使用Python脚本批量转换网页文件编码为UTF-8

import os
import chardet
import shutil

# ========== 配置区 ==========
SRC_DIR = "另存的网页"      # 源文件夹（请确保此目录存在）
DST_DIR = "output_utf8"     # 输出文件夹（脚本会自动创建）

# 被视为“文本文件”的扩展名（会进行编码转换）
TEXT_EXTS = (
    ".html", ".htm", ".css", ".js", ".txt", ".json", ".xml", ".下载"
)

# ========== 工具函数 ==========
def ensure_dir_for_file(path):
    """确保文件所在目录存在"""
    dir_path = os.path.dirname(path)
    if dir_path:
        os.makedirs(dir_path, exist_ok=True)

def convert_text(src_path, dst_path):
    """将文本文件转为 UTF-8"""
    with open(src_path, "rb") as f:
        raw = f.read()

    # 自动检测编码，失败时 fallback 到 gb18030（兼容 GBK/GB2312）
    result = chardet.detect(raw)
    enc = result.get("encoding") or "gb18030"

    try:
        text = raw.decode(enc, errors="ignore")  # 忽略非法字符
        ensure_dir_for_file(dst_path)
        with open(dst_path, "w", encoding="utf-8") as f:
            f.write(text)
        print(f"✅ 文本 {src_path} [{enc}] → UTF-8")
    except Exception as e:
        print(f"❌ 文本失败 {src_path}: {e}")

def copy_binary(src_path, dst_path):
    """直接复制二进制文件"""
    try:
        ensure_dir_for_file(dst_path)
        shutil.copyfile(src_path, dst_path)
        print(f"📦 二进制 {src_path} → 原样拷贝")
    except Exception as e:
        print(f"❌ 拷贝失败 {src_path}: {e}")

# ========== 主逻辑 ==========
if __name__ == "__main__":
    if not os.path.exists(SRC_DIR):
        print(f"❌ 源目录 '{SRC_DIR}' 不存在，请检查！")
        exit(1)

    for root, _, files in os.walk(SRC_DIR):
        for name in files:
            src = os.path.join(root, name)
            rel = os.path.relpath(src, SRC_DIR)   # 获取相对于源目录的路径
            dst = os.path.join(DST_DIR, rel)      # 构建目标路径

            lower = name.lower()
            if lower.endswith(TEXT_EXTS):
                convert_text(src, dst)
            else:
                copy_binary(src, dst)  # 非文本文件一律原样拷贝

    print(f"\n🎉 处理完成！结果已保存至 '{DST_DIR}' 目录。")

pip install chardet

python convert_webpage_to_utf8.py