'update'

annotationdata.py

@@ -20,26 +20,81 @@ import os
 from collections import defaultdict
 
 class AnnotationManager:
+    """
+    iBooks笔记管理器
+    
+    负责从iBooks的AEAnnotation.sqlite数据库中提取和解析用户的阅读笔记和高亮标记。
+    支持获取所有书籍的笔记或指定书籍的笔记，并提供位置信息解析功能。
+    """
+    
     def __init__(self, db_path=None):
+        """
+        初始化笔记管理器
+        
+        Args:
+            db_path (str, optional): 数据库文件路径，默认使用config.LOCAL_ANNOTATION_DB
+        """
         self.db_path = db_path or config.LOCAL_ANNOTATION_DB
 
     @staticmethod
     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
+        解析iBooks笔记的位置信息
+        
+        从ZANNOTATIONLOCATION字段解析出章节标识符和文件内位置信息。
+        支持epubcfi格式的位置字符串解析。
+        
+        Args:
+            location (str): 笔记位置字符串，通常为epubcfi格式
+            
+        Returns:
+            tuple: (idref, filepos)
+                - idref (str): 章节标识符，用于定位具体章节
+                - filepos (str): 文件内位置，用于精确定位笔记位置
+                
+        Examples:
+            >>> parse_location('epubcfi(/6/746[id509]!/4[abc]/10,/2/1:0,/7:8)')
+            ('id509', 'abc')
         """
         idref = None
         filepos = None
         if not location:
             return idref, filepos
+        # 使用正则表达式提取[]内的内容
         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(self, bookid=None):
+        """
+        从数据库获取笔记数据
+        
+        从iBooks的AEAnnotation.sqlite数据库中提取所有或指定书籍的笔记和高亮内容。
+        自动处理时间戳转换和位置信息解析。
+        
+        Args:
+            bookid (str, optional): 书籍资产ID，如果为None则获取所有书籍的笔记
+            
+        Returns:
+            dict: 笔记数据字典，结构为：
+                {
+                    assetid: {
+                        uuid: {
+                            'creationdate': '创建日期',
+                            'filepos': '文件位置',
+                            'idref': '章节标识',
+                            'note': '笔记内容',
+                            'selectedtext': '选中文本'
+                        }
+                    }
+                }
+                
+        Note:
+            - 会检查WAL模式相关文件(-wal, -shm)的存在性
+            - 自动转换苹果时间戳格式(以2001-01-01为基准)
+            - 过滤掉既没有笔记也没有选中文本的空记录
+        """
         # 检查WAL模式相关文件
         base = self.db_path.rsplit('.', 1)[0]
         wal_path = base + '.sqlite-wal'
@@ -47,8 +102,11 @@ class AnnotationManager:
         for f in [self.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')
+        # 连接数据库并执行查询
         conn = sqlite3.connect(self.db_path)
         cursor = conn.cursor()
+        
+        # 根据是否指定bookid选择不同的查询语句
         if bookid is not None:
             cursor.execute('''
                 SELECT ZANNOTATIONASSETID, ZANNOTATIONCREATIONDATE, ZANNOTATIONLOCATION, ZANNOTATIONNOTE, ZANNOTATIONSELECTEDTEXT, ZANNOTATIONUUID
@@ -59,12 +117,16 @@ class AnnotationManager:
                 SELECT ZANNOTATIONASSETID, ZANNOTATIONCREATIONDATE, ZANNOTATIONLOCATION, ZANNOTATIONNOTE, ZANNOTATIONSELECTEDTEXT, ZANNOTATIONUUID
                 FROM ZAEANNOTATION
             ''')
+        
         rows = cursor.fetchall()
         annotations = defaultdict(dict)
         import datetime
+        
+        # 处理每一行数据
         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）
+            
+            # 转换 creationdate格式为'YYYY-MM-DD HH:MM:SS'，支持苹果时间戳（以2001-01-01为基准）
             date_str = creationdate
             if creationdate:
                 try:
@@ -74,13 +136,20 @@ class AnnotationManager:
                     elif isinstance(creationdate, str) and creationdate.replace('.', '', 1).isdigit():
                         dt = origin + datetime.timedelta(seconds=float(creationdate))
                     else:
+                        # 支持原有格式'2025/9/6'等
                         dt = datetime.datetime.strptime(creationdate[:10], "%Y-%m-%d")
-                    date_str = f"{dt.year}/{dt.month}/{dt.day}"
+                    date_str = dt.strftime('%Y-%m-%d %H:%M:%S')
                 except Exception:
                     date_str = str(creationdate)
+            
+            # 解析位置信息
             idref, filepos = self.parse_location(location)
+            
+            # 过滤空记录（既没有笔记也没有选中文本）
             if note is None and selectedtext is None:
                 continue
+                
+            # 构建笔记数据结构
             annotations[str(assetid)][uuid] = {
                 'creationdate': date_str,
                 'filepos': filepos,
@@ -88,14 +157,26 @@ class AnnotationManager:
                 'note': note,
                 'selectedtext': selectedtext
             }
+        
         conn.close()
+        
+        # 根据查询类型返回相应结果
         if bookid is not None:
             return {str(bookid): annotations.get(str(bookid), {})}
         return annotations
 
 if __name__ == "__main__":
+    """
+    测试模块功能
+    
+    包含两个测试用例：
+    1. 测试parse_location方法解析各种格式的位置字符串
+    2. 测试get_annotations方法获取指定书籍的笔记数据
+    """
     manager = AnnotationManager()
-    # 测试 parse_location
+    
+    # 测试 parse_location 方法
+    print("=== 测试位置解析功能 ===")
     test_locations = [
         'epubcfi(/6/746[id509]!/4[4MLOS0-27b363c65bfe41ad8429f530566a2737]/10,/2/1:0,/7:8',
         'epubcfi(/6/22[id15]!/4/156/1,:21,:157)',
@@ -105,7 +186,8 @@ if __name__ == "__main__":
         idref, filepos = manager.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
+    # 测试获取特定书籍的笔记
+    print("=== 测试笔记获取功能 ===")
     test_bookid = "B18FCD9F90FD43C2373AE52BAEF9A77C"
     annotations = manager.get_annotations(bookid=test_bookid)
     from pprint import pprint

booklist_parse.py

@@ -6,6 +6,7 @@ import os
 from collections import defaultdict
 
 class BookListManager:
+
     def __init__(self, plist_path=None, db_path=None):
         self.plist_path = plist_path or config.LOCAL_BOOKS_PLIST
         self.db_path = db_path or config.LOCAL_LIBRARY_DB
@@ -32,6 +33,93 @@ class BookListManager:
                 'date': book.get('BKInsertionDate',''),
                 'updatedate': book.get('updateDate','')
             }
+        # 统计每本书最近30天每天的阅读时长
+        try:
+            from annotationdata import AnnotationManager
+            import datetime
+            # 每天最小阅读时长（有笔记）
+            READ_TIME_DAY = getattr(config, 'READ_TIME_DAY', 60)  # 单位：分钟
+            # 无笔记但当天有打开书籍时的阅读时长
+            READ_TIME_OPEN_DAY = getattr(config, 'READ_TIME_OPEN_DAY', 30)  # 单位：分钟
+            today = datetime.datetime.now().date()
+            manager = AnnotationManager()
+            annotations = manager.get_annotations()
+            # 获取所有书籍的打开时间（ZLASTOPENDATE），单位为苹果时间戳
+            books_open = self.get_books_last_open()
+            this_year = today.year
+            for bk_id in booksinfo:
+                notes = annotations.get(bk_id, {})
+                day_notes = {}
+                # 收集每本书所有笔记的创建时间，按天分组
+                for uuid, note in notes.items():
+                    raw_date = note.get('creationdate')
+                    try:
+                        dt = datetime.datetime.strptime(raw_date, '%Y-%m-%d %H:%M:%S')
+                        day = dt.date()
+                        if day not in day_notes:
+                            day_notes[day] = []
+                        day_notes[day].append(dt)
+                    except Exception:
+                        pass
+                # 获取该书的打开时间戳（ZLASTOPENDATE），用于判断无笔记时是否有打开过书籍
+                open_info = books_open.get(bk_id, {})
+                last_open_ts = open_info.get('last_open')
+                # 生成最近30天的阅读时长列表
+                readtime30d = []
+                for i in range(30):
+                    day = today - datetime.timedelta(days=i)
+                    times = day_notes.get(day, [])
+                    if not times:
