Created
June 17, 2020 07:37
-
-
Save curegit/e2e263c63f9d6c6de9f13dade5ee20ce to your computer and use it in GitHub Desktop.
Safebooru から画像をスクレイピングするスクリプト
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
import sys | |
from os import makedirs | |
from itertools import count | |
from os.path import basename | |
from xml.etree import ElementTree | |
from urllib.parse import urlencode | |
from urllib.request import urlopen, urlretrieve | |
for tag in sys.argv[1:]: | |
dir = basename(tag) | |
makedirs(dir, exist_ok=True) | |
base_url = "https://safebooru.org/index.php?page=dapi&s=post&q=index&{}" | |
for page in count(1): | |
url = base_url.format(urlencode({ "tags": tag, "pid": page })) | |
with urlopen(url) as response: | |
content = response.read() | |
xml = ElementTree.fromstring(content) | |
posts = list(xml.iter("post")) | |
if len(posts) < 1: | |
break | |
for post in posts: | |
image_url = post.get("file_url") | |
urlretrieve(image_url, filename=f"{dir}/{basename(image_url)}") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment