Last active
November 5, 2021 13:46
-
-
Save dreizehnutters/c3a16bd23b715745ace7045719afe92e to your computer and use it in GitHub Desktop.
p5.js webeditor scrapper
This file contains hidden or 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
""" | |
what: | |
download all sketches (as .zip) from a given user on p5.js | |
how: | |
python <TARGET> [<OUT_DIR>] | |
who: | |
@13utters | |
""" | |
from sys import argv, exit | |
from pathlib import Path | |
from requests import get | |
try: | |
TARGET = argv[1] | |
except IndexError: | |
exit(f"python {argv[0]} <TARGET> [<OUT_DIR>]") | |
try: | |
BASE = argv[2] | |
except IndexError: | |
BASE = argv[1] | |
finally: | |
Path(BASE).mkdir(parents=True, exist_ok=True) | |
CHUNK_SIZE = 1024 | |
PROTO = "https" | |
HOST = "editor.p5js.org" | |
ENDPOINT = lambda x : f"/editor/projects/{x}/zip" | |
BANNER = f"[*] scraping \x1b[1m{TARGET}\x1b[0m's sketches from {HOST}" | |
print(f"{BANNER}\n{'-'*(len(BANNER)-7)}") | |
try: | |
RESPONSE = get(f"{PROTO}://{HOST}/editor/{TARGET}/projects") | |
except TypeError as err: | |
exit(f"[!] {TARGET} does not exist", err) | |
else: | |
JSONRESP = RESPONSE.json() | |
for idx, elm in enumerate(JSONRESP): | |
sketch_name = elm['name'].replace(' ', '_').replace('/','_') | |
sketch_id = elm['_id'] | |
print(f"\t[{idx+1}/{len(JSONRESP)}]\tscraping: \x1b[1m{sketch_name}\x1b[0m ({sketch_id})") | |
print('\t...', end='\r') | |
with open(f"{BASE}/{sketch_name}.zip", 'wb') as fd: | |
zip_data = get(f"{PROTO}://{HOST}{ENDPOINT(sketch_id)}") | |
for chunk in zip_data.iter_content(chunk_size=CHUNK_SIZE): | |
fd.write(chunk) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment