def test_save_image_location():
assert (Comic.save_image_location(
"http://imgs.xkcd.com/comics/barrel_cropped_(1).jpg", 1,
"foo") == "foo/1.jpg")
assert Comic.save_image_location("", 1, "bar") == "bar/1"
assert (Comic.save_image_location(
"http://imgs.xkcd.com/comics/barrel_cropped_(1).jpg?q=123", 1,
"foo") == "foo/1.jpg")
def image_in_zipfile(item, directory):
zipfile_path = "{}.cbz".format(directory)
if not os.path.isfile(zipfile_path):
return False
image_path_cbz = Comic.save_image_location(item.get("url"),
item.get("page"))
with ZipFile(zipfile_path, "r") as zipfile:
return image_path_cbz in zipfile.namelist()
def get_media_requests(self, item, info):
click.echo("Saving image {}".format(item.get("url")))
url, page, title, alt_text = itemgetter("url", "page", "title",
"alt_text")(item)
image_path_directory = Comic.save_image_location(
url, page, info.spider.directory, title)
if os.path.isfile(image_path_directory) or self.image_in_zipfile(
item, info.spider.directory):
click.echo("The image was already downloaded. Skipping...")
raise DropItem("The image was already downloaded. Skipping...")
if alt_text is not None:
with open(
Comic.save_alt_text_location(page, info.spider.directory),
"w") as alt_text_file:
alt_text_file.write(alt_text)
yield scrapy.Request(
item.get("url"),
meta={
"image_file_name":
Comic.save_image_filename(item.get("url"), item.get("page"),
title, info.spider.directory)
},
)