图片管道 ImagePipeLine

需要从新写两个方法

保存图片别忘了在设置中设置图片保存的位置 IMAGES_STORE = “xxx”

  1.  def get_media_requests(self, item, info):
  2.     pass
  3. def item_completed(self, results, item, info):
  4.     return item
  6. # results 数据类型
  7. [(True, 
  8. {'url': 'https://image1.ljcdn.com/110000-inspection/pc1_Kz21DStHD_1.jpg.296x216.jpg', 
  9. 'path': 'full/4495a2b603444ec1ed1c2451c690d814fbb33afb.jpg', 
  10. 'checksum': '3400355050afbbc17602f061ba1adba7'})]
  2. import scrapy
  3. from scrapy.utils.project import get_project_settings # 获取设置的内容
  4. import os
  5. from scrapy.pipelines.images import ImagesPipeline
  6. image_store = get_project_settings.get("IMAGES_STORE")
  7. class ImagePipeline(ImagesPipeline):
  8.     def __ init__(self):
  9.         # 定义初始化内容
  11.     def get_media_requests(self, item, info):
  12.         for url in item["image_urls]:
  13.              yiled scrapy.Request(url)
  14.         # 或者                
  15.         yiled scrapy.Request([ url for url in item["image_urls"]])               
  17.         # 或者
  18.         url = item["iomage_url]
  19.         yiled scrapy.Request(url)
  21.     def item_completed(self, results, item, info):
  22.         image_path = [x['path'] for status,x in results if status]           
  23.         os.rename(image_store+image[0],image_store+item['name']+".jpg")
  24.         image_path = images_store+itme["name"] + ".jpg"
  25.         imte['iamge_paths']  = image_store                
  26.         return item

注意：
setting中要配置图片的保存的位置
需要重写两个方法 可以自定义保存的路径
导入包 ImagePipeline get_project_setting
from scrapy.pipeline.image import ImagePipeline
from scrapy.utils.project import get_project_setting