxy
class BaseSpider(object):
#类成员变量
#代理IP网址的URL的列表
urls =[]
#分组XPATH, 获取包含代理IP信息标签列表的XPATH
group_xpath = ''
#组内XPATH, 获取代理IP详情的信息XPATH, 格式为: {'ip':'xx', 'port':'xx', 'area':'xx'}
detail_xpath ={}
def __init__(self,urls =[],group_xpath='',detail_xpath={}):
#提供初始方法, 传入爬虫URL列表, 分组XPATH, 详情(组内)XPATH
if urls:
self.urls =urls
if group_xpath:
self.group_xpath =group_xpath
if detail_xpath:
self.detail_xpath=detail_xpath
def get_proxies(self):
#获取页面数据
for url in self.urls:
page_html = self.get_page(url)
proxies =self.get_html_proxies(page_html)
#yeild from 返回的是proxies内的数据
yield from proxies
def get_page(self,url):
#请求页面数据
res =requests.get(url,headers = get_request_headers())
#每次请求url休眠1秒
time.sleep(random.uniform(1,5))
return res.content
def get_html_proxies(self,page_html):
element = etree.HTML(page_html)
trs = element.xpath(self.group_xpath)
for tr in trs:
ip = self.get_list_first(tr.xpath(self.detail_xpath['ip']))
port = self.get_list_first(tr.xpath(self.detail_xpath['port']))
area = self.get_list_first(tr.xpath(self.detail_xpath['area']))
proxy = Proxy(ip,port,area=area)
yield proxy
def get_list_first(self,lst):
#返回列表的第一个元素
return lst[0] if len(lst) !=0 else ''
if __name__ == '__main__':
config = {
'urls':['http://www.ip3366.net/free/?stype=1&page={}'.format(i) for i in range(1,3)],
'group_xpath':'//*[@id="list"]/table/tbody/tr',
'detail_xpath':{
'ip':'./td[1]/text()',
'port':'./td[2]/text()',
'area':'./td[5]/text()',
}
}
spider = BaseSpider(**config)
for proxy in spider.get_proxies():
print(proxy)
7.实现具体的爬虫类(proxy_spiders.py)
'''
实现具体的爬虫类
'''
#import time
#import random
import requests
import sys
sys.path.append('../')
#import re
#import js2py
from proxy_spider.base_spider import BaseSpider
class XiciSpider(BaseSpider):
'''西刺代理爬虫 '''
urls = ['http://www.xicidaili.com/nn/{}'.format(i) for i in range(1,21)]
group_xpath = '//*[@id="ip_list"]//tr[position()>1]'
detail_xpath = {
'ip':'./td[2]/text()',
'port':'./td[3]/text()',
'area':'./td[4]/a/text()',
}
class Ip3366Spider(BaseSpider):
'''
ip3366代理爬虫
'''
urls = ['http://www.ip3366.net/free/?stype={}&page={}'.format(i,j) for i in range(1,4,2) for j in range(1,8)]
group_xpath = '//*[@id="list"]/table/tbody/tr'
detail_xpath = {
'ip':'./td[1]/text()',
'port':'./td[2]/text()',
'area':'./td[5]/text()',
}
class kuaiSpider(BaseSpider):
'''
快代理爬虫
'''
urls = ['http://www.kuaidaili.com/free/in{}/{}'.format(i,j) for i in ['ha','tr'] for j in range(1,21)]
group_xpath = '//*[@id="list"]/table/tbody/tr'
detail_xpath = {
'ip':'./td[1]/text()',
'port':'./td[2]/text()',
'area':'./td[5]/a/text()',
}
'''
def get_page(self,url):
#随机等待时间
time.sleep(random.uniform(1,2))
return super().get_page(url)
'''
class Free89ipSpider(BaseSpider):
'''
89ip代理爬虫
'''
urls = ['http://www.89ip.cn/index{}.html'.format(i) for i in range(1,17)]
group_xpath = '//div[3]//table/tbody/tr'
detail_xpath = {
'ip':'./td[1]/text()',
'port':'./td[2]/text()',
'area':'./td[3]/text()',
}
def get_page(self,url):
return super().get_page(url).decode()
def get_proxies(self):
proxies = super().get_proxies()
for item in proxies:
item.ip = str(item.ip).replace("\n","").replace("\t","")
item.area = str(item.area).replace("\n","").replace("\t","")
item.port = str(item.port).replace("\n","").replace("\t","")
