Files
2026-07-02 11:00:05 +08:00

8.3 KiB
Raw Permalink Blame History

name, description, status, version, date
name description status version date
calibre-title-cleaner 清洗 Calibre 书库中损坏的 txt 文档书名(HTML标签/长文本/乱码/路径超限修复) proposal v2 2026-06-24T01:12:53.053Z

Calibre 书库书名清洗 & 作者提取 Skill

概述

清洗 Calibre 书库中因从 txt 文件自动导入而产生的损坏书名,同时从书名中提取作者信息并更新到作者字段。适用于 Calibre 书库路径 /home/yangxuan/calibre/books

前置条件

  • Calibre 数据库路径:/home/yangxuan/calibre/books
  • 元数据文件:/home/yangxuan/calibre/books/metadata.db
  • 需要 calibre-debugcalibre Python 环境(使用 LibraryDatabase API
  • 运行前须停止其他 Calibre 进程(桌面版、Calibre-Web Docker
  • 运行前必须备份 metadata.db

作者提取规则(从书名中提取)

需要匹配的作者格式(基于实际书库数据)

格式 示例 正则
作者:xxx(中文冒号) ...作者:镜欲 作者[:]\s*([^\s,,、\)]+)
作者:xxx(英文冒号) ...作者:镜欲 同上
-xxx(英文 dash 结尾) 善良的美艳妈妈-糠麸 -([^-()【】\[\]]+)$
翻译:xxx ...翻译:kkmanlg 翻译[:]\s*([^\s,,、\)]+)
BY xxx(英文 BY ...BY狱厨 \b[Bb][Yy]\s+([^\s,,、\)]+)
&xxxand 符结尾) ...&axenic &([^&()【】\[\] ]+)$

提取策略

  1. 优先匹配精确的"作者:"标记(最可靠)
  2. 失败后尝试 -xxx 结尾(短作者名)
  3. 再尝试 翻译:BY&xxx
  4. 如果提取到的作者名仍是乱填的(如 正文第01章【内容简介】),跳过,标为 Unknown

排除项(以下不是真作者)

  • 正文内容简介
  • 第\d+[章节](章节名)
  • 长度 > 30 字符的内容摘要

书名清洗规则

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)
    # 合并多余空格
    t = re.sub(r'\s+', ' ', t).strip()
    # 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'

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
)

完整脚本示例(含作者提取)

import re
from calibre.db.legacy import LibraryDatabase

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')

EXCLUDE_AUTHORS = {'正文', '内容简介', ''}

def extract_author_from_title(title):
    """从书名中提取作者名"""
    # 1. 作者:xxx
    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
    # 2. 翻译:xxx
    m = re.search(r'翻译[:]\s*([^\s,,、\))《\[]+)', title)
    if m:
        return m.group(1).strip()
    # 3. BY xxx
    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
    # 4. -xxx 结尾(最后一个 dash 后的词)
    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
    # 5. &xxx 结尾
    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

def clean_title_and_extract_author(n):
    """清洗书名并返回 (cleaned_title, extracted_author_or_None)"""
    t = n
    t = re.sub(r'<[^>]+>', '', t)
    t = re.sub(r'_BR_', ' ', t, flags=re.IGNORECASE)
    t = re.sub(r'_BR(?![a-zA-Z])', ' ', t)
    t = re.sub(r'_font[^_]*_', '', t)
    t = re.sub(r'_img[^_]*_', '', t)
    t = re.sub(r'\s+', ' ', t).strip()

    extracted_author = extract_author_from_title(t)

    # 如果提取到了作者,从书名中移除作者部分
    if extracted_author:
        t = re.sub(r'作者[:]\s*' + re.escape(extracted_author), '', t)
        t = re.sub(r'翻译[:]\s*' + re.escape(extracted_author), '', t)
        t = re.sub(r'\b[Bb][Yy]\s+' + re.escape(extracted_author), '', t)
        t = re.sub(r'-' + re.escape(extracted_author) + r'$', '', t)
        t = re.sub(r'&' + re.escape(extracted_author) + r'$', '', t)

    # 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()

    t = re.sub(r'[\x00-\x08\x0b\x0c\x0e-\x1f]', '', t)
    t = shorten(t, 100).strip() or 'Unknown'

    return t, extracted_author


db = LibraryDatabase('/home/yangxuan/calibre/books')
count_clean = 0
count_author = 0
errors = []

for bid in list(db.all_ids()):
    mi = db.get_metadata(bid)
    title = mi.title
    author_name = mi.authors[0] if mi.authors else 'Unknown'

    # 检测是否需要清洗书名
    need_clean = (
        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
    )

    # 检测是否需要提取作者(当前作者为 Unknown)
    need_author = (author_name == 'Unknown')

    if need_clean or need_author:
        new_title, extracted = clean_title_and_extract_author(title)

        changed = False
        if new_title and new_title != title:
            mi.title = new_title
            changed = True
            count_clean += 1

        if need_author and extracted:
            mi.authors = [extracted]
            changed = True
            count_author += 1

        if changed:
            try:
                db.set_metadata(bid, mi)
            except Exception as e:
                errors.append((bid, str(e)[:80]))

print(f'书名清洗: {count_clean}')
print(f'作者提取: {count_author}')
print(f'错误: {len(errors)}')

常用操作

查看 Unknown 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;
"

# 统计
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;
"

运行清洗脚本

# 停服务 + 备份
cd /home/yangxuan/calibre
docker compose down
cp books/metadata.db books/metadata.db.backup.$(date +%Y%m%d)
killall calibre 2>/dev/null

# 执行
calibre-debug /tmp/fix_titles_v2.py

# 重启
docker compose up -d

已知问题

set_metadataErrno 36 文件名过长

author_sort 字段(基于作者名生成)超 80 字节时,Calibre 更新路径会触及 ext4 255 字节限制。此时需先清理极长作者名:

sqlite3 /home/yangxuan/calibre/books/metadata.db "
UPDATE authors SET name='Unknown' WHERE LENGTH(name) > 30;
"

然后重新执行脚本。