+                        opened = False
+                        if last_open_ts:
+                            open_dt = datetime.datetime(2001, 1, 1) + datetime.timedelta(seconds=last_open_ts)
+                            if open_dt.date() == day:
+                                opened = True
+                        readtime = READ_TIME_OPEN_DAY if opened else 0
+                    elif len(times) == 1:
+                        readtime = READ_TIME_DAY
+                    else:
+                        times_sorted = sorted(times)
+                        total_minutes = 0
+                        for idx in range(1, len(times_sorted)):
+                            delta = (times_sorted[idx] - times_sorted[idx-1]).total_seconds() / 60
+                            if 0 < delta <= 180:
+                                total_minutes += int(delta)
+                        readtime = total_minutes if total_minutes > 0 else READ_TIME_DAY
+                    readtime30d.append(readtime)
+                booksinfo[bk_id]['readtime30d'] = readtime30d
+
+                # 新增：统计今年每个月的阅读时长和年总阅读时长（遍历今年每一天）
+                readtime12m = [0] * 12  # 今年每月阅读时长
+                readtime_year = 0       # 今年总阅读时长
+                first_day = datetime.date(this_year, 1, 1)
+                days_in_year = (today - first_day).days + 1
+                for i in range(days_in_year):
+                    day = first_day + datetime.timedelta(days=i)
+                    times = day_notes.get(day, [])
+                    if not times:
+                        opened = False
+                        if last_open_ts:
+                            open_dt = datetime.datetime(2001, 1, 1) + datetime.timedelta(seconds=last_open_ts)
+                            if open_dt.date() == day:
+                                opened = True
+                        readtime = READ_TIME_OPEN_DAY if opened else 0
+                    elif len(times) == 1:
+                        readtime = READ_TIME_DAY
+                    else:
+                        times_sorted = sorted(times)
+                        total_minutes = 0
+                        for idx in range(1, len(times_sorted)):
+                            delta = (times_sorted[idx] - times_sorted[idx-1]).total_seconds() / 60
+                            if 0 < delta <= 180:
+                                total_minutes += int(delta)
+                        readtime = total_minutes if total_minutes > 0 else READ_TIME_DAY
+                    readtime12m[day.month-1] += readtime
+                    readtime_year += readtime
+                booksinfo[bk_id]['readtime12m'] = readtime12m
+                booksinfo[bk_id]['readtime_year'] = readtime_year
+        except Exception as e:
+            print(f'警告: 统计readtime30d失败: {e}')
         self._booksinfo = booksinfo
         return booksinfo
 
@@ -58,7 +146,45 @@ class BookListManager:
         self._books_open = books_open
         return books_open
 
