scratch_18.py

import os
import re
import time

import requests
import csv

# 读取CSV文件并提取data-artid列的值
csv_file_path = r".\cards.csv"  # 替换为你的CSV文件路径
art_ids = set()
with open(csv_file_path, newline='', encoding="utf-8") as csvfile:
    reader = csv.DictReader(csvfile)
    for row in reader:
        art_id = row['data-artid'].rstrip('j')  # 假设CSV中的artid后缀是'j'，根据实际情况调整
        art_ids.add(art_id)
print(len(art_ids))
# 读取CSS文件
css_file_path = r"./assets\cards_html\asset-v9.css"  # 替换为你的CSS文件路径
with open(css_file_path, "r", encoding="utf-8") as f:
    css_content = f.read()

# 正则表达式匹配CSS中的图片URL
img_url_pattern = re.compile(r'url\((https?://[^\)]+)\)')

# 查找所有图片链接并过滤，只下载CSV文件中存在的art_id对应的图片
img_urls = img_url_pattern.findall(css_content)
download_folder = r"./assets\download_imgs"

# 确保下载文件夹存在
if not os.path.exists(download_folder):
    os.makedirs(download_folder)
c = 0
# 下载并保存图片
for url in []:
    c += 1
    print(f"{c}/{len(img_urls)}")
    # 从URL中提取图片编号
    try:
        response = requests.get(url)
        img_name = f"{url.split('/')[-1]}"
        with open(os.path.join(download_folder, img_name), 'wb') as f:
            f.write(response.content)
        print(f"Downloaded {img_name} to {download_folder}, {c}/{len(art_ids)}")
    except Exception as e:
        print(f"Failed to download {url}. Error: {e}")
    time.sleep(1)

# 更新CSS中的图片链接
updated_css_content = css_content
for url in img_urls:
    if url in css_content:  # 确保URL存在于CSS内容中
        match = re.search(r'/(\d+).png', url)
        img_name = f".\\{url.split('/')[-1]}.png"
        updated_css_content = updated_css_content.replace(url, img_name)

# 将更新后的CSS内容写回到文件
with open(css_file_path, 'w') as file:
    file.write(updated_css_content)
print("All relevant images have been downloaded and CSS updated.")