def check_large_images(self, node, parent_depth_level, sibling_depth_level):
"""\
although slow the best way to determine the best image is to download
them and check the actual dimensions of the image when on disk
so we'll go through a phased approach...
1. get a list of ALL images from the parent node
2. filter out any bad image names that we know of (gifs, ads, etc..)
3. do a head request on each file to make sure it meets
our bare requirements
4. any images left over let's do a full GET request,
download em to disk and check their dimensions
5. Score images based on different factors like height/width
and possibly things like color density
"""
good_images = self.get_image_candidates(node)
if good_images:
scored_images = self.fetch_images(good_images, parent_depth_level)
if scored_images:
highscore_image = sorted(scored_images.items(), key=lambda x: x[1], reverse=True)[0][0]
main_image = Image()
main_image.src = highscore_image.src
main_image.width = highscore_image.width
main_image.height = highscore_image.height
main_image.extraction_type = "bigimage"
main_image.confidence_score = 100 / len(scored_images) if len(scored_images) > 0 else 0
return main_image
depth_obj = self.get_depth_level(node, parent_depth_level, sibling_depth_level)
if depth_obj:
return self.check_large_images(depth_obj.node, depth_obj.parent_depth, depth_obj.sibling_depth)
return None
def get_best_image(self, doc, topNode):
image = self.check_known_elements()
if image:
return image
image = self.check_large_images(topNode, 0, 0)
if image:
return image
image = self.check_meta_tag()
if image:
return image
return Image()
def get_image(self, element, src, score=100, extraction_type="N/A"):
# build the Image object
image = Image()
image.src = self.build_image_path(src)
image.extraction_type = extraction_type
image.confidence_score = score
# check if we have a local image
# in order to add more information
# on the Image object
local_image = self.get_local_image(image.src)
if local_image:
image.bytes = local_image.bytes
image.height = local_image.height
image.width = local_image.width
# return the image
return image
def get_image(self, element, src, score=100, extraction_type="N/A"):
# build the Image object
image = Image()
image.src = self.build_image_path(src)
image.extraction_type = extraction_type
image.confidence_score = score
# check if we have a local image
# in order to add more information
# on the Image object
local_image = self.get_local_image(image.src)
if local_image:
image.bytes = local_image.bytes
image.height = local_image.height
image.width = local_image.width
# return the image
return image
def check_large_images(self, node, parent_depth_level,
sibling_depth_level):
"""\
although slow the best way to determine the best image is to download
them and check the actual dimensions of the image when on disk
so we'll go through a phased approach...
1. get a list of ALL images from the parent node
2. filter out any bad image names that we know of (gifs, ads, etc..)
3. do a head request on each file to make sure it meets
our bare requirements
4. any images left over let's do a full GET request,
download em to disk and check their dimensions
5. Score images based on different factors like height/width
and possibly things like color density
"""
good_images = self.get_image_candidates(node)
if good_images:
scored_images = self.fetch_images(good_images, parent_depth_level)
if scored_images:
highscore_image = sorted(scored_images.items(),
key=lambda x: x[1],
reverse=True)[0][0]
main_image = Image()
main_image.src = highscore_image.src
main_image.width = highscore_image.width
main_image.height = highscore_image.height
main_image.extraction_type = "bigimage"
main_image.confidence_score = 100 / len(scored_images) \
if len(scored_images) > 0 else 0
return main_image
depth_obj = self.get_depth_level(node, parent_depth_level,
sibling_depth_level)
if depth_obj:
return self.check_large_images(depth_obj.node,
depth_obj.parent_depth,
depth_obj.sibling_depth)
return None
def getExpectedImage(self, expected_value):
image = Image()
for k, v in expected_value.items():
setattr(image, k, v)
return image