scrapy图片爬取ImagesPipeline

只需将spider类解析到的src地址 yield item

pipelines.py写法

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

class ImgPipeline(ImagesPipeline):
#根据图片的src进行图片数据请求
def get_media_requests(self,item,info):
    yield scrapy.Request(item['src'])
#指定图片的存取名称
def file_path(self,request,response=None,info=None):
    img_name = request.url.split('/')[-1]
    return img_name
#返回给下一个管道类
def item_completed(self,results,item,info):
    return item

setting.py中需加入设置

#图片存储路径
IMAGES_STORE = './ccc'