爬虫之代理池维护

一 准备工作

1 安装aiohttp

(venv) E:\WebSpider>pip3 install aiohttp

2 安装flask

(venv) E:\WebSpider>pip install flask

二 代理池的模块

1 存储模块：负载存储抓取下来的代理。存储模块使用Redis的有序集合，用来做代理的去重和状态标识，同时它也是中心模块和基础模块，将其他模块串联起来。

2 获取模块：需要定时在各大代理网址抓取代理。将获取的代理传递给存储模块，并保存到数据库。

3 检测模块：需要定时检测数据库中的代理。并对代理进行检测，根据不同的检查结果对代理设置不同的标识。

4 接口模块：需要用API来提取对外服务的接口。接口通过连接数据库并通过Web形式返回可用的代理。

三 代理池的实现

1 存储模块实现

import redis
from proxypool.error import PoolEmptyError
from proxypool.setting import REDIS_HOST, REDIS_PORT, REDIS_PASSWORD, REDIS_KEY
from proxypool.setting import MAX_SCORE, MIN_SCORE, INITIAL_SCORE
from random import choice
import re


class RedisClient(object):
    def __init__(self, host=REDIS_HOST, port=REDIS_PORT, password=REDIS_PASSWORD):
        """
        初始化
        :param host: Redis 地址
        :param port: Redis 端口
        :param password: Redis密码
        """
        self.db = redis.StrictRedis(host=host, port=port, password=password, decode_responses=True)
    
    def add(self, proxy, score=INITIAL_SCORE):
        """
        添加代理，设置分数为最高
        :param proxy: 代理
        :param score: 分数
        :return: 添加结果
        """
        if not re.match('\d+\.\d+\.\d+\.\d+\:\d+', proxy):
            print('代理不符合规范', proxy, '丢弃')
            return
        if not self.db.zscore(REDIS_KEY, proxy):
            proxy1 = proxy
            print(score)
            print(proxy)
            #return self.db. zadd('zz', 'n1', 1)
            #return self.db.zadd(REDIS_KEY, '171.42.172.114:8060',10)
            #return self.db.zadd(REDIS_KEY, proxy1=score)
            return self.db.zadd(REDIS_KEY,  {proxy1:score})
    
    def random(self):
        """
        随机获取有效代理，首先尝试获取最高分数代理，如果不存在，按照排名获取，否则异常
        :return: 随机代理
        """
        result = self.db.zrangebyscore(REDIS_KEY, MAX_SCORE, MAX_SCORE)
        if len(result):
            return choice(result)
        else:
            result = self.db.zrevrange(REDIS_KEY, 0, 100)
            if len(result):
                return choice(result)
            else:
                raise PoolEmptyError
    
    def decrease(self, proxy):
        """
        代理值减一分，小于最小值则删除
        :param proxy: 代理
        :return: 修改后的代理分数
        """
        score = self.db.zscore(REDIS_KEY, proxy)
        if score and score > MIN_SCORE:
            print('代理', proxy, '当前分数', score, '减1')
            #return self.db.zincrby(REDIS_KEY, proxy, -1)
            return self.db.zincrby(REDIS_KEY,-1, proxy,)
        else:
            print('代理', proxy, '当前分数', score, '移除')
            return self.db.zrem(REDIS_KEY, proxy)
    
    def exists(self, proxy):
        """
        判断是否存在
        :param proxy: 代理
        :return: 是否存在
        """
        return not self.db.zscore(REDIS_KEY, proxy) == None
    
    def max(self, proxy):
        """
        将代理设置为MAX_SCORE
        :param proxy: 代理
        :return: 设置结果
        """
        print('代理', proxy, '可用，设置为', MAX_SCORE)
        return self.db.zadd(REDIS_KEY, {proxy: MAX_SCORE})
    
    def count(self):
        """
        获取数量
        :return: 数量
        """
        return self.db.zcard(REDIS_KEY)
    
    def all(self):
        """
        获取全部代理
        :return: 全部代理列表
        """
        return self.db.zrangebyscore(REDIS_KEY, MIN_SCORE, MAX_SCORE)
    
    def batch(self, start, stop):
        """
        批量获取
        :param start: 开始索引
        :param stop: 结束索引
        :return: 代理列表
        """
        return self.db.zrevrange(REDIS_KEY, start, stop - 1)


if __name__ == '__main__':
    conn = RedisClient()
    result = conn.batch(680, 688)
    print(result)

