skills.rest
grahama1970
grahama1970COMMUNITY
Explore all skills by this author →
WebsiteGitHub

fetcher

Fetch web pages and PDFs with content extraction and structured exports.

1|Updated Nov 12, 2025
Search Tags:#automation#pdf#cli#fetch#web#data-extraction
One-click install
npx skills add https://github.com/grahama1970/fetcher --skill fetcher
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: fetcher
Source: https://github.com/grahama1970/fetcher/tree/main/.agents/skills/fetcher
Command: npx skills add https://github.com/grahama1970/fetcher --skill fetcher

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Web content retrieval and document extraction are error-prone and time consuming; this Skill automates fetching pages, PDFs, and gated content, then extracts usable text and metadata to accelerate research and data pipelines.

Core Features & Use Cases

  • Automate web content retrieval: fetch single URLs or batches with deterministic fallbacks and content extraction.
  • Handle PDFs and HTML: extract text, metadata, and provide structured outputs suitable for downstream processing.
  • Real-world use: when you need to pull data from a website or a set of documents for indexing, analysis, or archival tasks, run the tool to obtain ready-to-use results.

Quick Start

Fetch this URL now and I will retrieve the content and present the results.

Frequently Asked Questions about fetcher

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

FAQPage Schema
How do I automate web page and PDF extraction from a list of URLs?▼

Automating web page and PDF extraction is handled by fetching single URLs or batches with built-in content retrieval. The tool pulls text and metadata from HTML and PDFs, providing structured outputs ready for downstream data pipelines.

What is the best way to fetch gated web content for data pipelines?▼

Fetching gated web content for data pipelines is managed through automated retrieval with deterministic fallbacks. It handles diverse environments to extract usable text and metadata, accelerating research without requiring manual pre-installation steps.

Do I need to install any dependencies to fetch PDFs and HTML pages in diverse environments?▼

No pre-installation is required to fetch PDFs and HTML pages. The Skill operates across diverse environments without dependencies, automatically retrieving documents and exporting structured results suitable for indexing and analysis.

How does web content retrieval work when a primary URL fetch fails?▼

Web content retrieval uses deterministic fallbacks like Brave and Wayback when a primary URL fetch fails. This ensures automated data extraction continues smoothly, returning structured text and metadata from web pages or PDFs.

Can I extract metadata from multiple PDFs in a single batch process?▼

Extracting metadata from multiple PDFs in a single batch process is fully supported. You can fetch batches of URLs to automatically retrieve document content, extracting text and metadata into structured outputs for archival tasks.

Why use automated data extraction instead of manual web scraping for research?▼

Automated data extraction replaces manual web scraping to eliminate error-prone and time-consuming retrieval. It accelerates research by automatically fetching pages, PDFs, and gated content while extracting usable text and metadata into structured exports.

Related Skills

Explore More Data & Analytics Skills→
olostepolostep

batch

Scrape up to 10,000 URLs in parallel with configurable output formats.

Community
Intermediate
ygfuyfffdf-maxygfuyfffdf-max

pdf

Extract text, tables, and metadata from PDFs using Python scripts.

Community
Advanced
PthahnixPthahnix
393

Web Searching

Perform Brave searches, fetch pages, and convert them to markdown.

Community
Intermediate
nimadorostkarnimadorostkar
25

document-conversion

Convert HTML documents into structured Markdown or PDF files.

Community
Intermediate