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

export/formatter.md

@@ -0,0 +1,115 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+import os
+import re
+from datetime import datetime
+from pathlib import Path
+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 slugify(title):
+    # 拼音 + 只保留字母 + 最多15个字符
+    py = "".join(lazy_pinyin(title))
+    s = re.sub("[^a-zA-Z]", "", py)
+    return s[:15]
+
+def parse_filename(fname):
+    # 去掉 note_bleaf 前缀
+    name = fname[len("note_bleaf"):]
+    # 分 title / subtitle
+    if "：" in name:
+        title, rest = name.split("：", 1)
+        # 去掉尾部可能的 -xxxx.md
+        subtitle = re.sub(r'-.*\.md$', '', rest)
+    else:
+        title = re.sub(r'-.*\.md$', '', name).replace(".md","")
+        subtitle = ""
+    return title.strip(), subtitle.strip()
+
+def parse_file(filepath):
+    """逐行解析，保证 CONTENT 中有 | 也能处理"""
+    entries = []
+    with open(filepath, "r", encoding="utf-8") as f:
+        lines = f.readlines()
+    for line in lines:
+        line = line.strip()
+        if not line or line.startswith("--") or line.startswith("TYPE"):
+            continue
+        parts = line.split("|", 4)  # 只分成 5 个字段
+        if len(parts) < 5:
+            print(f"⚠️ 跳过解析失败行: {line}")
+            continue
+        type_, bookname, author, marktime, content = parts
+        try:
+            marktime_dt = datetime.strptime(marktime.strip(), "%Y/%m/%d %H:%M:%S")
+        except:
+            try:
+                marktime_dt = datetime.strptime(marktime.strip(), "%Y/%m/%d %H:%M")
+            except:
+                marktime_dt = None
+        entries.append({
+            "TYPE": type_.strip(),
+            "BOOKNAME": bookname.strip(),
+            "AUTHOR": author.strip(),
+            "MARKTIME": marktime_dt,
+            "CONTENT": content.strip()
+        })
+    return entries
+
+def convert_file(filepath):
+    fname = os.path.basename(filepath)
+    title, subtitle = parse_filename(fname)
+    entries = parse_file(filepath)
+    if not entries:
+        print(f"❌ 解析失败 {filepath}")
+        return
+
+    # 最早的时间
+    times = [e["MARKTIME"] for e in entries if e["MARKTIME"]]
+    ddd = min(times).strftime("%Y-%m-%d %H:%M:%S") if times else datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+
+    slug = slugify(title)
+    output_fname = f"note_{title}.md"
+    output_path = os.path.join(OUTPUT_DIR, output_fname)
+
+    lines = [
+        "---",
+        f"title: '{title}'",
+        f"subtitle: '{subtitle}'",
+        f"author: '大童'",
+        f"date: {ddd}",
+        f"slug: {slug}",
+        "description:",
+        "---",
+        ""
+    ]
+
+    # 作者显示第一条的 AUTHOR
+    author_line = f"作者：{entries[0]['AUTHOR']}"
+    lines.append(author_line)
+    lines.append("")
+
+    for e in entries:
+        if e["TYPE"] == "HL":
+            lines.append(e["CONTENT"])
+            lines.append("")
+        elif e["TYPE"] == "NT":
+            lines.append(f"> {e['CONTENT']}")
+    content_text = "\n".join(lines)
+
+    with open(output_path, "w", encoding="utf-8") as f:
+        f.write(content_text)
+
+    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()