+    def get_total_readtime(self, days=30):
+        """
+        获取最近days天每天所有书籍的总阅读时间（分钟），返回长度为days的列表。
+        列表第0项为今天，第1项为昨天，依次类推。
+        """
+        booksinfo = self.get_books_info()
+        total = [0] * days
+        for info in booksinfo.values():
+            readtime30d = info.get('readtime30d', [])
+            for i in range(min(days, len(readtime30d))):
+                total[i] += readtime30d[i]
+        return total
+
+    def get_total_readtime_year(self):
+        """
+        获取全年所有书的累计阅读时间（分钟）。
+        """
+        booksinfo = self.get_books_info()
+        total = 0
+        for info in booksinfo.values():
+            total += info.get('readtime_year', 0)
+        return total
+
+    def get_total_readtime12m(self):
+        """
+        获取全年所有书的月度累计阅读时间（长度12的列表，单位：分钟）。
+        """
+        booksinfo = self.get_books_info()
+        total = [0] * 12
+        for info in booksinfo.values():
+            readtime12m = info.get('readtime12m', [0]*12)
+            for i in range(12):
+                total[i] += readtime12m[i]
+        return total
+
 if __name__ == '__main__':
+    manager = BookListManager()
+    booksinfo = manager.get_books_info()
+
     manager = BookListManager()
     booksinfo = manager.get_books_info()
     from pprint import pprint
@@ -74,4 +200,48 @@ if __name__ == '__main__':
     for k, v in list(books_open.items())[:3]:
         ts = v['last_open']
         dt = datetime.datetime(2001, 1, 1) + datetime.timedelta(seconds=ts)
-        print(f"{k}: {dt} (timestamp: {ts})")
+        print(f"{k}: {dt} (timestamp: {ts})")
+
+    # 展示最近5天有阅读行为的书籍的readtime30d信息
+    print("\n【最近5天有阅读行为的书籍的readtime30d信息】")
+    books_with_recent_reading = []
+    for book_id, book in booksinfo.items():
+        readtime30d = book.get('readtime30d', [])
+        # 最近5天（含今天）有阅读行为
+        if len(readtime30d) >= 5 and any(rt > 0 for rt in readtime30d[:5]):
+            books_with_recent_reading.append((book_id, book))
+    for book_id, book in books_with_recent_reading:
+        print(f"书名: {book.get('displayname', book_id)}")
+        print(f"readtime30d: {book.get('readtime30d', [])}")
+        print('-' * 60)
+
+    # 测试每本书今年每月和年总阅读时长
+    print("\n【每本书今年每月阅读时长（分钟）和年总阅读时长】")
+    for k, v in booksinfo.items():
+        print(f"书名: {v.get('displayname', k)}")
+        print(f"readtime12m: {v.get('readtime12m', [])}")
+        print(f"readtime_year: {v.get('readtime_year', 0)} 分钟")
+        print('-' * 60)
+
+    # 测试get_total_readtime，天数可自定义
+    print("\n【最近7天每天所有书籍总阅读时间（分钟）】")
+    total_readtime7d = manager.get_total_readtime(days=7)
+    for i, mins in enumerate(total_readtime7d):
+        if i == 0:
+            label = "今天"
+        elif i == 1:
+            label = "昨天"
+        else:
+            label = f"{i}天前"
+        print(f"{label}: {mins} 分钟")
+
+        # 测试全年总阅读时间
+        print("\n【全年所有书的累计阅读时间（分钟）】")
+        total_readtime_year = manager.get_total_readtime_year()
+        print(f"全年总阅读时间: {total_readtime_year} 分钟")
+
+        # 测试全年每月累计阅读时间
+        print("\n【全年所有书的月度累计阅读时间（分钟）】")
+        total_readtime12m = manager.get_total_readtime12m()
+        for month, mins in enumerate(total_readtime12m, start=1):
+            print(f"{month}月: {mins} 分钟")

config.py

@@ -1,3 +1,5 @@
+# 统计用：无笔记但当天有打开书籍时的阅读时长（单位：分钟）
+READ_TIME_OPEN_DAY = 15
 """
 config.py
 ---------
@@ -29,5 +31,6 @@ LOCAL_ANNOTATION_WAL = os.path.join(DATA_DIR, 'AEAnnotation.sqlite-wal')
 LOCAL_LIBRARY_DB = os.path.join(DATA_DIR, 'BKLibrary.sqlite')
 LOCAL_BOOKS_PLIST = os.path.join(DATA_DIR, 'Books.plist')
 
-# 其他可扩展配置项
+# 统计用：每日最小阅读时长（单位：秒）
+READ_TIME_DAY = 60
 

readme.md

@@ -213,8 +213,8 @@ booksnote = {
 1. 增加QTUI
 2. 增加统计和展示
   统计
-  - 周活跃 - 7天每天的阅读时长，柱状图
-    每本书，ZANNOTATIONCREATIONDATE，落在7天前到今天的天数*60min(60mins为每天阅读时间，可配置） 
+  - 周活跃 - 30天每天的阅读时长，柱状图
+    某本书，根据每条笔记note中ZANNOTATIONCREATIONDATE，如果某天没有note，则阅读时间为0；如果只有一条note，阅读时间为READ_TIME_DAY=60(在config.py中配置)；如果note超过1条，计算第一条和最后一条的时间差，作为阅读时长。放在readtime30d这个list中。
   - 月活跃 - 30天每天的阅读时长，柱状图
     每本书，ZANNOTATIONCREATIONDATE，落在30天前到今天的天数*60min(60mins为每天阅读时间，可配置）
   - 已阅读的书籍: 每本平均阅读时长。所有书籍：总阅读时长，年阅读时长，年平均每日阅读时长，累计阅读天数。用气泡图表示。