skills.rest
jjyaoao
jjyaoaoCOMMUNITY
Explore all skills by this author →
GitHub

web-reader

Fetch web pages and extract title, HTML, and publication time.

2.7k|627|Updated Sep 11, 2025
Search Tags:#html#sdk#metadata#web#content-extraction#page_reader
One-click install
npx skills add https://github.com/jjyaoao/HelloAgents --skill web-reader-jjyaoao
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-reader
Source: https://github.com/jjyaoao/HelloAgents/tree/main/skills/web-reader
Command: npx skills add https://github.com/jjyaoao/HelloAgents --skill web-reader-jjyaoao

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill provides a robust method to fetch web pages and extract structured content, including the main HTML, title, and publication time, enabling downstream tasks such as summarization, indexing, and monitoring.

Core Features & Use Cases

  • Automatic content extraction: fetches title, HTML, and metadata from any web URL.
  • Metadata enrichment: retrieves publishedTime and URL for archival and analysis.
  • Flexible usage: supports the SDK and CLI for batch processing, monitoring, and integration with web apps.

Quick Start

Call the page_reader function with a URL to fetch the page content and metadata.

Frequently Asked Questions about web-reader

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

FAQPage Schema
How do I extract web content and metadata from a web page URL?▼

To extract web content and metadata from a web page URL, you can use a content extraction function that fetches the site and returns structured data including the title, HTML, and publishedTime for downstream analysis.

What is the best way to build a content monitor for web pages?▼

Building a content monitor involves fetching web pages periodically to extract titles and publication times, enabling you to track site updates and archive changes automatically for research or indexing purposes.

Does the z-ai-web-dev-sdk support retrieving publication times from HTML?▼

Yes, the z-ai-web-dev-sdk supports retrieving publication times from HTML by invoking the page_reader function, which parses the web page to return publishedTime alongside the title, url, and html content.

Can I use extracted web content to build a knowledge base?▼

You can use extracted web content to build a knowledge base by fetching structured data like titles and HTML from various sites, which can then be indexed and summarized for archival and research applications.

How do I fetch a web page and return structured content using an SDK?▼

To fetch a web page and return structured content using an SDK, call the page_reader function with the target URL to receive parsed data including title, html, publishedTime, and usage tokens.

Related Skills

Explore More Data & Analytics Skills→
zakarooozakarooo

web-reader

Extract web page content and metadata via the page_reader function.

Community
Intermediate
shhubbhshhubbh
1

canary

Monitor a live URL for console errors, performance regressions, and page failures after deploy.

Community
Advanced
Sspanwar31Sspanwar31
4

web-reader

Extract web page title, HTML, and publication time as structured data.

Community
Intermediate
zeustritonzeustriton

web-reader

Extract page titles, HTML, and metadata from single or batch URLs.

Community
Intermediate