fetch-text

Fetch and extract text from URLs, base64 PDFs, and Note or Collection IDs.

10|Updated Jul 22, 2025
One-click install
npx skills add https://github.com/bdambrosio/Cognitive_workbench --skill fetch-text
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: fetch-text
Source: https://github.com/bdambrosio/Cognitive_workbench/tree/main/src/tools/fetch-text
Command: npx skills add https://github.com/bdambrosio/Cognitive_workbench --skill fetch-text

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf, unstructured, playwright, python-docx, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of extracting complete text content from various sources like web pages, PDFs, and even base64 encoded documents, saving users from manual copy-pasting or complex parsing.

Core Features & Use Cases

  • Universal Text Extraction: Fetches text from URLs (HTML, MD, TXT) and base64 encoded PDFs.
  • Format Auto-Detection: Intelligently identifies the document format for accurate parsing.
  • Collection/Note Awareness: Can process the first item from a Collection or retrieve content directly from a Note ID.
  • Use Case: Quickly get the full content of an online article or a research paper PDF without needing to manually save and open files.

Quick Start

Use the fetch-text skill to get all the text from the URL https://example.com/document.pdf.

Frequently Asked Questions about fetch-text

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

FAQPage Schema
How do I extract text from a PDF and web URL automatically?

Text extraction from a PDF or web URL is automated by fetching the specified target, auto-detecting the document format, and parsing the content to return complete raw text alongside metadata.

Can I parse base64 encoded PDFs without manually saving files?

Base64 encoded PDFs can be parsed directly without manual saving by passing the encoded string as the target, allowing the system to decode and extract text content on the fly.

Does web scraping with this approach work on JavaScript-rendered HTML pages?

Web scraping for HTML pages is supported, and the implementation includes Playwright as a dependency to handle dynamic, JavaScript-rendered content during the text extraction process.

What is the best way to extract text from internal Notes or Collections?

The best way to extract text from internal Notes or Collections is to provide the Note or Collection ID as the target, which fetches the content directly or processes the first item.

What formats are supported for automatic text extraction and data ingestion?

Supported formats for automatic text extraction include PDF, HTML, Markdown, and plain text, with the system intelligently identifying the document type to ensure accurate parsing for data ingestion.

When should I not use this approach for content retrieval?

You should not use this content retrieval approach if you require structural layout preservation or image extraction, as it is designed specifically to extract complete raw text and metadata.