#返回Proxy对象
yield item
if __name__ == '__main__':
spider = Free89ipSpider()
count= 0
for proxy in spider.get_proxies():
count+=1
print(proxy)
8. 实现运行爬虫模块(run_spider.py)
创建RunSpider类
run方法运行爬虫, 作为运行爬虫的入口,获取爬虫列表并运行,检测代理IP,可用,写入数据库并处理爬虫内部异常
使用协程异步来执行每一个爬虫任务, 以提高抓取代理IP效率
使用schedule模块, 实现每隔一定的时间, 执行一次爬取任务
'''
from gevent import monkey
monkey.patch_all()
from gevent.pool import Pool
import importlib
import sys,time
import schedule
sys.path.append('../')
from settings import PROXIES_SPIDERS,SPIDERS_RUN_INTERVAL
from proxy_validate.httpbin_validator import check_proxy
from proxies_db.mongo_pool import MongoPool
from proxies_utils.log import logger
class RunSpider(object):
def __init__(self):
self.mongo_pool = MongoPool()
self.coroutine_pool = Pool()
def get_spider_from_settings(self):
'''
获取配置文件中的具体爬虫列表创建对象
'''
for full_class_name in PROXIES_SPIDERS:
module_name,class_name = full_class_name.rsplit('.',maxsplit =1)
#动态导入模块
module = importlib.import_module(module_name)
cls = getattr(module,class_name)
spider = cls()
yield spider
def run(self):
'''
遍历爬虫对象,执行get_proxies方法
'''
spiders = self.get_spider_from_settings()
for spider in spiders:
self.coroutine_pool.apply_async(self.__run_one_spider,args=(spider,))
#当前线程等待爬虫执行完毕
self.coroutine_pool.join()
def __run_one_spider(self,spider):
try:
for proxy in spider.get_proxies():
time.sleep(0.1)
checked_proxy = check_proxy(proxy)
if proxy.speed != -1:
self.mongo_pool.insert(checked_proxy)
except Exception as er:
logger.exception(er)
logger.exception("爬虫{} 出现错误".format(spider))
@classmethod
def start(cls):
'''
类方法,依据配置文件汇总的时间间隔run爬虫,单位小时
'''
rs = RunSpider()
rs.run()
schedule.every(SPIDERS_RUN_INTERVAL).hours.do(rs.run)
while 1:
schedule.run_pending()
time.sleep(60)
if __name__ == '__main__':
#类方法调用
RunSpider.start()
#app = RunSpider()
#app.run()
#测试schedue
'''def task():
print("haha")
schedule.every(10).seconds.do(task)
while 1:
schedule.run_pending()
time.sleep(1)'''
9. 代理IP检查模块(proxy_test.py)
'''
定期检测数据库中的代理ip的可用性,分数评级,更新数据库
'''
from gevent import monkey
monkey.patch_all()
from gevent.pool import Pool
from queue import Queue
import schedule
import sys
sys.path.append('../')
from proxy_validate.httpbin_validator import check_proxy
from proxies_db.mongo_pool import MongoPool
from settings import TEST_PROXIES_ASYNC_COUNT,MAX_SCORE,TEST_RUN_INTERVAL
class DbProxiesCheck(object):
def __init__(self):
#创建操作数据库对象
self.mongo_pool = MongoPool()
#待检测ip队列
self.queue = Queue()
#协程池
self.coroutine_pool = Pool()
#异步回调函数
def __check_callback(self,temp):
self.coroutine_pool.apply_async(self.__check_one,callback = self.__check_one())
def run(self):
#处理检测代理ip核心逻辑
proxies = self.mongo_pool.find_all()
for proxy in proxies:
self.queue.put(proxy)
#开启多异步任务
for i in range(TEST_PROXIES_ASYNC_COUNT):
#异步回调,死循环执行该方法
self.coroutine_pool.apply_async(self.__check_one,callback =self.__check_one())
#当前线程等待队列任务完成
self.queue.join()
def __check_one(self):
#检查一个代理ip可用性
#从队列中获取一个proxy
proxy = self.queue.get()
checked_proxy = check_proxy(proxy)
if checked_proxy.speed == -1:
checked_proxy.score -= 1
if checked_proxy.score == 0:
self.mongo_pool.delete(checked_proxy)
else:
self.mongo_pool.update(checked_proxy)
else:
checked_proxy.score = MAX_SCORE
self.mongo_pool.updata(checked_proxy)
