pdf

Extract text, tables, and form data from PDFs using Python.

Updated Dec 9, 2025
One-click install
npx skills add https://github.com/h4v1d/extension-collection-geminicli --skill pdf-h4v1d
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/h4v1d/extension-collection-geminicli/tree/main/pdf
Command: npx skills add https://github.com/h4v1d/extension-collection-geminicli --skill pdf-h4v1d

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Many workflows deal with static PDF documents that are difficult to search, analyze, or reuse. This Skill provides a comprehensive toolkit to automate PDF text and data extraction, generate new PDFs, merge/split documents, and manage forms, reducing manual effort and errors.

Core Features & Use Cases

  • Text and table extraction from PDFs into plain text, CSV, or Excel formats.
  • Create, merge, and split PDFs, and manage multi-page workflows.
  • Fillable and non-fillable form handling, including guided field annotation workflows.

Use Case: Imagine processing a batch of 100 vendor invoices in PDF; this Skill can extract key fields, compile a summary, and generate a consolidated report.

Quick Start

Run a simple example to count pages in a document: python -c 'from pypdf import PdfReader; r = PdfReader("document.pdf"); print(len(r.pages))'

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 into CSV or Excel formats?

PDF text and table extraction into plain text, CSV, or Excel formats is achieved by automating document processing with Python libraries like pypdf. This handles static documents across batch workflows, converting unstructured PDF data into editable formats for downstream analysis and reporting.

Can I automate batch form processing for hundreds of PDF documents?

Batch form processing across many PDFs is fully supported, handling both fillable and non-fillable forms. You can automate field extraction, data compilation, and generate consolidated reports for large document sets like vendor invoices without manual data entry.

Do I need Python and specific packages to parse and render PDFs?

Python is required along with packages such as pypdf, pdf2image, and Pillow to parse, render, and annotate PDFs. These dependencies provide the core functionality to extract text, manage forms, and handle multi-page document workflows.

What is the best way to merge, split, and manage multi-page PDF workflows?

Merging, splitting, and managing multi-page PDF workflows is done using Python automation scripts. This approach handles document generation and multi-page workflows, reducing manual effort and errors when organizing archival documents or processing batch forms.

How does guided field annotation work for non-fillable PDF forms?

Guided field annotation for non-fillable PDF forms uses rendering libraries like pdf2image and Pillow to visually overlay and extract form data. This enables structured data capture from static documents where traditional fillable form fields are absent.

Why does PDF table extraction result in misaligned data columns?

PDF table extraction can yield misaligned data columns when static document structures lack clear boundaries or contain complex layouts. Using Python parsers like pypdf helps render and identify structural elements, improving accuracy for documents with consistent formatting.