Scrapy, a fast high-level web crawling & scraping framework for Python.
do not degrade JPEG files.
Anubhav Patel25e616fa04bf
diff --git a/scrapy/pipelines/images.py b/scrapy/pipelines/images.pyindex a1457c7e9..add606a2e 100644--- a/scrapy/pipelines/images.py+++ b/scrapy/pipelines/images.py@@ -127,7 +127,7 @@ class ImagesPipeline(FilesPipeline):raise ImageException("Image too small (%dx%d < %dx%d)" %(width, height, self.min_width, self.min_height))- image, buf = self.convert_image(orig_image)+ image, buf = self.convert_image(orig_image, BytesIO(response.body))yield path, image, buffor thumb_id, size in six.iteritems(self.thumbs):@@ -135,7 +135,7 @@ class ImagesPipeline(FilesPipeline):thumb_image, thumb_buf = self.convert_image(image, size)yield thumb_path, thumb_image, thumb_buf- def convert_image(self, image, size=None):+ def convert_image(self, image, response_body, size=None):if image.format == 'PNG' and image.mode == 'RGBA':background = Image.new('RGBA', image.size, (255, 255, 255))background.paste(image, image)@@ -152,6 +152,9 @@ class ImagesPipeline(FilesPipeline):image = image.copy()image.thumbnail(size, Image.ANTIALIAS)+ if not size and image.format == 'JPEG':+ return image, response_body+buf = BytesIO()image.save(buf, 'JPEG')return image, buf