import os
import chardet
import shutil

# ========== 配置區(qū) ==========
SRC_DIR = "另存的網(wǎng)頁"      # 源文件夾（請確保此目錄存在）
DST_DIR = "output_utf8"     # 輸出文件夾（腳本會自動創(chuàng)建）

# 被視為“文本文件”的擴展名（會進行編碼轉(zhuǎn)換）
TEXT_EXTS = (
    ".html", ".htm", ".css", ".js", ".txt", ".json", ".xml", ".下載"
)

# ========== 工具函數(shù) ==========
def ensure_dir_for_file(path):
    """確保文件所在目錄存在"""
    dir_path = os.path.dirname(path)
    if dir_path:
        os.makedirs(dir_path, exist_ok=True)

def convert_text(src_path, dst_path):
    """將文本文件轉(zhuǎn)為 UTF-8"""
    with open(src_path, "rb") as f:
        raw = f.read()

    # 自動檢測編碼，失敗時 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"? 文本失敗 {src_path}: {e}")

def copy_binary(src_path, dst_path):
    """直接復(fù)制二進制文件"""
    try:
        ensure_dir_for_file(dst_path)
        shutil.copyfile(src_path, dst_path)
        print(f"?? 二進制 {src_path} → 原樣拷貝")
    except Exception as e:
        print(f"? 拷貝失敗 {src_path}: {e}")

# ========== 主邏輯 ==========
if __name__ == "__main__":
    if not os.path.exists(SRC_DIR):
        print(f"? 源目錄 '{SRC_DIR}' 不存在，請檢查！")
        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)   # 獲取相對于源目錄的路徑
            dst = os.path.join(DST_DIR, rel)      # 構(gòu)建目標路徑

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

    print(f"\n?? 處理完成！結(jié)果已保存至 '{DST_DIR}' 目錄。")

pip install chardet

python convert_webpage_to_utf8.py