14 KiB
14 KiB
name, description, status, version, date
| name | description | status | version | date |
|---|---|---|---|---|
| calibre-cleaner | 清洗 Calibre 书库:修复损坏书名/提取作者/检测编码损坏、小文件的批量删除 | proposal | v1 | 2026-06-24T03:23:27.062Z |
Calibre 书库清洗 Skill
概述
Calibre 书库整理三件套:
- 书名清洗 —— 修复从 txt 导入产生的 HTML 标签/长文本/乱码书名,截取前 20 个中文字符,移除网站链接
- 作者提取 —— 从书名或原始文件名
data.name中自动提取作者名(匹配作者:xxx、-xxx、BY xxx等格式) - 脏数据清理 —— 检测并删除内容损坏的 txt(中文 < 10%)、小于 10KB 的垃圾文件、Python 列表格式垃圾标题
前置条件
- 书库路径:
/home/yangxuan/calibre/books - 元数据文件:
/home/yangxuan/calibre/books/metadata.db - 运行前须停止其他 Calibre 进程(桌面版、Docker Calibre-Web)
- 运行前 必须备份
metadata.db
一、书名清洗 & 作者提取
shorten(s, max_bytes=120)
将字符串截断到指定字节数,避免因 UTF-8 中文字符跨字节而损坏。
def shorten(s, max_bytes=120):
encoded = s.encode('utf-8')
if len(encoded) <= max_bytes:
return s
try:
return encoded[:max_bytes].decode('utf-8')
except:
return encoded[:max_bytes-3].decode('utf-8', errors='ignore')
clean_title(title)
def clean_title(title):
t = title
# 移除 HTML 标签
t = re.sub(r'<[^>]+>', '', t)
# 替换 _BR_ / _BR 标记
t = re.sub(r'_BR_', ' ', t, flags=re.IGNORECASE)
t = re.sub(r'_BR(?![a-zA-Z])', ' ', t)
# 移除 _fontxxx_ / _imgxxx_ 标记
t = re.sub(r'_font[^_]*_', '', t)
t = re.sub(r'_img[^_]*_', '', t)
# 移除网站链接
t = re.sub(r'[\((]www\.[^))]+[\))]', '', t)
t = re.sub(r'^[a-zA-Z0-9.-]+\.com@', '', t)
t = re.sub(r'[-–—][a-zA-Z0-9.-]+\.com$', '', t)
t = re.sub(r'【[^】]*?(?:下载|网站|书城|声明|提供)[^】]*】', '', t)
t = re.sub(r'[::].*?(?:本文由|本电子书).*$', '', t)
t = re.sub(r'[//]\s*www\.[^\s]+.*$', '', t)
t = re.sub(r'[,,。]?https?://[^\s\))\]]+', '', t)
# 移除声明文字当书名
t = re.sub(r'^内容简介[】】]?', '', t)
# 移除作者/翻译标记(批量清洗时用)
t = re.sub(r'[ \s]*?(?:作者|翻译|原?作者)[::].*$', '', t, flags=re.DOTALL)
# 移除 Unknown/未知 尾巴
t = re.sub(r'\s*-\s*(Unknown|未知)\s*$', '', t)
# 合并多余空格
t = re.sub(r'\s+', ' ', t).strip()
# 截取前 20 个中文字符(保留非中文直到第 20 个中文出现)
chinese_count = 0
pos = 0
for i, c in enumerate(t):
if '\u4e00' <= c <= '\u9fff':
chinese_count += 1
if chinese_count == 20:
pos = i + 1
break
if chinese_count > 20:
t = t[:pos]
# 超长截短
if len(t) > 100:
m = re.search(r'[\u4e00-\u9fff]{2,}', t)
if m:
t = t[m.start():]
t = t[:60].rstrip(',。;:、!?…\ufffd\'"').rstrip('.,;:!?\'').strip()
# 移除控制字符
t = re.sub(r'[\x00-\x08\x0b\x0c\x0e-\x1f]', '', t)
return shorten(t, 100).strip() or 'Unknown'
作者提取规则(从文件中同时匹配 title 和 data.name)
优先从 data.name(原始文件名)提取,更准确:
EXCLUDE_AUTHORS = {'正文', '内容简介', ''}
def extract_author_from_name(file_name):
"""从 data.name(原始文件名)提取作者"""
name = file_name
# 去掉尾巴
name = re.sub(r'\s*-\s*(Unknown|未知)\s*$', '', name)
