Scrapy--设置代理ip

最新推荐文章于 2024-09-25 16:09:22 发布

hs947463167

最新推荐文章于 2024-09-25 16:09:22 发布

阅读量4.2k

点赞数 3

分类专栏： Scrapy 代理ip

本文链接：https://blog.csdn.net/hs947463167/article/details/80537178

版权

Scrapy 同时被 2 个专栏收录

5 篇文章 0 订阅

订阅专栏

代理ip

1 篇文章 0 订阅

订阅专栏

本次使用的代理Ip是蘑菇代理，数据库是redis

1.settings配置

"""REDIS 配置链接"""
REDIS_URL = "redis://127.0.0.1:6379"

RETRY_TIMES = 2

2.写入工具类

import requests
import json
import time
import redis
from 项目名.settings import REDIS_URL


def get_ip():
    coon = redis.from_url(REDIS_URL)
    url = "生成的API链接"
    body = requests.get(url)
    data = json.loads(body.text)
    code = data["code"]
    if code == "0":
        msgs = data["msg"]
        for msg in msgs:
            ip = msg["ip"]
            port = msg["port"]
            IP = ip + ":" + port
            coon.lpush("proxies", IP)
    elif code == "3001":
        time.sleep(5)
        get_ip()

3.配置Middlewares

class ProxiesMiddleware(object):
    def __init__(self):
        self.coon = redis.from_url(REDIS_URL)

    def process_request(self, request, spider):
        if self.coon.llen("proxies") == 0:
            get_ip()
        ip_list = self.coon.lrange("proxies", 0, -1)
        IP_LIST = []
        for ip in ip_list:
            IP = ip.decode("utf-8")
            IP_LIST.append(IP)
            request.meta["proxy"] = "http://{}".format(random.choice(IP_LIST))

    def process_response(self, response, request, spider):
        if "人机交互校验" in response.text:
            proxy = request.meta["proxy"].split("/")[-1]
            print("需要输入验证码，更换ip")
            print(response.url)
            self.coon.lrem("proxies", proxy)
            return request
        return response

    def process_exception(self, request, exception, spider):
        if exception:
            proxy = request.meta["proxy"].split("/")[-1]
            print("删除失效IP")
            self.coon.lrem("proxies", proxy)
            return request