pdf

Extract text and structured data from PDF documents using pypdf and pdfplumber.

3|Updated Feb 16, 2026

Search Tags:#ocr #pdf #pdfplumber #pypdf #text-extraction #form-filling #pdf-processing

Ready to run

npx skills add https://github.com/Zhangyinglun/resume-tailor-skill --skill pdf-zhangyinglun

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/Zhangyinglun/resume-tailor-skill/tree/main/vendor/skills/pdf
Command: npx skills add https://github.com/Zhangyinglun/resume-tailor-skill --skill pdf-zhangyinglun

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

It removes manual PDF handling by providing reliable extraction, form filling, conversion, and basic OCR so users can automate document workflows and avoid repetitive editing.

Core Features & Use Cases

Text & Table Extraction: Extract plain text and structured tables from PDFs for downstream analysis.
Form Filling: Fill native PDF form fields or add precise text annotations to non-fillable forms with coordinate mapping and validation.
PDF Manipulation & OCR: Merge, split, rotate, watermark, protect, render pages to images, and OCR scanned pages to searchable text.
Use Case: Batch-process invoices or onboarding forms to produce a merged searchable PDF and a CSV of extracted fields.

Quick Start

Ask the agent to extract text and tables from document.pdf, fill any form fields, and return a searchable PDF plus a CSV of extracted data.

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 structured tables from PDF documents for automated analysis?▼

Extract text and structured tables from PDFs using pdfplumber to pull plain text and tabular data for downstream analysis. It reliably parses reports and invoices, returning structured outputs ready for automated processing workflows.

Does pypdf support filling native PDF form fields and adding text annotations to non-fillable forms?▼

Yes, pypdf supports filling native PDF form fields, while coordinate mapping and validation allow precise text annotations on non-fillable forms. This combination enables automated form completion across various document types without manual editing.

What is the best way to apply OCR to scanned PDF pages and convert them to searchable text?▼

Apply OCR to scanned PDF pages by rendering them to images with pdf2image and Pillow, then processing them to extract searchable text. This approach transforms image-based documents into searchable text for automated data retrieval.

Can I merge, split, and watermark PDF files within a single automated workflow?▼

Yes, you can merge, split, rotate, and watermark PDF files within a single workflow using pypdf. It handles document manipulation tasks alongside rendering pages to images, allowing batch processing of invoices and reports.

How do I batch process invoices and onboarding forms to produce a searchable PDF and a CSV of extracted data?▼

Batch process invoices and onboarding forms by extracting text and structured data using pdfplumber, filling form fields with pypdf, and applying OCR. This yields a merged searchable PDF and a CSV of extracted fields.

What are the limitations of using pdfplumber for text extraction across complex PDF layouts?▼

While pdfplumber extracts plain text and structured tables effectively, complex PDF layouts with irregular formatting may yield misaligned data. For scanned pages, applying OCR via pdf2image and Pillow is necessary to retrieve searchable text.