# setting.py 为项目配置文件

# 配置API服务

HOST = "0.0.0.0"               # IP
PORT = 5000                    # 监听端口


# 配置数据库

DB_CONN = 'redis://:[email protected]:8888/0'


# 配置 ProxyFetcher

PROXY_FETCHER = [
    "freeProxy01",      # 这里是启用的代理抓取方法名，所有fetch方法位于fetcher/proxyFetcher.py
    "freeProxy02",
    # ....
]

import requests

def get_proxy():
    return requests.get("http://127.0.0.1:5010/get/").json()

def delete_proxy(proxy):
    requests.get("http://127.0.0.1:5010/delete/?proxy={}".format(proxy))

# your spider code

def getHtml():
    # ....
    retry_count = 5
    proxy = get_proxy().get("proxy")
    while retry_count > 0:
        try:
            html = requests.get('http://www.example.com', proxies={"http": "http://{}".format(proxy)})
            # 使用代理访问
            return html
        except Exception:
            retry_count -= 1
    # 删除代理池中代理
    delete_proxy(proxy)
    return None

class ProxyFetcher(object):
    # ....

    # 自定义代理源获取方法
    @staticmethod
    def freeProxyCustom1():  # 命名不和已有重复即可

        # 通过某网站或者某接口或某数据库获取代理
        # 假设你已经拿到了一个代理列表
        proxies = ["x.x.x.x:3128", "x.x.x.x:80"]
        for proxy in proxies:
            yield proxy
        # 确保每个proxy都是 host:ip正确的格式返回

PROXY_FETCHER = [
    "freeProxy01",    
    "freeProxy02",
    # ....
    "freeProxyCustom1"  #  # 确保名字和你添加方法名字一致
]