Python使用scrapy采集数据过程中放回下载过大页面的方法

DOWNLOADER_HTTPCLIENTFACTORY = 'myproject.downloader.LimitSizeHTTPClientFactory'

MAX_RESPONSE_SIZE = 1048576 # 1Mb
from scrapy.core.downloader.webclient import ScrapyHTTPClientFactory, ScrapyHTTPPageGetter
class LimitSizePageGetter(ScrapyHTTPPageGetter):
    def handleHeader(self, key, value):
        ScrapyHTTPPageGetter.handleHeader(self, key, value)
        if key.lower() == 'content-length' and int(value) > MAX_RESPONSE_SIZE:
            self.connectionLost('oversized')
class LimitSizeHTTPClientFactory(ScrapyHTTPClientFactory):
     protocol = LimitSizePageGetter