137 lines
5.3 KiB
Python
137 lines
5.3 KiB
Python
"""
|
||
annotationdata.py
|
||
-----------------
|
||
功能：
|
||
- 解析iBooks的AEAnnotation.sqlite数据库，提取所有或指定书籍（assetid/bookid）的笔记。
|
||
- 提供parse_location辅助函数，解析笔记定位信息。
|
||
- 返回结构化的annotations数据，便于后续章节定位与导出。
|
||
|
||
依赖：config.py 统一管理路径和配置项。
|
||
|
||
主要接口：
|
||
- get_annotations(db_path, bookid=None)：返回所有或指定assetid的笔记，结构为{assetid: {uuid: {...}}}
|
||
- parse_location(location)：解析ZANNOTATIONLOCATION，返回(idref, filepos)
|
||
|
||
依赖：sqlite3, collections, re, os, datetime
|
||
"""
|
||
import config
|
||
|
||
import sqlite3
|
||
from collections import defaultdict
|
||
import re
|
||
import os
|
||
|
||
def parse_location(location):
|
||
"""
|
||
解析ZANNOTATIONLOCATION，返回(idref, filepos)
|
||
- epubcfi(...)格式优先提取[]内内容为idref
|
||
- 其他格式兼容原逻辑
|
||
"""
|
||
idref = None
|
||
filepos = None
|
||
if not location:
|
||
return idref, filepos
|
||
# 统一处理，提取前两个[]内容
|
||
matches = re.findall(r'\[(.*?)\]', location) if location else []
|
||
idref = matches[0] if len(matches) > 0 else None
|
||
filepos = matches[1] if len(matches) > 1 else None
|
||
return idref, filepos
|
||
|
||
def get_annotations(db_path=config.LOCAL_ANNOTATION_DB, bookid=None):
|
||
# 检查WAL模式相关文件
|
||
base = db_path.rsplit('.', 1)[0]
|
||
wal_path = base + '.sqlite-wal'
|
||
shm_path = base + '.sqlite-shm'
|
||
for f in [db_path, wal_path, shm_path]:
|
||
if not os.path.exists(f):
|
||
print(f'警告: 缺少 {f}，可能无法获取全部最新笔记')
|
||
conn = sqlite3.connect(db_path)
|
||
cursor = conn.cursor()
|
||
if bookid is not None:
|
||
cursor.execute('''
|
||
SELECT ZANNOTATIONASSETID, ZANNOTATIONCREATIONDATE, ZANNOTATIONLOCATION, ZANNOTATIONNOTE, ZANNOTATIONSELECTEDTEXT, ZANNOTATIONUUID
|
||
FROM ZAEANNOTATION WHERE ZANNOTATIONASSETID=?
|
||
''', (bookid,))
|
||
else:
|
||
cursor.execute('''
|
||
SELECT ZANNOTATIONASSETID, ZANNOTATIONCREATIONDATE, ZANNOTATIONLOCATION, ZANNOTATIONNOTE, ZANNOTATIONSELECTEDTEXT, ZANNOTATIONUUID
|
||
FROM ZAEANNOTATION
|
||
''')
|
||
rows = cursor.fetchall()
|
||
annotations = defaultdict(dict)
|
||
import datetime
|
||
for row in rows:
|
||
assetid, creationdate, location, note, selectedtext, uuid = row
|
||
# 转换 creationdate 格式，支持苹果时间戳（以2001-01-01为基准）
|
||
date_str = creationdate
|
||
if creationdate:
|
||
try:
|
||
origin = datetime.datetime(2001, 1, 1)
|
||
# 苹果时间戳 float/int 或数字字符串
|
||
if isinstance(creationdate, (int, float)):
|
||
dt = origin + datetime.timedelta(seconds=creationdate)
|
||
elif isinstance(creationdate, str) and creationdate.replace('.', '', 1).isdigit():
|
||
dt = origin + datetime.timedelta(seconds=float(creationdate))
|
||
else:
|
||
dt = datetime.datetime.strptime(creationdate[:10], "%Y-%m-%d")
|
||
date_str = f"{dt.year}/{dt.month}/{dt.day}"
|
||
except Exception:
|
||
date_str = str(creationdate)
|
||
idref, filepos = parse_location(location)
|
||
# 跳过note和selectedtext都为None的笔记
|
||
if note is None and selectedtext is None:
|
||
continue
|
||
annotations[str(assetid)][uuid] = {
|
||
'creationdate': date_str,
|
||
'filepos': filepos,
|
||
'idref': idref,
|
||
'note': note,
|
||
'selectedtext': selectedtext
|
||
}
|
||
conn.close()
|
||
if bookid is not None:
|
||
# 只返回特定bookid的笔记结构
|
||
return {str(bookid): annotations.get(str(bookid), {})}
|
||
return annotations
|
||
|
||
# 用法示例：输出每本书的前3条笔记
|
||
if __name__ == "__main__":
|
||
# 测试 parse_location
|
||
'''
|
||
test_locations = [
|
||
'epubcfi(/6/746[id509]!/4[4MLOS0-27b363c65bfe41ad8429f530566a2737]/10,/2/1:0,/7:8',
|
||
'epubcfi(/6/22[id15]!/4/156/1,:21,:157)',
|
||
'epubcfi(/6/764[id518]!/4[4V8DU0-27b363c65bfe41ad8429f530566a2737]/56,/1:0,/3:2)'
|
||
]
|
||
for loc in test_locations:
|
||
idref, filepos = parse_location(loc)
|
||
print(f"location: {loc}\n idref: {idref}\n filepos: {filepos}\n")
|
||
'''
|
||
|
||
# 测试只获取特定 assetid 的笔记
|
||
test_bookid = "B18FCD9F90FD43C2373AE52BAEF9A77C"
|
||
annotations = get_annotations(bookid=test_bookid)
|
||
|
||
# 格式化打印该书的所有笔记
|
||
from pprint import pprint
|
||
print(f"\nAssetID={test_bookid} 的所有笔记:")
|
||
pprint(annotations, indent=2, sort_dicts=False)
|
||
|
||
# 输出每本书的前3条笔记
|
||
'''
|
||
book_notes = defaultdict(list)
|
||
for assetid, notes_dict in annotations.items():
|
||
for uuid, ann in notes_dict.items():
|
||
book_notes[assetid].append({**ann, 'uuid': uuid})
|
||
for assetid, notes in book_notes.items():
|
||
print(f"\nAssetID: {assetid}")
|
||
for i, note in enumerate(notes[:3]):
|
||
print(f" 笔记{i+1}:")
|
||
print(f" creationdate: {note['creationdate']}")
|
||
print(f" idref: {note['idref']}")
|
||
print(f" filepos: {note['filepos']}")
|
||
print(f" note: {note['note']}")
|
||
print(f" selectedtext: {note['selectedtext']}")
|
||
print(f" uuid: {note['uuid']}")
|
||
'''
|