Extract text, tables, and metadata from PDFs using Python libraries.
npx skills add https://github.com/ashleytower/claude-skills-collection --skill pdf
Please help me install this Agent Skill. Skill: pdf Source: https://github.com/ashleytower/claude-skills-collection/tree/main/skills/pdf-processor Command: npx skills add https://github.com/ashleytower/claude-skills-collection --skill pdf
Working with PDFs often involves manual, repetitive tasks like data extraction, merging, splitting, or filling forms. This skill provides a comprehensive toolkit to automate all these operations, transforming static documents into dynamic, actionable data and saving countless hours.
from pypdf import PdfReader reader = PdfReader("document.pdf") text = "" for page in reader.pages: text += page.extract_text() print(f"Pages: {len(reader.pages)}")
High-intent search queries and answers about installing and using this skill.
Extract text and tables from PDFs using pdfplumber for structured data or pypdf for standard documents. Both libraries parse page content into readable strings or table objects, supporting scanned PDFs through OCR when pytesseract is configured with image preprocessing via pdf2image.
Yes, automate form filling by reading PDF structure with pypdf, identifying form fields, and writing values directly to the document. ReportLab enables creating new PDFs with pre-filled content, and batch scripts process multiple forms end-to-end without manual intervention.
Merge PDFs by combining page objects from pypdf readers; split by extracting specific page ranges; rotate using page rotation methods. These operations work on standard and password-protected documents, enabling batch workflows that reorganize multi-document sets before distribution or archiving.
Extract data from scanned PDFs by converting pages to images with pdf2image, running OCR via pytesseract, and parsing recognized text into structured format. This workflow handles low-quality or image-only documents that standard text extraction cannot process.
Add watermarks using ReportLab overlays or pypdf page manipulation; apply password protection through pypdf encryption methods. Both operations work in batch workflows, allowing you to secure and brand documents at scale before sharing or archiving.
Python libraries like pypdf and pdfplumber handle most tasks natively, but advanced features require CLI tools: poppler-utils provides pdftotext and image conversion; qpdf and pdftk offer command-line splitting and encryption when integrated into scripted pipelines.
jdrodriguezExtract text from scanned PDFs and images using OCR.
malue-aiAnalyze and process Excel/CSV files with pandas and openpyxl.
VYRE-StudiosExtract text and tables from PDF documents using PyPDF2 and pdfplumber.
jholhewresExtract text from images and PDF documents using OCR engines.
