update at 2026-07-17 15:39:39

export/formatter1.md

@@ -0,0 +1,115 @@
+
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+import os
+import pandas as pd
+import re
+from pypinyin import lazy_pinyin
+
+INPUT_DIR = "/Users/gavin/kman/export"
+OUTPUT_DIR = os.path.join(INPUT_DIR, "out")
+os.makedirs(OUTPUT_DIR, exist_ok=True)
+
+def parse_filename(filename):
+    """
+    从文件名解析 title 和 subtitle
+    note_bleafA：B-C.md -> title=A, subtitle=B
+    如果没有冒号，subtitle为空
+    """
+    base = os.path.basename(filename).replace("note_bleaf", "").rsplit("-", 1)[0].rsplit(".md", 1)[0]
+    if "：" in base:
+        title, subtitle = base.split("：", 1)
+    else:
+        title = base
+        subtitle = ""
+    return title.strip(), subtitle.strip()
+
+def slugify(title):
+    """
+    中文转拼音，保留字母，长度不超过15
+    """
+    py = "".join(lazy_pinyin(title))
+    py = re.sub("[^a-zA-Z]", "", py)
+    return py[:15]
+
+def parse_content(filepath):
+    """
+    使用 pandas 读取 CSV 内容，跳过第二行分隔符
+    """
+    try:
+        df = pd.read_csv(filepath, sep="|", engine="python", dtype=str, skiprows=[1]).dropna(how="all", axis=1)
+    except Exception as e:
+        print(f"❌ 解析失败 {filepath}: {e}")
+        return pd.DataFrame()
+
+    # MARKTIME 转 datetime
+    if "MARKTIME" in df.columns:
+        df["MARKTIME"] = pd.to_datetime(df["MARKTIME"], errors="coerce")
+    else:
+        df["MARKTIME"] = pd.NaT
+
+    # AUTHOR 列保证存在
+    if "AUTHOR" not in df.columns:
+        df["AUTHOR"] = "未知"
+
+    return df
+
+def convert_file(filepath):
+    df = parse_content(filepath)
+    if df.empty:
+        return
+
+    title, subtitle = parse_filename(filepath)
+    slug = slugify(title)
+    author_name = df['AUTHOR'].iloc[0] if not df['AUTHOR'].isnull().all() else "未知"
+
+    # 最早的标记时间
+    if df['MARKTIME'].isnull().all():
+        date_str = "2025-01-07 11:00:00"
+    else:
+        date_str = df['MARKTIME'].min().strftime("%Y-%m-%d %H:%M:%S")
+
+    out_lines = [
+        "---",
+        f"title: '{title}'",
+        f"subtitle: '{subtitle}'",
+        f"author: 大童",
+        f"date: {date_str}",
+        f"slug: {slug}",
+        "description:",
+        "---",
+        f"作者：{author_name}",
+        ""
+    ]
+
+    # 处理正文
+    prev_hl = ""
+    for _, row in df.iterrows():
+        content = row.get("CONTENT", "")
+        if row.get("TYPE") == "HL":
+            out_lines.append(content)
+            out_lines.append("")  # 空行
+            prev_hl = content
+        elif row.get("TYPE") == "NT":
+            out_lines.append(f"> {content}")
+            out_lines.append("")  # 可选空行
+        else:
+            # 其他类型直接加内容
+            out_lines.append(content)
+            out_lines.append("")
+
+    output_filename = f"note_{title}.md"
+    output_path = os.path.join(OUTPUT_DIR, output_filename)
+    with open(output_path, "w", encoding="utf-8") as f:
+        f.write("\n".join(out_lines))
+
+    print(f"✅ 生成 {output_path}")
+
+def main():
+    for fname in os.listdir(INPUT_DIR):
+        if fname.startswith("note_bleaf") and fname.endswith(".md"):
+            convert_file(os.path.join(INPUT_DIR, fname))
+
+if __name__ == "__main__":
+    main()