#调度队列的task_done方法(一个任务完成)
self.queue.task_done()
@classmethod
def start(cls):
'''
类方法,依据配置文件的时间间隔运行检测数据库中的ip可用性,单位小时
'''
test = DbProxiesCheck()
test.run()
schedule.every(TEST_RUN_INTERVAL).hours.do(test.run)
while 1:
schedule.run_pending()
time.sleep(60)
if __name__ == '__main__':
DbProxiesCheck.start()
#test = DbProxiesCheck()
#test.run()
10. 代理IP池的API模块(proxy_api.py)
'''
为爬虫提供稳定可用的代理ip的接口
根据协议类型和域名,提供随机的稳定可用ip的服务
根据协议类型和域名,提供获取多个高可用代理ip的服务
给指定ip上追加不可用域名的服务
'''
from flask import Flask
from flask import request
import json
from proxies_db.mongo_pool import MongoPool
from settings import PROXIES_MAX_COUNT
class ProxyApi(object):
def __init__(self):
self.app = Flask(__name__)
#操作数据库的对象
self.mongo_pool = MongoPool()
#获取接口url中参数
@self.app.route('/random')
def random():
protocol = request.args.get('protocol')
domain = request.args.get('domain')
proxy = self.mongo_pool.random_proxy(protocal,domain,count = PROXIES_MAX_COUNT)
if protocol:
return '{}://{}:{}'.format(protocol,proxy.ip,proxy.port)
else:
return '{}:{}'.format(proxy.ip,proxy.port)
@self.app.route('/proxies')
def proxies():
protocol = request.args.get('protocol')
domain = request.args.get('domain')
proxies =self.mongo_pool.get_proxies(protocol,domain,count =PROXIES_MAX_COUNT)
#proxies是proxy对象构成的列表,需要转换为字典的列表
proxies_dict_list =[proxy.__dict__ for proxy in proxies]
return json.dumps(proxies_dict_list)
@self.app.route('/disabldomain')
def disable_domain():
ip = request.args.get('ip')
domain = request.args.get('domain')
if ip is None:
return '请提供ip参数'
if domain is None:
return '请提供域名domain参数'
self.mongo_pool.add_disable_domain(ip,domain)
return '{} 禁用域名 {} 成功'.format(ip,domain)
def run(self,debug):
self.app.run('0.0.0.0',port = 16888,debug = debug)
@classmethod
def start(cls,debug = None):
proxy_api = cls()
proxy_api.run(debug = debug)
if __name__ == '__main__':
ProxyApi.start(debug = True)
#proxy_api = ProxyApi()
#proxy_api.run(debug = True)
11. 代理池启动入口(main.py)
'''
代理池统一入口:
开启多个进程,分别启动,爬虫,检测代理ip,WEB服务
'''
from multiprocessing import Process
from proxy_spider.run_spider import RunSpider
from proxy_test import DbProxiesCheck
from proxy_api import ProxyApi
def run():
process_list = []
#启动爬虫
process_list.append(Process(target = RunSpider.start))
#启动检测
process_list.append(Process(target = DbProxiesCheck.start))
#启动web服务
process_list.append(Process(target = ProxyApi.start))
for process in process_list:
#设置守护进程
process.daemon = True
process.start()
#主进程等待子进程的完成
for process in process_list:
process.join()
if __name__ == '__main__':
run()
12 .配置文件模块(settings.py)
#默代理IP的默认最高分数
MAX_SCORE =50
import logging
#日志模块默认配置:
# 默认等级
LOG_LEVEL = logging.DEBUG
#默认日志格式
LOG_FMT = '%(asctime)s %(filename)s [line:%(lineno)d] %(levelname)s: %(message)s'
# 默认时间格式
LOG_DATEFMT = '%Y-%m-%d %H:%M:%S'
# 默认日志文件名称
LOG_FILENAME = 'log.log'
#请求超时参数
CHECK_TIMEOUT = 10
#mongodb的URL配置
MONGO_URL = 'mongodb://127.0.0.1:27017/'
#具体爬虫的配置列表
PROXIES_SPIDERS = [
"proxy_spider.proxy_spiders.XiciSpider",
"proxy_spider.proxy_spiders.Ip3366Spider",
"proxy_spider.proxy_spiders.kuaiSpider",
"proxy_spider.proxy_spiders.Free89ipSpider",
]
#爬虫间隔自动运行时间
SPIDERS_RUN_INTERVAL = 4
#配置检测代理ip的异步数量
TEST_PROXIES_ASYNC_COUNT = 10
#db中ip间隔自动运行时间
TEST_RUN_INTERVAL = 2
#随机获取代理ip的最大数量
PROXIES_MAX_COUNT = 50
网友评论