Book Catalog Search Tool
Paste the following prompt into your AI chat to install this skill:
Follow https://skillhub.cn/install/skillhub.md to install @user_5ee3d2f0/book-retrieval-v1.
About this skill
Problem Solved
When book catalogs reach tens of millions of records, searching by title, author, publisher, ISBN, or year can easily degrade into a full table scan. Ordinary scripts often struggle to cover single-condition lookup, boolean combinations, Excel batch import, and keyword filtering at once. This skill consolidates those needs into a local Python retrieval tool for offline processing of Chinese and English bibliographic data.
How It Works
The tool loads CSV files with pandas and caches column data in numpy. Its core capabilities include:
- Single-condition search: matches fields such as
title,author,publisher,isbn, andyear. - Advanced search: supports
AND/ORcombinations and expression input likeT=math AND P=Higher Education OR A=Zhang San. - Batch search: queries Excel rows one by one, using the ISBN hash index when available and falling back to text scanning otherwise.
- Keyword filtering: filters the full catalog by title and exports Excel results.
The ISBN hash index keeps lookup close to O(1), reducing full-table scans during batch retrieval. A tkinter GUI exposes manual, advanced, batch, keyword, and path settings.
Boundaries
Loading the full dataset into memory can require around 8GB for tens of millions of rows, so 16GB or more is recommended. ISBN is treated as a unique identifier, and the fast path does not re-validate title or author. CSV files should be read with dtype=str, and expression mode must follow the field=value logic field=value format.
Use Cases
- A librarian needs to screen a very large Chinese and English bibliographic catalog by title, author, publisher, ISBN, and publication year to shortlist candidate books for acquisition or reference.
- A procurement analyst receives an Excel book list with title, ISBN13, author, and publisher columns, then batch-queries rows, uses the ISBN hash path, and exports matched and missing records.
- A publishing editor builds an expression combining title, publisher, author, and year, then uses advanced search to extract records that satisfy both inclusion and exclusion conditions for a special report.
- A researcher working with a large local Chinese catalog enters comma-separated keywords, filters the title field across millions of rows, and outputs matched books with keyword labels into Excel.
Best For
- Librarians managing multi-million-row bibliographic datasets who need fast manual lookups by title, ISBN, author, publisher, or year.
- Collection development librarians who import purchase lists, batch-check ISBNs, and need exports of matched and missing catalog records.
- Publishing editors or data analysts who combine title, publisher, author, and year conditions to screen catalogs for reports or selection lists.
- Python users who want a local tkinter GUI and CLI scripts for searching CSV or Excel book catalogs.
Related Skills
Search Huawei Cloud official docs and product pages to find ECS, OBS, RDS, CCE product specs, parameters, documentation, and API references without login.
OCR-based recognition for movie, train, flight, and event tickets in images or PDFs, extracting key fields into Markdown or JSON reports.
Turns notes, research, and meeting summaries into actionable next moves, plans, decisions, experiments, and decision-changing gaps.
A local wiki knowledge base manager that compiles raw documents into sourced, indexed Markdown pages with wikilinks, query support, and health checks.