ebook-extractor

Use when user wants to extract text from ebooks (EPUB, MOBI, PDF). Use for converting ebooks to plain text for analysis, processing, or reading. Handles all common ebook formats.

$ Installieren

git clone https://github.com/ratacat/claude-skills /tmp/claude-skills && cp -r /tmp/claude-skills/skills/ebook-extractor ~/.claude/skills/claude-skills

// tip: Run this command in your terminal to install the skill


name: ebook-extractor description: Use when user wants to extract text from ebooks (EPUB, MOBI, PDF). Use for converting ebooks to plain text for analysis, processing, or reading. Handles all common ebook formats.

Ebook Text Extractor

Overview

Extract plain text from EPUB, MOBI, and PDF files using Python scripts. No LLM calls - pure text extraction.

Supported Formats

FormatTool UsedNotes
EPUBebooklib + BeautifulSoupDirect parsing, preserves structure
MOBICalibre ebook-convertConverts to EPUB first, then extracts
PDFPyMuPDF (fitz)Fast, handles most PDFs well

Usage

Unified extractor (auto-detects format):

python3 ~/.claude/skills/ebook-extractor/scripts/extract.py /path/to/book.epub
python3 ~/.claude/skills/ebook-extractor/scripts/extract.py /path/to/book.mobi
python3 ~/.claude/skills/ebook-extractor/scripts/extract.py /path/to/book.pdf

Output options:

# To stdout (default)
python3 scripts/extract.py book.epub

# To file
python3 scripts/extract.py book.epub -o output.txt
python3 scripts/extract.py book.epub > output.txt

Format-specific scripts:

python3 scripts/extract_epub.py book.epub
python3 scripts/extract_mobi.py book.mobi
python3 scripts/extract_pdf.py book.pdf

Setup

# One-command setup (installs all dependencies)
~/.claude/skills/ebook-extractor/setup.sh

# Or manually:
pip install -r ~/.claude/skills/ebook-extractor/requirements.txt
brew install calibre  # macOS, for MOBI support

Script Location

~/.claude/skills/ebook-extractor/scripts/

Common Issues

ProblemSolution
Missing packageRun setup.sh or pip install -r requirements.txt
MOBI failsEnsure Calibre is installed: brew install calibre
PDF garbledSome PDFs are image-based; OCR needed (not supported)