Download original size artwork from https://wikiart.org
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/env python | |
""" | |
Usage: | |
download-artwork-from-wikiart-url.py URL | |
Arguments: | |
URL URL of artwork in wikiart.org | |
(ex.: https://www.wikiart.org/en/rene-magritte/gonconda-1953/) | |
""" | |
from bs4 import BeautifulSoup | |
from docopt import docopt | |
import requests | |
from json import loads | |
from re import sub | |
def retrieve(url): | |
return requests.get(url).content | |
def parse(html): | |
soup = BeautifulSoup(html, features="html.parser") | |
source = sub( | |
r"^.*= ", | |
"", | |
soup.find( | |
"main", | |
{"ng-controller": "ArtworkViewCtrl"} | |
).get("ng-init")[:-1] | |
) | |
thumbnails = loads(source)["ImageThumbnailsModel"][0]["Thumbnails"] | |
url = next( | |
thumbnail for thumbnail in thumbnails | |
if thumbnail["Name"].lower() == "original" | |
)["Url"] | |
title, artist, _ = soup.find("title").text.split(" - ") | |
name = "{a}, {t}".format(a=artist, t=title) | |
return url, name | |
def download(url, name): | |
extension = url.split(".")[-1] | |
with open(".".join([name, extension]), "wb") as artwork: | |
artwork.write(requests.get(url).content) | |
if __name__ == "__main__": | |
ARGS = docopt(__doc__) | |
URL = ARGS["URL"] | |
IMAGE_URL, IMAGE_NAME = parse(retrieve(URL)) | |
download(IMAGE_URL, IMAGE_NAME) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment