Does this skill use LLM tokens for extraction?

No, it uses local Python libraries for pure text extraction, ensuring your processing is fast, private, and does not incur LLM token costs.

Can it handle MOBI files?

Yes, it supports MOBI files by utilizing Calibre's ebook-convert utility to process the format through an integrated conversion step.

How do I install the required dependencies?

You can use the provided setup.sh script within the skill directory or manually install requirements via pip and Calibre for full format support.

Can I export the extracted text directly to a file?

Yes, the script supports an output flag (-o) to save text directly to a file, or you can use standard terminal redirection.

Is OCR supported for scanned PDFs?

No, this skill is designed for programmatic text extraction from digital files; image-based or scanned PDFs require external OCR tools.

Ebook Text Extractor

Name: Ebook Text Extractor
Author: ratacat

byratacat

웹 스크래핑 및 데이터 수집

Extracts clean, plain text from EPUB, MOBI, and PDF files for analysis and data processing.

소개

Ebook Text Extractor provides a set of high-performance local Python scripts designed to convert common ebook formats into structured plain text without requiring LLM calls. This skill is ideal for developers and researchers who need to preprocess large volumes of text from digital books for RAG (Retrieval-Augmented Generation) pipelines, data analysis, or minimalist reading. By utilizing specialized libraries like ebooklib and PyMuPDF, it ensures fast, accurate extraction while preserving document structure and eliminating API costs.

주요 기능

Unified extraction command with auto-format detection
High-performance extraction using PyMuPDF and ebooklib
Support for EPUB, MOBI, and PDF formats
Pure local processing with no external API or LLM token costs
Flexible output options for stdout or direct file export
0 GitHub stars

사용 사례

Converting digital libraries into searchable plain text archives
Preprocessing ebooks for RAG and AI model training
Extracting book content for NLP projects and sentiment analysis

소개

주요 기능

Unified extraction command with auto-format detection
High-performance extraction using PyMuPDF and ebooklib
Support for EPUB, MOBI, and PDF formats
Pure local processing with no external API or LLM token costs
Flexible output options for stdout or direct file export
0 GitHub stars

사용 사례

Converting digital libraries into searchable plain text archives
Preprocessing ebooks for RAG and AI model training
Extracting book content for NLP projects and sentiment analysis