Python：使用scrapy框架的ImagesPipeline下载图片如何保持原文件名呢？

Question

仔细看了下scrapy的官方文档关于ImagesPipeline的介绍说明及使用例子：Downloading Item Images
感觉官方文档太过简单。
比如：通过在setting.py文件中通过给IMAGES_STORE赋值，就可以指定图片的保存路径。
并且默认情况下，文件名是通过对url使用SHA1 hash得来的。
现在我想以原来的图片名进行保存，不知道该如何做，希望有经验的朋友帮忙指点下~

另外求大家帮忙推荐下关于scrapy的相关书籍（中英文都行）

Answer 1

查看下ImagePipeline的源码，发现可以重写file_path函数以修改图片名称，例如：

def file_path(self, request, response=None, info=None):
        open("image_urls.txt","a").write(request.url + "\n")
        image_guid = request.url.split('/')[-1]
        return 'full/%s' % (image_guid)

ImagePipeline的源码如下：

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

Answer 2

现在我想以原来的图片名进行保存

貌似这个没有直接的参数可以传，需要自己实现Images Pipeline

scrapy.contrib.pipeline.images.ImagesPipeline类的get_media_requests(item, info)会下载图片，并把结果喂给item_completed()方法，结果是一个tuple，(success, image_info_or_failure)，其中success是下载是否成功的bool，image_info_or_failure包括url、path和checksum三项。其中，path就是相对于IMAGES_STORE的路径（含文件名）。

[(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(...))]

上面是官网上的例子。

所以你需要做的是改写item_completed(results, items, info)方法，用原本的文件名替换掉item['image_paths']。

Answer 3

修改file_path对原代码侵入太大，如果只是为了修改文件路径的话，可以在item_completed对文件进行重命名。

class NeteaseautoImagePipeline(ImagesPipeline):
    def get_media_requests(self, item, info):
        for image_url in item['image_urls']:
            yield scrapy.Request(image_url.replace('120x90', '800x600'))

    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")
        if item['jk']:
            newname = item['car'] + '-' + item['jk'] + '-' + item['model'] + '.jpg'
        else:
            newname = item['car'] + '-' + item['model'] + '.jpg'
        os.rename("/neteaseauto/" + image_paths[0], "/neteaseauto/" + newname)
        return item