关于Redis操作，可参考：https://blog.csdn.net/hongyd/article/details/84588524

https://blog.csdn.net/qq_41389266/article/details/86674910

2 获取模块实现

import json
import re
from .utils import get_page
from pyquery import PyQuery as pq


class ProxyMetaclass(type):
    def __new__(cls, name, bases, attrs):
        count = 0
        attrs['__CrawlFunc__'] = []
        for k, v in attrs.items():
            if 'crawl_' in k:
                attrs['__CrawlFunc__'].append(k)
                count += 1
        attrs['__CrawlFuncCount__'] = count
        return type.__new__(cls, name, bases, attrs)


class Crawler(object, metaclass=ProxyMetaclass):
    def get_proxies(self, callback):
        proxies = []
        for proxy in eval("self.{}()".format(callback)):
            print('成功获取到代理', proxy)
            proxies.append(proxy)
        return proxies
       
    def crawl_daili66(self, page_count=4):
        """
        获取代理66
        :param page_count: 页码
        :return: 代理
        """
        start_url = 'http://www.66ip.cn/{}.html'
        urls = [start_url.format(page) for page in range(1, page_count + 1)]
        for url in urls:
            print('Crawling', url)
            html = get_page(url)
            if html:
                doc = pq(html)
                trs = doc('.containerbox table tr:gt(0)').items()
                for tr in trs:
                    ip = tr.find('td:nth-child(1)').text()
                    port = tr.find('td:nth-child(2)').text()
                    yield ':'.join([ip, port])

    def crawl_ip3366(self):
        for page in range(1, 4):
            start_url = 'http://www.ip3366.net/free/?stype=1&page={}'.format(page)
            html = get_page(start_url)
            ip_address = re.compile('\s*(.*?)\s*(.*?)')
            # \s * 匹配空格，起到换行作用
            re_ip_address = ip_address.findall(html)
            for address, port in re_ip_address:
                result = address+':'+ port
                yield result.replace(' ', '')
    
    def crawl_kuaidaili(self):
        for i in range(1, 4):
            start_url = 'http://www.kuaidaili.com/free/inha/{}/'.format(i)
            html = get_page(start_url)
            if html:
                ip_address = re.compile('(.*?)')
                re_ip_address = ip_address.findall(html)
                port = re.compile('(.*?)')
                re_port = port.findall(html)
                for address,port in zip(re_ip_address, re_port):
                    address_port = address+':'+port
                    yield address_port.replace(' ','')

    def crawl_xicidaili(self):
        for i in range(1, 3):
            start_url = 'http://www.xicidaili.com/nn/{}'.format(i)
            headers = {
                'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
                'Cookie':'_free_proxy_session=BAh7B0kiD3Nlc3Npb25faWQGOgZFVEkiJWRjYzc5MmM1MTBiMDMzYTUzNTZjNzA4NjBhNWRjZjliBjsAVEkiEF9jc3JmX3Rva2VuBjsARkkiMUp6S2tXT3g5a0FCT01ndzlmWWZqRVJNek1WanRuUDBCbTJUN21GMTBKd3M9BjsARg%3D%3D--2a69429cb2115c6a0cc9a86e0ebe2800c0d471b3',
                'Host':'www.xicidaili.com',
                'Referer':'http://www.xicidaili.com/nn/3',
                'Upgrade-Insecure-Requests':'1',
            }
            html = get_page(start_url, options=headers)
            if html:
                find_trs = re.compile('(.*?)', re.S)
                trs = find_trs.findall(html)
                for tr in trs:
                    find_ip = re.compile('(\d+\.\d+\.\d+\.\d+)')
                    re_ip_address = find_ip.findall(tr)
                    find_port = re.compile('(\d+)')
                    re_port = find_port.findall(tr)
                    for address,port in zip(re_ip_address, re_port):
                        address_port = address+':'+port
                        yield address_port.replace(' ','')
    
