web-reader

Extract article content, metadata, and HTML from web pages using z-ai-web-dev-sdk.

Updated Mar 30, 2026
One-click install
npx skills add https://github.com/tmtgroupbot/lptracker-deploy --skill web-reader-tmtgroupbot
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: web-reader
Source: https://github.com/tmtgroupbot/lptracker-deploy/tree/main/skills/web-reader
Command: npx skills add https://github.com/tmtgroupbot/lptracker-deploy --skill web-reader-tmtgroupbot

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Manually copying content from web pages is slow and error-prone, and building custom scrapers requires handling HTML parsing, metadata extraction, and error cases yourself. This Skill provides a ready-made page_reader function that fetches any URL and returns structured data including title, HTML content, plain text, and publication time. ## Core Features & Use Cases - Automatic Content Extraction: Invoke the page_reader function with a URL to retrieve the page title, main HTML content, publication timestamp, and metadata in a single call. - CLI and SDK Modes: Use the z-ai CLI for quick one-off scraping tasks, or integrate the z-ai-web-dev-sdk into backend JavaScript/TypeScript applications for batch processing, caching, and rate limiting. - Use Case: Imagine you are building a news aggregation service. Use this Skill to fetch articles from dozens of source URLs in parallel, extract their titles and text, and compile them into a searchable feed with publication dates. ## Quick Start Ask the AI to extract the article content and title from a specific URL using the web-reader skill.

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 the page title, HTML content, publication time, and metadata as structured JSON without writing custom parsing logic.

How to scrape multiple URLs at once with page_reader?

Loop through your URL array and invoke page_reader for each, or use Promise.allSettled for parallel batch processing with controlled concurrency. Add delays or a rate limiter to avoid overwhelming target servers.

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

No, z-ai-web-dev-sdk must be used in backend code only. Importing it in client-side code will fail and could expose credentials, so always call page_reader from server-side endpoints or scripts.

Why does page_reader return empty or incomplete HTML content?

Pages requiring authentication, behind paywalls, or rendering content via client-side JavaScript may return incomplete data, since the reader extracts static HTML. Verify the URL is publicly accessible and check the response status code.

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

Implement caching with a time-to-live so repeated requests for the same URL return stored results instead of new API calls. Token usage scales with page size, so also extract only the fields you need from responses.