scrapy yield发起网络请求,网页重定向到登录页面,导致request.url为登录url

怎么解决

重新构建middlewares.py中的process_response()

class Spider1688DownloaderMiddleware(object):

    @classmethod
    def from_crawler(cls, crawler):
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_request(self, request, spider):
        return None

    def process_response(self, request, response, spider):
        if '验证' in response.text:
            if 'offerlist' in response.url:
                mall_id = re.findall('%3A%2F%2F(.*?).1688', response.url)[0]
                requests_url = 'https://{}.1688.com/page/offerlist.htm'.format(mall_id)
                request._set_url(requests_url)
            return request
        elif 'login' in response.url:
            if '%3A%2F%2F' in response.url:
                pagenum = ''
                if 'pageNum' in response.url:
                    # try:
                    num = re.findall('pageNum%3D(.*?)&', response.url)[0]
                    pagenum = '?pageNum={}'.format(num)
                mall_id = re.findall('%3A%2F%2F(.*?).1688', response.url)[0]
                if 'login' in mall_id:
                    mall_id = re.findall('%253A%252F%252F(.*?).1688', response.url)[0]
                requests_url = 'https://{}.1688.com/page/offerlist.htm{}'.format(mall_id[0], pagenum)
                request._set_url(requests_url)
            return request
        else:
            return response

判断response.text中字段或者response.url中特殊字符判断是否网页重定向

从response.url中获取字符串,截取需要构建的url参数

使用request._set_url重新构建request中的访问URL

spider中加上

class Al1688MallSpiderSpider(scrapy.Spider):
    name = 'al_1688_mall_spider'
    allowed_domains = ['re.1688.com']
    # start_urls = ['http://re.1688.com/']
    custom_settings = {
        'DOWNLOADER_MIDDLEWARES': {
            'spider_1688.middlewares.Spider1688DownloaderMiddleware': 120,  # 中间件
        },
        'RETRY_HTTP_CODECS': 20,  # 网络请求重试次数
        "COOKIES_ENABLED": False #   每次请求不携带cookies
    }