    def crawl_ip3366(self):
        for i in range(1, 4):
            start_url = 'http://www.ip3366.net/?stype=1&page={}'.format(i)
            html = get_page(start_url)
            if html:
                find_tr = re.compile('(.*?)', re.S)
                trs = find_tr.findall(html)
                for s in range(1, len(trs)):
                    find_ip = re.compile('(\d+\.\d+\.\d+\.\d+)')
                    re_ip_address = find_ip.findall(trs[s])
                    find_port = re.compile('(\d+)')
                    re_port = find_port.findall(trs[s])
                    for address,port in zip(re_ip_address, re_port):
                        address_port = address+':'+port
                        yield address_port.replace(' ','')
    
    def crawl_iphai(self):
        start_url = 'http://www.iphai.com/'
        html = get_page(start_url)
        if html:
            find_tr = re.compile('(.*?)', re.S)
            trs = find_tr.findall(html)
            for s in range(1, len(trs)):
                find_ip = re.compile('\s+(\d+\.\d+\.\d+\.\d+)\s+', re.S)
                re_ip_address = find_ip.findall(trs[s])
                find_port = re.compile('\s+(\d+)\s+', re.S)
                re_port = find_port.findall(trs[s])
                for address,port in zip(re_ip_address, re_port):
                    address_port = address+':'+port
                    yield address_port.replace(' ','')

    def crawl_data5u(self):
        start_url = 'http://www.data5u.com/free/gngn/index.shtml'
        headers = {
            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
            'Accept-Encoding': 'gzip, deflate',
            'Accept-Language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',
            'Cache-Control': 'max-age=0',
            'Connection': 'keep-alive',
            'Cookie': 'JSESSIONID=47AA0C887112A2D83EE040405F837A86',
            'Host': 'www.data5u.com',
            'Referer': 'http://www.data5u.com/free/index.shtml',
            'Upgrade-Insecure-Requests': '1',
            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36',
        }
        html = get_page(start_url, options=headers)
        if html:
            ip_address = re.compile('
(\d+\.\d+\.\d+\.\d+)
.*?
(\d+)
', re.S)
            re_ip_address = ip_address.findall(html)
            for address, port in re_ip_address:
                result = address + ':' + port
                yield result.replace(' ', '')

from proxypool.tester import Tester
from proxypool.db import RedisClient
from proxypool.crawler import Crawler
from proxypool.setting import *
import sys

class Getter():
    def __init__(self):
        self.redis = RedisClient()
        self.crawler = Crawler()
    
    def is_over_threshold(self):
        """
        判断是否达到了代理池限制
        """
        if self.redis.count() >= POOL_UPPER_THRESHOLD:
            return True
        else:
            return False
    
    def run(self):
        print('获取器开始执行')
        if not self.is_over_threshold():
            for callback_label in range(self.crawler.__CrawlFuncCount__):
                callback = self.crawler.__CrawlFunc__[callback_label]
                # 获取代理
                proxies = self.crawler.get_proxies(callback)
                sys.stdout.flush()
                print(proxies)
                for proxy in proxies:

                    self.redis.add(proxy)


if __name__ == '__main__':
    getter = Getter()
    getter.run()

3 检测模块

import asyncio
import aiohttp
import time
import sys
try:
    from aiohttp import ClientError
except:
    from aiohttp import ClientProxyConnectionError as ProxyConnectionError
from proxypool.db import RedisClient
from proxypool.setting import *


class Tester(object):
    def __init__(self):
        self.redis = RedisClient()
    
