pdf

Extract text and tables from PDFs using Python libraries.

6|1|Updated Jan 12, 2026

Search Tags:#pdf #python #text-extraction #form-filling #merge-split #pdf-manipulation

Ready to run

npx skills add https://github.com/code-sensei/artemiskit --skill pdf-code-sensei

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/code-sensei/artemiskit/tree/main/.agents/skills/pdf
Command: npx skills add https://github.com/code-sensei/artemiskit --skill pdf-code-sensei

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdf2image, Pillow, and includes scripts (resource) components.

What problem does it solve?

PDF workflows are tedious and error-prone; this skill automates text extraction, table parsing, PDF creation, and form handling to speed up document processing.

Core Features & Use Cases

Extract text and tables from PDFs using Python libraries like pypdf and pdfplumber.
Create, merge, split, and annotate PDFs; fillable and non-fillable forms are handled.
Use cases include digitizing invoices, processing contracts, or archiving scanned documents.

Quick Start

Run a basic extraction example on a PDF to retrieve all text.

Frequently Asked Questions about pdf

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract text and tables from PDF files using Python?▼

Python libraries like pypdf and pdfplumber extract text and tables from PDFs by parsing document structures. This approach automates data extraction from varied PDF formats, converting unstructured documents into actionable text and tabular data.

What's the best way to automate filling PDF forms?▼

Automating PDF form filling is handled by Python scripts that process both fillable and non-fillable forms. By leveraging pypdf, these scripts populate form fields automatically, streamlining contract management and administrative document workflows.

How do I merge, split, and annotate PDF documents programmatically?▼

You can merge, split, and annotate PDF documents programmatically using Python libraries like pypdf. This enables automated PDF manipulation for archiving scanned documents, combining multiple files, or splitting large reports into manageable sections.

Does pypdf work with scanned PDF documents and images?▼

Yes, pypdf works alongside pdf2image and Pillow to process scanned PDF documents. These libraries convert PDF pages into images for further processing, enabling text extraction and annotation across scanned administrative workflows and digitized archives.

Can I create new PDF files from extracted data using Python?▼

Yes, you can create new PDF files from extracted data using Python libraries like reportlab. Combined with pypdf for extraction, this enables end-to-end PDF creation workflows for generating invoices, contracts, and processed administrative documents.

Why does PDF text extraction return garbled or missing characters?▼

PDF text extraction may return garbled characters due to scanned image formats lacking embedded text. Using pdf2image to convert pages and applying OCR preprocessing handles these edge cases, ensuring accurate extraction from varied PDF formats.