下载和处理文件和图像

import scrapy
from itemadapter import ItemAdapter
from scrapy.exceptions import DropItem
from scrapy.pipelines.images import ImagesPipeline

class MyImagesPipeline(ImagesPipeline):

    def get_media_requests(self, item, info):
        for image_url in item['image_urls']:
            yield scrapy.Request(image_url)

    def item_completed(self, results, item, info):
        image_paths = [x['path'] for ok, x in results if ok]
        if not image_paths:
            raise DropItem("Item contains no images")
        adapter = ItemAdapter(item)
        adapter['image_paths'] = image_paths
        return item

ITEM_PIPELINES = {
    'myproject.pipelines.MyImagesPipeline': 300
}