Pipelines.py

ImagesPipeline.py

from scrapy.contrib.pipeline.images import ImagesPipeline
from scrapy.exceptions import DropItem
from scrapy.http import Request

class MyImagesPipeline(ImagesPipeline):

  def image_key(self, url):
    image_guid = url.split('/')[-1]
    return '%s.jpg' % (image_guid)

  def get_media_requests(self, item, info):
    for image_url in item['image_urls']:
        yield 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")
    item['image_paths'] = image_paths
    return item