web-reader

Fetch web pages and extract structured content with TypeScript scripts.

Updated Jan 7, 2026

Search Tags:#content processing #HTML parsing #backend sdk #web-reader #web content extraction #URL fetch

Ready to run

npx skills add https://github.com/ashishkushwaha-mpu/ChocoWrap --skill web-reader-ashishkushwaha-mpu

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: web-reader
Source: https://github.com/ashishkushwaha-mpu/ChocoWrap/tree/main/skills/web-reader
Command: npx skills add https://github.com/ashishkushwaha-mpu/ChocoWrap --skill web-reader-ashishkushwaha-mpu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires z-ai-web-dev-sdk, and includes scripts (resource) components.

What problem does it solve?

This skill enables backend systems to fetch web pages and extract structured content (title, URL, HTML, and metadata) for downstream processing, analytics, and content pipelines.

Core Features & Use Cases

Web page retrieval and content extraction: extract the main article HTML, title, URL, and publish time.
Metadata processing: parse common metadata for SEO, enrichment, and indexing.
Use Case: Build a content aggregator that collects articles from multiple sites for indexing and analysis.

Quick Start

Use the web-reader skill to fetch and process a webpage by invoking the page_reader function from the z-ai-web-dev-sdk on the backend with a URL.

Frequently Asked Questions about web-reader

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

FAQPage Schema

How do I extract structured content and metadata from a fetched web page?▼

Web content extraction parses fetched HTML pages to retrieve structured data including the article title, URL, HTML body, and publish time for downstream indexing and analytics pipelines.

What is the best way to fetch web content for backend article reading workflows?▼

Backend article reading workflows fetch web pages via an SDK to extract main article HTML and metadata, enabling content aggregators to collect and process articles from multiple sites efficiently.

Does the z-ai-web-dev-sdk support retrieving publish time and metadata from diverse sites?▼

Yes, the z-ai-web-dev-sdk supports metadata processing across diverse sites, retrieving common metadata fields like publish time and title for SEO enrichment and content indexing.

Can I use TypeScript scripts to fetch and process web page HTML in a backend environment?▼

Yes, TypeScript scripts can invoke backend SDK functions to fetch web pages and process the extracted HTML, returning structured outputs like URL and title for backend content pipelines.

What are the limitations of web content extraction for HTML processing?▼

Web content extraction relies on backend SDK dependencies and structured HTML output, meaning dynamically rendered content or sites blocking automated URL fetches may limit metadata retrieval success.

When do I need web content extraction for a content aggregator?▼

You need web content extraction when building content aggregators that collect articles from multiple sites, requiring structured retrieval of title, URL, HTML, and publish time for indexing and analysis.