# 匹配作者:xxx
m = re.search(r'作者[::]\s*([^\s_)\)《\[【\]】\-,]+)', name)
if m:
candidate = m.group(1).strip()
if candidate not in EXCLUDE_AUTHORS and len(candidate) < 30:
return candidate
# 匹配翻译:xxx
m = re.search(r'翻译[::]\s*([^\s_)\)《\[【\]】\-,]+)', name)
if m:
candidate = m.group(1).strip()
if len(candidate) < 20:
return candidate
# 匹配原作者:xxx
m = re.search(r'原?作者[::]\s*([^\s_)\)《\[【\]】\-,]+)', name)
if m:
candidate = m.group(1).strip()
if len(candidate) < 30:
return candidate
return None
def extract_author_from_title(title):
"""从 title 提取作者(降级方案,仅在 data.name 无用时)"""
m = re.search(r'作者[::]\s*([^\s,,、\))《\[]+)', title)
if m:
name = m.group(1).strip()
if name not in EXCLUDE_AUTHORS and not re.match(r'^第\d+[章节]', name):
return name
m = re.search(r'翻译[::]\s*([^\s,,、\))《\[]+)', title)
if m:
return m.group(1).strip()
m = re.search(r'\b[Bb][Yy]\s+([^\s,,、\))《\[]+)', title)
if m:
name = m.group(1).strip()
if name not in EXCLUDE_AUTHORS:
return name
m = re.search(r'-([^-()【】\[\]{}《》\s]{2,30})$', title)
if m:
name = m.group(1).strip()
if name not in EXCLUDE_AUTHORS and not re.match(r'^\d+', name):
return name
m = re.search(r'&([^&()【】\[\]\s]{2,30})$', title)
if m:
name = m.group(1).strip()
if name not in EXCLUDE_AUTHORS:
return name
return None
坏书检测条件
is_bad = (
len(title) > 100 or
'<img' in title or '<BR' in title or '<font' in title or
'\ufffd' in title or
len(title.encode('utf-8')) > 150
)
二、脏数据清理
2.1 检测条件
扫描书库中所有 TXT 文件,读取前 20KB 检测中文比例:
- 内容损坏/二进制垃圾:中文比例 < 10%(标记为待删除)
- 小文件垃圾:
uncompressed_size < 10240(10KB 以下) - 垃圾格式标题:Python 列表格式(含
'xxx', 'R-18'单引号列表)、转义字符(\n、\u3000、id=)、HTML 实体(raquo;、laquo;)
def is_garbage_format_title(title):
"""检测标题是否为垃圾格式"""
import re
if re.search(r"'.*',\s*'R-18'", title):
return True
if re.search(r'[\\]u[0-9a-fA-F]{4}', title):
return True
if re.search(r'id=|pid=', title):
return True
if 'raquo;' in title or 'laquo;' in title:
return True
if '【内容简介】' in title or '内容简介】' in title:
return True
return False
def is_dirty_content(full_path):
"""检测文件内容是否为垃圾"""
if not os.path.exists(full_path):
return True # 文件丢失也算脏
with open(full_path, 'rb') as f:
raw = f.read(20480)
text = raw.decode('utf-8', errors='replace')
chinese = sum(1 for c in text if '\u4e00' <= c <= '\u9fff')
ratio = chinese / len(text) if len(text) > 0 else 0
return ratio < 0.10
2.2 批量删除(通过 SQLite 直写)
停掉 calibre 进程后,通过 SQLite 删除记录并清理文件系统:
DELETE FROM data WHERE book = ?
DELETE FROM books_authors_link WHERE book = ?
DELETE FROM books_languages_link WHERE book = ?
DELETE FROM books_publishers_link WHERE book = ?
DELETE FROM books_series_link WHERE book = ?
DELETE FROM books_tags_link WHERE book = ?
DELETE FROM comments WHERE book = ?
DELETE FROM identifiers WHERE book = ?
DELETE FROM books WHERE id = ?
同时删除对应目录:shutil.rmtree(os.path.join('/home/yangxuan/calibre/books', bpath))
2.3 完整删除脚本
import sqlite3, os, shutil
db_path = '/home/yangxuan/calibre/books/metadata.db'
conn = sqlite3.connect(db_path)
c = conn.cursor()
c.execute('''
SELECT b.id, b.title, b.path, d.name, d.uncompressed_size
FROM books b
JOIN data d ON d.book = b.id
WHERE d.format = 'TXT'
''')
rows = c.fetchall()
to_delete = []
for bid, title, bpath, fname, size in rows:
full_path = os.path.join('/home/yangxuan/calibre/books', bpath, fname + '.txt')
# 条件0:垃圾格式标题(Python列表、转义字符等)
if is_garbage_format_title(title):
to_delete.append((bid, bpath))
continue
# 条件1:小文件垃圾
if size < 10240:
to_delete.append((bid, bpath))
continue
if not os.path.exists(full_path):
continue
# 条件2:内容损坏(中文 < 10%)
if is_dirty_content(full_path):
to_delete.append((bid, bpath))
print(f"待删除: {len(to_delete)}", flush=True)
for bid, bpath in to_delete:
for table in ['data', 'books_authors_link', 'books_languages_link',
'books_publishers_link', 'books_series_link', 'books_tags_link',
'comments', 'identifiers']:
c.execute(f'DELETE FROM {table} WHERE book=?', (bid,))
c.execute('DELETE FROM books WHERE id=?', (bid,))
full_dir = os.path.join('/home/yangxuan/calibre/books', bpath)
if os.path.exists(full_dir):
shutil.rmtree(full_dir)
conn.commit()
conn.close()
print(f"完成,删除: {len(to_delete)}", flush=True)
三、书名批量清洗(作者标记去除 + 前 20 中文截取)
对于书名中含 作者:xxx、翻译:xxx 标记但作者字段已有值的书,使用此脚本批量清洗:
import sqlite3, re
db_path = '/home/yangxuan/calibre/books/metadata.db'
conn = sqlite3.connect(db_path)
c = conn.cursor()
c.execute('''
SELECT b.id, b.title, a.name as author_name, d.name as file_name
FROM books b
JOIN data d ON d.book = b.id AND d.format = 'TXT'
JOIN books_authors_link l ON b.id = l.book
JOIN authors a ON l.author = a.id
WHERE (b.title LIKE '%作者:%' OR b.title LIKE '%作者:%' OR b.title LIKE '%翻译:%' OR b.title LIKE '%翻译:%')
AND a.name NOT IN ('未知', 'Unknown')
ORDER BY b.id
''')
rows = c.fetchall()
for bid, title, author_name, file_name in rows:
# 1. 从 data.name 提取作者并更新 author 字段(如不同)
name_clean = re.sub(r'\s*-\s*(Unknown|未知)\s*$', '', file_name)
m = re.search(r'[ \s]*?(?:作者|翻译|原?作者)[::]\s*([^\s_)\)《\[【\]】\-,]+)', name_clean)
if m:
extracted = m.group(1).strip()
if extracted and extracted != author_name and len(extracted) < 30:
cur = conn.cursor()
cur.execute("SELECT id FROM authors WHERE name=?", (extracted,))
ar = cur.fetchone()
if ar:
aid = ar[0]
else:
cur.execute("INSERT INTO authors (name, sort) VALUES (?, ?)", (extracted, extracted.replace(',', '').strip()))
aid = cur.lastrowid
cur.execute("UPDATE books_authors_link SET author=? WHERE book=?", (aid, bid))
cur.close()
# 2. 裁剪书名:去标记 + 前 20 中文
clean_title = re.sub(r'[ \s]*?(?:作者|翻译|原?作者)[::].*$', '', file_name, flags=re.DOTALL)
clean_title = re.sub(r'\s*-\s*(Unknown|未知)\s*$', '', clean_title).strip()
if clean_title:
count = 0
pos = 0
for i, ch in enumerate(clean_title):
if '\u4e00' <= ch <= '\u9fff':
count += 1
if count == 20:
pos = i + 1
break
if count > 20:
clean_title = clean_title[:pos]
if clean_title != title:
c.execute("UPDATE books SET title=? WHERE id=?", (clean_title, bid))
conn.commit()
conn.close()
四、常用查询
4.1 查看 XX 作者的书
sqlite3 /home/yangxuan/calibre/books/metadata.db "
SELECT b.id, b.title
FROM books b JOIN books_authors_link l ON b.id = l.book
JOIN authors a ON l.author = a.id
WHERE a.name = 'Unknown'
LIMIT 20;
"
4.2 统计作者分布
sqlite3 /home/yangxuan/calibre/books/metadata.db "
SELECT a.name, COUNT(*) as cnt
FROM books b JOIN books_authors_link l ON b.id = l.book
JOIN authors a ON l.author = a.id
GROUP BY a.name ORDER BY cnt DESC LIMIT 20;
"
4.3 书名异常检测
sqlite3 /home/yangxuan/calibre/books/metadata.db "
SELECT id, title FROM books WHERE
title LIKE '%作者%' OR title LIKE '%翻译%' OR
title LIKE '%.com%' OR title LIKE '%http%' OR
title LIKE '%内容简介%' OR
LENGTH(title) > 80;
"
4.4 书库统计
python3 -c "
import sqlite3
conn = sqlite3.connect('/home/yangxuan/calibre/books/metadata.db')
c = conn.cursor()
c.execute('SELECT COUNT(*) FROM books')
print(f'总书籍: {c.fetchone()[0]}')
c.execute('SELECT COUNT(*) FROM data WHERE format=\"TXT\"')
print(f'TXT 文件: {c.fetchone()[0]}')
conn.close()
"
五、操作流程(推荐顺序)
cd /home/yangxuan/calibre
# 1. 停服务 + 备份
docker compose down
cp books/metadata.db books/metadata.db.backup.$(date +%Y%m%d)
killall calibre 2>/dev/null
# 2. 脏数据清理(内容损坏 + 小文件 + 垃圾格式标题)
python3 /path/to/clean_dirty_data.py
# 3. 书名清洗 & 作者提取(含 data.name 级别提取)
calibre-debug /path/to/fix_titles.py
# 4. 检查是否有遗漏的异常书籍
sqlite3 books/metadata.db \"SELECT id, title FROM books WHERE title LIKE '%作者%' OR title LIKE '%翻译%' OR title LIKE '%.com%';\" | head -10
# 5. 重启
docker compose up -d
六、已知问题
set_metadata 报 Errno 36 文件名过长
当 author_sort 字段超 80 字节时,Calibre 路径会触及 ext4 255 字节限制。先清理极长作者名:
sqlite3 /home/yangxuan/calibre/books/metadata.db "
UPDATE authors SET name='Unknown' WHERE LENGTH(name) > 30;
"
WSL /mnt/f 删除 NTFS 文件权限不够
WSL 的 drvfs 默认不带 metadata 选项,sudo rm、os.remove、cmd.exe /c del 均无法删除 NTFS 文件。不要在 WSL 下尝试跨分区删除操作,直接让 Windows 侧(文件资源管理器/PowerShell)操作。
书名长度截取规则
title 字段清洗后最多保留 20 个中文字符。计数规则:只计 Unicode 范围的 \u4e00-\u9fff 中文字符,保留第 20 个中文之前的所有字符(含非中文)。如书名不足 20 个中文则全保留。
title vs data.name 区别
books.title:Calibre 界面显示的书名(清洗后的)data.name:导入时的原始文件名(不含.txt)- 作者提取优先使用
data.name,其文件名保留原始信息、更可靠