python爬取mblock的图片素材

打开mblock:
URL: https://ide.makeblock.com/
开F12,切到角色页面:

点一下添加，看到有很多素材:

切到Network页的XHR找接口:

其中sprites.json引起了我的注意，点开看看:

是一个列表套dict的结构
其中一个dict:

{
	name: "Abby",  // 角色名
	md5: "afab2d2141e9811bd89e385e9628cb5f.svg",  // 图片url
	type: "sprite"
}

看一眼sprites.json的url:
https://res-cn.makeblock.com/mblock/static/sprites/scratch/sprites.json
刷新几次发现url是固定的。
先倒包:

import os
import sys
import glob

import requests
from bs4 import BeautifulSoup
try:
    import simplejson as json
except ModuleNotFoundError:
    import json

写一个load_json:

def load_json():
    url = 'https://res-cn.makeblock.com/mblock/static/sprites/makeblock/sprites.json'
    response = requests.get(url)
    response.encoding = 'utf-8'
    result = json.loads(response.text)
    print('INFO: loaded sprites json-file')
    return result

在写一个download_image:

def download_image(name, file_name):
    url = f'https://res-cn.makeblock.com/mblock/static/assets/scratch/{name}'
    response = requests.get(url)
    image_format = name.split('.')[-1]
    file_name = file_name + '.' + image_format
    with open(f'downloads/{file_name}', 'wb') as fp:
        fp.write(response.content)
    print(f'INFO: downloaded {file_name}')

串起来:

import os
import sys
import glob

import requests
from bs4 import BeautifulSoup
try:
    import simplejson as json
except ModuleNotFoundError:
    import json


def download_image(name, file_name):
    url = f'https://res-cn.makeblock.com/mblock/static/assets/scratch/{name}'
    response = requests.get(url)
    image_format = name.split('.')[-1]
    file_name = file_name + '.' + image_format
    with open(f'downloads/{file_name}', 'wb') as fp:
        fp.write(response.content)
    print(f'INFO: downloaded {file_name}')
    

def load_json():
    url = 'https://res-cn.makeblock.com/mblock/static/sprites/makeblock/sprites.json'
    response = requests.get(url)
    response.encoding = 'utf-8'
    result = json.loads(response.text)
    print('INFO: loaded sprites json-file')
    return result
    

def install():
    if not os.path.exists('downloads'):
        os.mkdir('downloads')
        print('INFO: created downloads folder')
    sprites = load_json()
    for sprite_info in sprites:
        name = sprite_info.get('name', 'nullify')
        md5 = sprite_info.get('md5', None)
        if md5:
            download_image(md5, name)
        

def clear():
    if os.path.exists('downloads'):
        for fp in glob.glob('downloads/*.*'):
            os.remove(fp)
            print(f'INFO: deleted {fp}')
    else:
        print('ERROR: not installed mblock-images')
        

def main():
    if len(sys.argv) != 1:
        name = sys.argv[1]
        if name in ('install', 'download'):
            install()
            sys.exit(0)
        elif name in ('clear', 'clean'):
            clear()
            sys.exit(0)
            

if __name__ == '__main__':
    main()

最后运行一下:

python -m install-mblock-images.py download

等待一分钟:

nice!