PDF Reader Skill#

Extract and analyze content from PDF files using pdfplumber and PyMuPDF.

Quick Start#

For basic text extraction, use the provided script:

bash

python scripts/extract_pdf.py <path-to-pdf>

Capabilities#

• Text extraction - Extract all text from PDF pages
• Table extraction - Extract tables as structured data
• Metadata - Get PDF metadata (author, pages, etc.)
• Page-specific - Extract from specific pages or ranges
• Search - Find specific text within PDF

Scripts#

ScriptPurposescripts/extract_pdf.pyExtract text from PDFscripts/analyze_pdf.pyAnalyze and summarize PDF content

References#

• references/pdf-libraries.md - Python PDF library documentation

Usage Examples#

Extract all text:

text

python scripts/extract_pdf.py document.pdf

Extract specific page:

text

python scripts/extract_pdf.py document.pdf --page 5

Analyze and summarize:

text

python scripts/analyze_pdf.py document.pdf