學習scrapy框架時，用到了自定義繼承自ImagePipeline的類下載圖片，對於函式中的引數存在疑問，查看了ImagePipeline的原始碼，如下：

class ImagesPipeline(FilesPipeline):
    """
    Abstract pipeline that implement the image thumbnail generation logic

    """

    MEDIA_NAME = 'image'
    MIN_WIDTH = 0
    MIN_HEIGHT = 0
    THUMBS = {}
    DEFAULT_IMAGES_URLS_FIELD = 'image_urls'
    DEFAULT_IMAGES_RESULT_FIELD = 'images'

    @classmethod
    def from_settings(cls, settings):
        cls.MIN_WIDTH = settings.getint('IMAGES_MIN_WIDTH', 0)
        cls.MIN_HEIGHT = settings.getint('IMAGES_MIN_HEIGHT', 0)
        cls.EXPIRES = settings.getint('IMAGES_EXPIRES', 90)
        cls.THUMBS = settings.get('IMAGES_THUMBS', {})
        s3store = cls.STORE_SCHEMES['s3']
        s3store.AWS_ACCESS_KEY_ID = settings['AWS_ACCESS_KEY_ID']
        s3store.AWS_SECRET_ACCESS_KEY = settings['AWS_SECRET_ACCESS_KEY']

        cls.IMAGES_URLS_FIELD = settings.get('IMAGES_URLS_FIELD', cls.DEFAULT_IMAGES_URLS_FIELD)
        cls.IMAGES_RESULT_FIELD = settings.get('IMAGES_RESULT_FIELD', cls.DEFAULT_IMAGES_RESULT_FIELD)
        store_uri = settings['IMAGES_STORE']
        return cls(store_uri)

    def file_downloaded(self, response, request, info):
        return self.image_downloaded(response, request, info)

    def image_downloaded(self, response, request, info):
        checksum = None
        for path, image, buf in self.get_images(response, request, info):
            if checksum is None:
                buf.seek(0)
                checksum = md5sum(buf)
            width, height = image.size
            self.store.persist_file(
                path, buf, info,
                meta={'width': width, 'height': height},
                headers={'Content-Type': 'image/jpeg'})
        return checksum

    def get_images(self, response, request, info):
        path = self.file_path(request, response=response, info=info)
        orig_image = Image.open(StringIO(response.body))

        width, height = orig_image.size
        if width < self.MIN_WIDTH or height < self.MIN_HEIGHT:
            raise ImageException("Image too small (%dx%d < %dx%d)" %
                                 (width, height, self.MIN_WIDTH, self.MIN_HEIGHT))

        image, buf = self.convert_image(orig_image)
        yield path, image, buf

        for thumb_id, size in self.THUMBS.iteritems():
            thumb_path = self.thumb_path(request, thumb_id, response=response, info=info)
            thumb_image, thumb_buf = self.convert_image(image, size)
            yield thumb_path, thumb_image, thumb_buf

    def convert_image(self, image, size=None):
        if image.format == 'PNG' and image.mode == 'RGBA':
            background = Image.new('RGBA', image.size, (255, 255, 255))
            background.paste(image, image)
            image = background.convert('RGB')
        elif image.mode != 'RGB':
            image = image.convert('RGB')

        if size:
            image = image.copy()
            image.thumbnail(size, Image.ANTIALIAS)

        buf = StringIO()
        image.save(buf, 'JPEG')
        return image, buf

    def get_media_requests(self, item, info):
        return [Request(x) for x in item.get(self.IMAGES_URLS_FIELD, [])]

    def item_completed(self, results, item, info):
        if self.IMAGES_RESULT_FIELD in item.fields:
            item[self.IMAGES_RESULT_FIELD] = [x for ok, x in results if ok]
        return item

    def file_path(self, request, response=None, info=None):
        ## start of deprecation warning block (can be removed in the future)
        def _warn():
            from scrapy.exceptions import ScrapyDeprecationWarning
            import warnings
            warnings.warn('ImagesPipeline.image_key(url) and file_key(url) methods are deprecated, '
                          'please use file_path(request, response=None, info=None) instead',
                          category=ScrapyDeprecationWarning, stacklevel=1)

