
import random

from scrapy import signals
from scrapy.downloadermiddlewares.useragent import UserAgentMiddleware
from scrapy.utils.log import logger
from fake_useragent import UserAgent

import config
import utils

# useful for handling different item types with a single interface
from itemadapter import is_item, ItemAdapter


class WebSpidersSpiderMiddleware:
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.

        # Should return None or raise an exception.
        return None

    def process_spider_output(self, response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.

        # Must return an iterable of Request, or item objects.
        for i in result:
            yield i

    def process_spider_exception(self, response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Request or item objects.
        pass

    def process_start_requests(self, start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.

        # Must return only requests (not items).
        for r in start_requests:
            yield r

    def spider_opened(self, spider):
        spider.logger.info("Spider opened: %s" % spider.name)


class WebSpidersDownloaderMiddleware:
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the downloader middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_request(self, request, spider):
        # Called for each request that goes through the downloader
        # middleware.

        # Must either:
        # - return None: continue processing this request
        # - or return a Response object
        # - or return a Request object
        # - or raise IgnoreRequest: process_exception() methods of
        #   installed downloader middleware will be called
        return None

    def process_response(self, request, response, spider):
        # Called with the response returned from the downloader.

        # Must either;
        # - return a Response object
        # - return a Request object
        # - or raise IgnoreRequest
        return response

    def process_exception(self, request, exception, spider):
        # Called when a download handler or a process_request()
        # (from other downloader middleware) raises an exception.

        # Must either:
        # - return None: continue processing this exception
        # - return a Response object: stops process_exception() chain
        # - return a Request object: stops process_exception() chain
        pass

    def spider_opened(self, spider):
        spider.logger.info("Spider opened: %s" % spider.name)


class RandomUserAgentMiddleware(UserAgentMiddleware):
    def __init__(self, user_agent=''):
        super().__init__(user_agent)
        self.ua = UserAgent(platforms='desktop')

    def process_request(self, request, spider):
        try:
            ua = self.ua.random
            spider.logger.debug(f'使用随机UA: {ua}')
        except Exception as e:
            spider.logger.warning(f"UA生成失败: {e}")
            # 备用UA列表
            fallback_ua = utils.read_list_from_txt(config.USER_AGENTS_PATH)
            ua = random.choice(fallback_ua)
            spider.logger.debug(f'使用随机UA【备用】: {ua}')

        request.headers.setdefault('User-Agent', ua)


class RandomProxyMiddleware:
    def __init__(self, proxies):
        self.proxies = proxies

    @classmethod
    def from_crawler(cls, crawler):
        proxies = utils.read_list_from_txt(config.PROXIES_PATH)
        crawler.signals.connect(cls.spider_opened, signal=signals.spider_opened)  # 绑定信号
        logger.info(f'成功加载代理IP列表, 数量: {len(proxies)}')
        return cls(proxies)

    @classmethod
    def spider_opened(cls, spider):
        spider.logger.info('爬虫已启动，RandomProxyMiddleware 已加载')

    def process_request(self, request, spider):
        proxy = random.choice(self.proxies)
        request.meta['proxy'] = proxy
        spider.logger.info(f'成功使用代理, 当前请求将使用代理: {proxy} -> {request.url}')
