Python：使用Scrapy框架的ImagesPipeline下载图片如何保持原图片名称呢？
默认情况下，使用 ImagePipeline
组件下载图片的时候， 图片名称是以图片URL的SHA1值进行保存的
。
如：
图片URL:
SHA1结果：
则图片名称：
但是，我想要以原来的图片名称进行保存，比如上面例子中的图片保存到本地的话，图片名称就应该是：
ImagesPipeline.image_key(url) and file_key(url) methods are deprecated, please use file_path(request, response=None, info=None) instead
也就是说，在最新版本的Scrapy中（0.22.2），使用file_path代替image_key函数。
如：
图片URL:
http://www.example.com/image.jpg
SHA1结果：
3afec3b4765f8f0a07b78f98c07b83f013567a0a
则图片名称：
3afec3b4765f8f0a07b78f98c07b83f013567a0a.jpg
但是，我想要以原来的图片名称进行保存，比如上面例子中的图片保存到本地的话，图片名称就应该是：
image.jpg
stackoverflow上说是可以重写image_key函数，不过我试了下，结果发现不行，重写的image_key函数没被调用。
后面查看了下ImagePipeline的源码：
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
其中，有这么一句话：
ImagesPipeline.image_key(url) and file_key(url) methods are deprecated, please use file_path(request, response=None, info=None) instead
也就是说，在最新版本的Scrapy中（0.22.2），使用file_path代替image_key函数。
因此，我在自定义的ImagePipeline类中，重写了file_path函数，代码如下：
__author__ = 'Fly'
#coding:utf-8
from scrapy.contrib.pipeline.images import ImagesPipeline
from scrapy.http import Request
from scrapy.exceptions import DropItem
class MyImagesPipeline(ImagesPipeline):
def file_path(self, request, response=None, info=None):
image_guid = request.url.split('/')[-1]
return 'full/%s' % (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")
return item以上代码主要返回原图片名称+图片后缀。
作者：曾是土木人（http://blog.csdn.net/php_fly）
原文地址：http://blog.csdn.net/php_fly/article/details/19688595