#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
扫描website目录下的所有数字人，生成静态HTML文件
"""
import os
import re
from pathlib import Path
def scan_and_generate_html():
"""扫描数字人目录并生成静态HTML"""
website_dir = Path(__file__).parent
digital_humans = []
# UUID正则表达式
uuid_pattern = re.compile(r'^[0-9a-f]{8}-[0-9a-f]{4}-[1-5][0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$', re.IGNORECASE)
print(f"正在扫描目录: {website_dir}")
# 扫描所有UUID格式的目录
try:
for item in os.listdir(website_dir):
item_path = website_dir / item
if item_path.is_dir() and uuid_pattern.match(item):
index_file = item_path / "index.html"
image_file = item_path / "image" / "bg.jpg"
if index_file.exists():
# 从 index.html 读取标题
name = "数字人"
try:
with open(index_file, 'r', encoding='utf-8') as f:
content = f.read()
title_match = re.search(r'(.*?)', content)
if title_match:
name = title_match.group(1)
except:
pass
mtime = item_path.stat().st_mtime
digital_humans.append({
"id": item,
"name": name,
"image": f"{item}/image/bg.jpg",
"url": f"{item}/index.html",
"mtime": mtime
})
print(f" 找到: {item} - {name}")
# 按时间倒序排序（最新的在前）
digital_humans.sort(key=lambda x: x['mtime'], reverse=True)
print(f"总共找到 {len(digital_humans)} 个数字人")
except Exception as e:
print(f"扫描失败: {e}")
import traceback
traceback.print_exc()
# 生成HTML内容
html_cards = ""
if digital_humans:
for i, dh in enumerate(digital_humans, 1):
html_cards += f"""
"""
else:
html_cards = """
暂无可用的数字人
"""
# 生成完整的HTML文件
html_content = f"""
数字人列表
"""
# 写入文件
output_file = website_dir / "digital_human_list.html"
with open(output_file, 'w', encoding='utf-8') as f:
f.write(html_content)
print(f"\n已生成静态HTML文件: {output_file}")
print(f"包含 {len(digital_humans)} 个数字人")
if __name__ == "__main__":
scan_and_generate_html()