scrapy开启ImagePilelin

1
在settings中写入 IMAGES_STORE = ‘./images’
开启ITEM_PIPELINES ={
‘someproject.pipelines.ImagePipeline’ : 300,}
2
在pipelines中写入

'''此代码复制后可直接使用'''
from scrapy import Request
from scrapy.pipelines.images import ImagesPipeline
from scrapy.exceptions import DropItem

class ImagePipeline(ImagesPipeline):
    def file_path(self, request, response=None, info=None):
        url = request.url
        file_name = url.split('/')[-1]
        return file_name

    def item_completed(self, results, item, info):
        image_paths = [x['path'] for ok, x in results if ok]
        if not image_paths:
            raise DropItem('Image Downloaded Failed')
        return item

    def get_media_requests(self, item, info):
        yield Request(item['url'])
        '''这里的item['url']必须是在spider中yield的下载图片的网址'''