skills.rest
yutaoshao
yutaoshaoCOMMUNITY
Explore all skills by this author →
GitHub

web-reader

Extract title, HTML, and publication time from web pages.

Updated Dec 26, 2025
Search Tags:#html#metadata#scraping#web#content-extraction
One-click install
npx skills add https://github.com/yutaoshao/agent-skills --skill web-reader-yutaoshao
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-reader
Source: https://github.com/yutaoshao/agent-skills/tree/main/glm-skills/web-reader
Command: npx skills add https://github.com/yutaoshao/agent-skills --skill web-reader-yutaoshao

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Web Reader enables automated extraction of essential web content from any URL, including the page title, main HTML, and publication time, so applications can ingest and process web information without manual scraping.

Core Features & Use Cases

  • Extracts title, HTML, and publish time from web pages for downstream processing.
  • Returns structured data and metadata suitable for dashboards, SEO tools, and research tooling.
  • Ideal for use cases like news aggregation, content monitoring, and academic research workflows.

Quick Start

Ask your AI to run the web reader on a target URL to fetch the title, HTML, and metadata for downstream processing.

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 web pages for my application?▼

Web content extraction automates fetching titles, HTML, and publication times from URLs. This Skill returns structured data and usage metrics suitable for downstream processing in news aggregation, research, or SEO tools.

How do I scrape multiple URLs to fetch the title and publishedTime for content monitoring?▼

You can extract content across multiple URLs by asking your AI to run the web reader on target links. It fetches the title, URL, HTML, and publishedTime, returning a consistent data structure for monitoring workflows.

Does this web scraping tool work with the z-ai-web-dev-sdk in backend code?▼

Yes, the extraction uses the z-ai-web-dev-sdk in backend code. It fetches web page content and returns usage tokens alongside the structured data, making it suitable for application ingestion.

What's the best way to get consistent data structures from web scraping for SEO analysis?▼

Using an automated extraction tool ensures consistent data structures. This Skill fetches the title, HTML, and metadata from web pages, providing a standardized output ideal for SEO analysis and dashboards.

Do I need to manually parse HTML when extracting web content for academic research workflows?▼

No, automated extraction eliminates manual scraping. The Skill ingests web information by fetching the title, main HTML, and publication time directly, returning structured data for research workflows.

Related Skills

Explore More Software Engineering Skills→
zeustritonzeustriton

VLM

Analyze images and generate descriptive responses using the z-ai-web-dev-sdk.

Community
Intermediate
atro2829-hubatro2829-hub

web-reader

Extract structured content and metadata from web pages via URLs.

Community
Advanced
OpenCovenOpenCoven
20

research-ingestion

Extract text from PDFs and web pages and structure insights.

Official
Intermediate
xberg-ioxberg-io
26

automating-the-browser

Automate browser interactions to scrape JavaScript-loaded dynamic web content.

Official
Advanced