221 lines
8.2 KiB
Python
221 lines
8.2 KiB
Python
"""
|
||
exportbooknotes.py
|
||
------------------
|
||
功能：
|
||
- 自动同步iBooks数据库和元数据文件到本地data目录。
|
||
- 解析AEAnnotation.sqlite、Books.plist、BKLibrary.sqlite，构建结构化笔记数据。
|
||
- 解析epub目录和章节信息，定位每条笔记所属章节。
|
||
- 命令行菜单按最近打开时间降序展示书籍列表，供用户选择导出。
|
||
- 仅导出选中书籍的所有笔记，按章节分组，生成Markdown文件。
|
||
|
||
依赖：config.py 统一管理路径和配置项。
|
||
|
||
主要数据流：
|
||
1. 数据同步到data目录
|
||
2. 解析Books.plist获取书籍元数据
|
||
3. 解析BKLibrary.sqlite获取最近打开时间
|
||
4. 菜单排序与显示（书名+时间戳）
|
||
5. 解析AEAnnotation.sqlite获取笔记
|
||
6. 解析epub目录，定位章节
|
||
7. 导出Markdown文件
|
||
|
||
依赖：Python 3, InquirerPy, bs4, shutil, os, datetime, sqlite3
|
||
|
||
主要数据流：
|
||
|
||
典型用法：
|
||
python exportbooknotes.py
|
||
# 按提示选择书籍，自动导出笔记到export_notes目录
|
||
"""
|
||
import config
|
||
"""
|
||
自动生成 booksnote 数据结构：
|
||
booksnote = {
|
||
assetid: { label_path: { uuid: {
|
||
'creationdate': '2023/7/12',
|
||
'filepos': None,
|
||
'idref': '008.xhtml',
|
||
'note': None,
|
||
'selectedtext': '這就是宣傳的恐怖之處'
|
||
}}}
|
||
}
|
||
"""
|
||
from collections import defaultdict
|
||
import os
|
||
from annotationdata import get_annotations
|
||
from booklist_parse import parse_books_plist
|
||
from opf_parse import parse_opf
|
||
from toc_parse import parse_navpoints, find_label_path
|
||
from bs4 import BeautifulSoup
|
||
from pprint import pprint
|
||
|
||
def find_file_by_ext(root, exts):
|
||
"""在root下递归查找第一个指定后缀的文件"""
|
||
for dirpath, _, files in os.walk(root):
|
||
for f in files:
|
||
for ext in exts:
|
||
if f.lower().endswith(ext):
|
||
return os.path.join(dirpath, f)
|
||
return None
|
||
|
||
def get_toc_tree(toc_path):
|
||
with open(toc_path, 'r', encoding='utf-8') as f:
|
||
soup = BeautifulSoup(f, 'xml')
|
||
nav_map = soup.find('navMap')
|
||
|
||
nav_points = nav_map.find_all('navPoint', recursive=False)
|
||
toc_tree = parse_navpoints(nav_points)
|
||
#pprint(toc_tree, indent=2, depth=5)
|
||
return toc_tree
|
||
|
||
def build_booksnote(annotation_db=config.LOCAL_ANNOTATION_DB, books_plist=config.LOCAL_BOOKS_PLIST, bookid=None):
|
||
# 支持只处理特定 assetid 的笔记
|
||
annotations = get_annotations(annotation_db, bookid=bookid)
|
||
booksinfo = parse_books_plist(books_plist)
|
||
booksnote = defaultdict(lambda: defaultdict(dict))
|
||
for assetid, notes in annotations.items():
|
||
# 获取epub路径
|
||
bookinfo = booksinfo.get(assetid)
|
||
if not bookinfo:
|
||
continue
|
||
epub_path = bookinfo.get('path')
|
||
if not epub_path or not os.path.isdir(epub_path):
|
||
continue
|
||
# 查找opf和ncx
|
||
opf_path = find_file_by_ext(epub_path, ['.opf'])
|
||
ncx_path = find_file_by_ext(epub_path, ['.ncx'])
|
||
if not opf_path or not ncx_path:
|
||
continue
|
||
id2href = parse_opf(opf_path)
|
||
toc_tree = get_toc_tree(ncx_path)
|
||
for uuid, ann in notes.items():
|
||
idref = ann['idref']
|
||
filepos = ann['filepos']
|
||
href = id2href.get(idref, idref)
|
||
chapter = find_label_path(toc_tree, href, filepos)
|
||
if chapter is None:
|
||
# 直接从html文件获取章节信息
|
||
html_path = os.path.join(epub_path, href.split('#')[0])
|
||
selectedtext = ann.get('selectedtext')
|
||
if os.path.exists(html_path) and selectedtext:
|
||
from toc_parse import find_section_by_selectedtext
|
||
section = find_section_by_selectedtext(html_path, selectedtext)
|
||
if section:
|
||
chapter = section
|
||
else:
|
||
chapter = "(未找到章节)"
|
||
else:
|
||
chapter = "(未找到章节)"
|
||
booksnote[assetid][chapter][uuid] = {
|
||
'creationdate': ann['creationdate'],
|
||
'filepos': filepos,
|
||
'idref': href,
|
||
'note': ann['note'],
|
||
'selectedtext': ann['selectedtext']
|
||
}
|
||