        # check if called from image_key or file_key with url as first argument
        if not isinstance(request, Request):
            _warn()
            url = request
        else:
            url = request.url

        # detect if file_key() or image_key() methods have been overridden
        if not hasattr(self.file_key, '_base'):
            _warn()
            return self.file_key(url)
        elif not hasattr(self.image_key, '_base'):
            _warn()
            return self.image_key(url)
        ## end of deprecation warning block

        image_guid = hashlib.sha1(url).hexdigest()  # change to request.url after deprecation
        return 'full/%s.jpg' % (image_guid)

    def thumb_path(self, request, thumb_id, response=None, info=None):
        ## start of deprecation warning block (can be removed in the future)
        def _warn():
            from scrapy.exceptions import ScrapyDeprecationWarning
            import warnings
            warnings.warn('ImagesPipeline.thumb_key(url) method is deprecated, please use '
                          'thumb_path(request, thumb_id, response=None, info=None) instead',
                          category=ScrapyDeprecationWarning, stacklevel=1)

        # check if called from thumb_key with url as first argument
        if not isinstance(request, Request):
            _warn()
            url = request
        else:
            url = request.url

        # detect if thumb_key() method has been overridden
        if not hasattr(self.thumb_key, '_base'):
            _warn()
            return self.thumb_key(url, thumb_id)
        ## end of deprecation warning block

        thumb_guid = hashlib.sha1(url).hexdigest()  # change to request.url after deprecation
        return 'thumbs/%s/%s.jpg' % (thumb_id, thumb_guid)

    # deprecated
    def file_key(self, url):
        return self.image_key(url)
    file_key._base = True

    # deprecated
    def image_key(self, url):
        return self.file_path(url)
    image_key._base = True

    # deprecated
    def thumb_key(self, url, thumb_id):
        return self.thumb_path(url, thumb_id)
    thumb_key._base = True

 

在def item_completed(self, results, item, info)：中的results引數，參考文章後得知，是相對應的get_media_requests(item, info)下載的結果，是一個列表型別，其中的元素是元組型別，形如：(success, image_info_or_failure)。

ps:並沒有從原始碼中發現這樣的返回內容

其中success是下載是否成功的bool，image_info_or_failure包括url、path和checksum三項。其中，path就是相對於IMAGES_STORE的路徑（含檔名）。

results例項：

[(True,
  {'checksum': '2b00042f7481c7b056c4b410d28f33cf',
   'path': 'full/7d97e98f8af710c7e7fe703abc8f639e0ee507c4.jpg',
   'url': 'http://www.example.com/images/product1.jpg'}),
 (True,
  {'checksum': 'b9628c4ab9b595f72f280b90c4fd093d',
   'path': 'full/1ca5879492b8fd606df1964ea3c1e2f4520f076f.jpg',
   'url': 'http://www.example.com/images/product2.jpg'}),
 (False,
  Failure(...))]
 

貼上練習的程式碼：

def file_path(self,request,response=None,info=None):
		"""獲取圖片名稱，作為檔名"""
		url = request.url
		file_name = url.spilt('/')[-1]
		return file_name
	
	def item_completed(self,results,item,info):
		"""清除下載失敗的圖片"""
		#result： 每個 Item 下載的結果，列表型別，每個元素為元組，包括下載完成或失敗的資訊
		image_paths = [x['path'] for ok,x in results if ok]
		if not images_paths:
			raise DropItem('圖片下載失敗')
		return item
	
	def get_media_requests(self,item,info):
		"""獲取圖片連結，並將其加入到Request佇列"""
		yield Request(item['url'])