使用 Scrapy-Splash 不断收到“502 Bad Gateway”错误

Question

我有一个蜘蛛，我试图在我试图抓取的实际网站上运行，但我不断收到 502 Bad Gateway，这让我觉得我被禁止了。作为测试，我在http://quotes.toscrape.com/ 上使用了下面的代码，但我仍然得到 502 Bad Gateway！不用说，我从来没有接触过“我们成功了”的印刷线。我正在使用 Scrapy-Splash 帮助！

注意：代理中间件可以很好地与我的其他蜘蛛一起使用，所以我认为那里没有任何问题。此外，我可以使用初始 Web 界面渲染一切。

蜘蛛：

import scrapy
from scrapy_splash import SplashRequest

LUA_SCRIPT = """
function main(splash, args)
  splash.private_mode_enabled = false
  assert(splash:go(args.url))
  assert(splash:wait(20))
  return {
    html = splash:html(),
    png = splash:png(),
    har = splash:har(),
  }
end
"""



class ExampleSpider(scrapy.Spider):
    name = 'example'
    allowed_domains = []
    start_urls = ["http://quotes.toscrape.com/"]


    def start_requests(self):
        for url in self.start_urls:
            print()

            yield SplashRequest(url, self.parse,
                                endpoint='execute',
                                args={'lua_source': LUA_SCRIPT}
                                )

    def parse(self, response):
        soup = BeautifulSoup(response.text, "lxml")
        print("we made it")

settings.py：

BOT_NAME = 'project'
SPIDER_MODULES = ['project.spiders']
NEWSPIDER_MODULE = 'project.spiders'

ROBOTSTXT_OBEY = False

AUTOTHROTTLE_ENABLED = True
AUTOTHROTTLE_START_DELAY = 1
AUTOTHROTTLE_MAX_DELAY = 3
DEFAULT_REQUEST_HEADERS = {
    'Referer': 'http://www.google.com'
}

SPIDER_MIDDLEWARES = {
    'scrapy_splash.SplashDeduplicateArgsMiddleware': 100,
    'project.middlewares.ProjectSpiderMiddleware': 543,
}

DOWNLOADER_MIDDLEWARES = {
    'scrapy_splash.SplashCookiesMiddleware': 723,
    'scrapy_splash.SplashMiddleware': 725,
    'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
    'project.middlewares.ProjectDownloaderMiddleware': 543,
    'project.middlewares.CustomProxyMiddleware': 350,
    'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware': 400,
    'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware': None,
    'scrapy_useragents.downloadermiddlewares.useragents.UserAgentsMiddleware': 500
}

ITEM_PIPELINES = {
    'project.pipelines.ProjectPipeline': 900,

}

SPLASH_URL = 'http://localhost:8050'
DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'
HTTPCACHE_STORAGE = 'scrapy_splash.SplashAwareFSCacheStorage'

USER_AGENTS = [("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
               "Chrome/83.0.4103.116 Safari/537.36"),  # chrome
               ("Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:78.0) Gecko/20100101 Firefox/78.0",  # firefox
               "Mozilla/5.0 (Windows NT 10.0; Trident/7.0; rv:11.0) like Gecko"),  # internet explorer
               ("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
               "Chrome/83.0.4103.116 Safari/537.36 Edg/83.0.478.61")]  # microsoft edge

middleswares.py：

    from scrapy import signals
    from w3lib.http import basic_auth_header
    
    
    class ProjectSpiderMiddleware:
        # 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, dict 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, dict
            # 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 ProjectDownloaderMiddleware:
        # 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 CustomProxyMiddleware(object):

    def process_request(self, request, spider):
        request.meta["proxy"] = "IP"
        request.headers["Proxy-Authorization"] = basic_auth_header("username",
                                                                   "password")

Answer 1

当你将请求发布到网站时，首先要splash，splash会在没有代理的情况下访问目标网站。

SPIDER_MIDDLEWARES = {
    'project.middlewares.ProjectSpiderMiddleware': 543,
    'scrapy_splash.SplashDeduplicateArgsMiddleware': 100,
}

试试看。