return booksnote
|
||
|
||
import datetime
|
||
|
||
def export_booksnote_to_md(booksnote, booksinfo, out_path=None):
|
||
"""
|
||
依据booksnote结构导出markdown文件，格式：
|
||
# “笔记导出”+导出时间
|
||
## 书名
|
||
### chapter
|
||
selectedtext
|
||
> note (如果存在)
|
||
"""
|
||
now = datetime.datetime.now().strftime('%Y-%m-%d %H:%M')
|
||
lines = [f'# 笔记导出 {now}\n']
|
||
for assetid, chapters in booksnote.items():
|
||
bookname = booksinfo.get(assetid, {}).get('itemname', assetid)
|
||
lines.append(f'\n## {bookname}\n')
|
||
for chapter, notes in chapters.items():
|
||
lines.append(f'### {chapter}')
|
||
for uuid, ann in notes.items():
|
||
sel = ann.get('selectedtext')
|
||
note = ann.get('note')
|
||
if sel:
|
||
lines.append(sel)
|
||
if note:
|
||
lines.append(f'> {note}')
|
||
lines.append('')
|
||
md = '\n'.join(lines)
|
||
if out_path:
|
||
with open(out_path, 'w', encoding='utf-8') as f:
|
||
f.write(md)
|
||
return md
|
||
|
||
|
||
if __name__ == '__main__':
|
||
import shutil
|
||
import os.path
|
||
# 自动覆盖 ./data 下的数据库和plist文件，源为iBooks真实路径
|
||
src_files = [
|
||
(config.IBOOKS_ANNOTATION_DB, config.LOCAL_ANNOTATION_DB),
|
||
(config.IBOOKS_ANNOTATION_SHM, config.LOCAL_ANNOTATION_SHM),
|
||
(config.IBOOKS_ANNOTATION_WAL, config.LOCAL_ANNOTATION_WAL),
|
||
(config.IBOOKS_LIBRARY_DB, config.LOCAL_LIBRARY_DB),
|
||
(config.IBOOKS_BOOKS_PLIST, config.LOCAL_BOOKS_PLIST)
|
||
]
|
||
for src, dst in src_files:
|
||
if os.path.exists(src):
|
||
shutil.copy2(src, dst)
|
||
print(f'copy source data file to ./data : {dst}')
|
||
else:
|
||
print(f'file not found: {src} ')
|
||
|
||
from booklist_parse import parse_books_plist
|
||
from InquirerPy import inquirer # type: ignore
|
||
|
||
# 先获取所有书籍元数据
|
||
booksinfo = parse_books_plist(config.LOCAL_BOOKS_PLIST)
|
||
|
||
# 构建书名列表（优先displayname, 其次itemname, 否则assetid），按parse_books_plist中的date字段排序
|
||
assetid2name = {}
|
||
assetid2lastopen = {}
|
||
from booklist_parse import get_books_last_open
|
||
|
||
# 获取所有书籍的最后打开时间（字典，值为{'last_open': 时间戳}）
|
||
last_open_times = get_books_last_open(config.LOCAL_LIBRARY_DB)
|
||
|
||
for assetid, info in booksinfo.items():
|
||
name = info.get('displayname') or info.get('itemname') or assetid
|
||
# 如果书名中包含“-”，只取“-”前面的部分
|
||
if '-' in name:
|
||
name = name.split('-', 1)[0].strip()
|
||
assetid2name[assetid] = name
|
||
# 用 get_books_last_open 返回的时间戳排序，如无则为0
|
||
ts = last_open_times.get(assetid, {}).get('last_open', 0)
|
||
assetid2lastopen[assetid] = ts
|
||
|
||
# 按last_open时间戳降序排列
|
||
sorted_assetids = sorted(assetid2name.keys(), key=lambda aid: assetid2lastopen[aid], reverse=True)
|
||
choices = [f"{assetid2name[aid]} [{assetid2lastopen[aid]}]" for aid in sorted_assetids]
|
||
if not choices:
|
||
print("无可导出的笔记")
|
||
exit(0)
|
||
answer = inquirer.fuzzy(
|
||
message="请选择要导出的书名（支持模糊搜索）:",
|
||
choices=choices,
|
||
multiselect=False,
|
||
instruction="上下键选择，输入可模糊筛选，回车确定"
|
||
).execute()
|
||
|
||
# 解析选中assetid
|
||
for aid, name in assetid2name.items():
|
||
if answer.startswith(name):
|
||
selected_assetid = aid
|
||
break
|
||
else:
|
||
print("未找到选中书籍")
|
||
exit(1)
|
||
|
||
# 只导出选中书的笔记
|
||
selected_booksnote = build_booksnote(bookid=selected_assetid)
|
||
selected_booksinfo = {selected_assetid: booksinfo.get(selected_assetid, {})}
|
||
out_path = f'export_notes/notes_export_{selected_assetid}.md'
|
||
export_booksnote_to_md(selected_booksnote, selected_booksinfo, out_path)
|
||
print(f'《{selected_booksinfo[selected_assetid].get("displayname") or selected_booksinfo[selected_assetid].get("itemname") or selected_assetid}》 导出笔记 {out_path}')
|