    async def test_single_proxy(self, proxy):
        """
        测试单个代理
        :param proxy:
        :return:
        """
        conn = aiohttp.TCPConnector(verify_ssl=False)
        async with aiohttp.ClientSession(connector=conn) as session:
            try:
                if isinstance(proxy, bytes):
                    proxy = proxy.decode('utf-8')
                real_proxy = 'http://' + proxy
                print('正在测试', proxy)
                async with session.get(TEST_URL, proxy=real_proxy, timeout=15, allow_redirects=False) as response:
                    if response.status in VALID_STATUS_CODES:
                        self.redis.max(proxy)
                        print('代理可用', proxy)
                    else:
                        self.redis.decrease(proxy)
                        print('请求响应码不合法 ', response.status, 'IP', proxy)
            except (ClientError, aiohttp.client_exceptions.ClientConnectorError, asyncio.TimeoutError, AttributeError):
                self.redis.decrease(proxy)
                print('代理请求失败', proxy)
    
    def run(self):
        """
        测试主函数
        :return:
        """
        print('测试器开始运行')
        try:
            count = self.redis.count()
            print('当前剩余', count, '个代理')
            for i in range(0, count, BATCH_TEST_SIZE):
                start = i
                stop = min(i + BATCH_TEST_SIZE, count)
                print('正在测试第', start + 1, '-', stop, '个代理')
                test_proxies = self.redis.batch(start, stop)
                loop = asyncio.get_event_loop()
                tasks = [self.test_single_proxy(proxy) for proxy in test_proxies]
                loop.run_until_complete(asyncio.wait(tasks))
                sys.stdout.flush()
                time.sleep(5)
        except Exception as e:
            print('测试器发生错误', e.args)

4 接口模块

from flask import Flask, g

from .db import RedisClient

__all__ = ['app']

app = Flask(__name__)


def get_conn():
    if not hasattr(g, 'redis'):
        g.redis = RedisClient()
    return g.redis


@app.route('/')
def index():
    return '
Welcome to Proxy Pool System
'


@app.route('/random')
def get_proxy():
    """
    Get a proxy
    :return: 随机代理
    """
    conn = get_conn()
    return conn.random()


@app.route('/count')
def get_counts():
    """
    Get the count of proxies
    :return: 代理池总量
    """
    conn = get_conn()
    return str(conn.count())


if __name__ == '__main__':
    app.run()

5 调度模块

import time
from multiprocessing import Process
from proxypool.api import app
from proxypool.getter import Getter
from proxypool.tester import Tester
from proxypool.db import RedisClient
from proxypool.setting import *


class Scheduler():
    def schedule_tester(self, cycle=TESTER_CYCLE):
        """
        定时测试代理
        """
        tester = Tester()
        while True:
            print('测试器开始运行')
            tester.run()
            time.sleep(cycle)
    
    def schedule_getter(self, cycle=GETTER_CYCLE):
        """
        定时获取代理
        """
        getter = Getter()
        while True:
            print('开始抓取代理')
            getter.run()
            time.sleep(cycle)
    
    def schedule_api(self):
        """
        开启API
        """
        app.run(API_HOST, API_PORT)
    
    def run(self):
        print('代理池开始运行')
        
        if TESTER_ENABLED:
            tester_process = Process(target=self.schedule_tester)
            tester_process.start()
        
        if GETTER_ENABLED:
            getter_process = Process(target=self.schedule_getter)
            getter_process.start()
        
        if API_ENABLED:
            api_process = Process(target=self.schedule_api)
            api_process.start()

四 运行

(venv) E:\Python\ProxyPool>python run.py

访问：http://127.0.0.1:5555/

访问：http://127.0.0.1:5555/random

访问：http://127.0.0.1:5555/count

获取代理的代码

import requests
from proxypool.setting import TEST_URL

PROXY_POOL_URL = 'http://localhost:5555/random'

def get_proxy():
    try:
        response = requests.get(PROXY_POOL_URL)
        if response.status_code == 200:
            return response.text
    except ConnectionError:
        return None

proxy = get_proxy()

proxies = {
    'http': 'http://' + proxy,
    'https': 'https://' + proxy,
}

print(TEST_URL)
response = requests.get(TEST_URL, proxies=proxies, verify=False)
if response.status_code == 200:
    print('Successfully')
    print(response.text)

测试结果