pdf

Extract text and tables from PDFs using pypdf and pdfplumber.

22|4|Updated May 25, 2026

Search Tags:#ocr #pdf #document-processing #data-extraction #text-extraction #form-filling #image-extraction

Ready to run

npx skills add https://github.com/crazymsn/academic-skills --skill pdf-crazymsn

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/crazymsn/academic-skills/tree/main/academic-skills/pdf
Command: npx skills add https://github.com/crazymsn/academic-skills --skill pdf-crazymsn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, Pillow.

What problem does it solve?

PDFs are ubiquitous in workflows but extracting content, merging documents, filling forms, and enabling searchable archives often requires manual, error-prone steps. This skill automates these tasks to save time and ensure consistency.

Core Features & Use Cases

Text and table extraction from PDFs for data pipelines and reporting.
Merge, split, rotate, watermark, encrypt/decrypt, and create new PDFs.
Fill forms (fillable and non-fillable) and perform OCR on scanned PDFs to enable search and accessibility.

Quick Start

Extract text from a PDF, merge documents, or fill forms.

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 a PDF for data reporting?▼

To extract text and tables from PDF documents, this skill uses pdfplumber to identify structured table layouts and pypdf to pull raw text. It processes both native and scanned files to output clean, editable data for reporting pipelines.

Can I perform OCR on a scanned PDF to make it searchable?▼

Yes, you can perform OCR on scanned PDFs to make them searchable. By leveraging pdf2image and Pillow, the skill converts document pages into images and applies optical character recognition, enabling full text search and accessibility across archival files.

How do I fill out both fillable and non-fillable PDF forms automatically?▼

Filling out both fillable and non-fillable PDF forms is handled by mapping input data to interactive fields using pypdf and overlaying text onto flat documents via Pillow. This automates administrative workflows and ensures consistent form completion.

What is the best way to merge, split, and rotate PDF pages?▼

The best way to merge, split, and rotate PDF pages is by using pypdf within this skill to reorganize document structures. It reliably concatenates multiple files, extracts specific page ranges, and corrects page orientation for archival digitization.

Does this PDF processing skill support adding watermarks and encrypting files?▼

Yes, this PDF processing skill supports applying watermarks and encrypting files. It uses pypdf to overlay image or text watermarks onto pages and applies password-based encryption or decryption to secure sensitive document workflows.

What are the limitations of using pypdf and pdfplumber for PDF data extraction?▼

Limitations of using pypdf and pdfplumber for PDF data extraction include difficulty parsing highly complex, non-standard table layouts and multi-column structures. While robust for standard documents, scanned files require additional OCR processing steps via pdf2image to yield accurate text.