web-reader

Extract article content, metadata, and publication time from web pages.

Updated Jul 11, 2026
One-click install
npx skills add https://github.com/mukaddam-ali/Anadolu-Kitchen --skill web-reader-mukaddam-ali
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: web-reader
Source: https://github.com/mukaddam-ali/Anadolu-Kitchen/tree/main/skills/web-reader
Command: npx skills add https://github.com/mukaddam-ali/Anadolu-Kitchen --skill web-reader-mukaddam-ali

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Manually scraping web pages and parsing raw HTML into usable content is tedious and error-prone. This Skill provides a structured way to fetch any web URL and receive clean, structured data including the page title, main HTML content, plain text, and publication timestamp. ## Core Features & Use Cases - Automatic Content Extraction: Invoke the page_reader function with a URL to retrieve the title, HTML content, and publication time without writing custom parsers. - CLI and SDK Access: Use the z-ai CLI for quick one-off scraping tasks, or integrate the z-ai-web-dev-sdk into backend applications for batch processing, caching, and rate-limited pipelines. - Use Case: Imagine you are building a news aggregation service. Use this Skill to fetch articles from multiple source URLs, extract their titles and content, and compile them into a searchable feed sorted by publication date. ## Quick Start Use the web-reader skill to extract the article content and title from https://example.com/article and save the result as JSON.

Frequently Asked Questions about web-reader

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

FAQPage Schema
How do I extract content from a web page in JavaScript?

Use the z-ai-web-dev-sdk page_reader function by calling zai.functions.invoke with the target URL. It returns structured data including the page title, HTML content, and publication time without requiring custom HTML parsing.

How to scrape multiple URLs at once with page_reader?

Process multiple URLs by looping through them with Promise.allSettled for parallel fetching, or iterate sequentially with delays. The Skill includes examples for batch processing with concurrency limits and per-URL error handling.

Can I use z-ai-web-dev-sdk in client-side browser code?

No, the z-ai-web-dev-sdk must be used in backend code only. Importing it in client-side code will fail and could expose credentials. Use it in server-side routes, API endpoints, or backend scripts.

Why does page_reader return empty or incomplete HTML content?

Pages with JavaScript-rendered dynamic content, authentication walls, or anti-scraping measures may return incomplete data. The reader extracts static HTML content, so verify the URL is publicly accessible without login.

How do I reduce token usage when reading many web pages?

Implement caching to avoid refetching unchanged pages, since token usage scales with page size. The Skill provides a CachedWebReader pattern with configurable cache duration and force-refresh options.