web-reader

Extract structured content and metadata from web pages via backend page_reader.

Updated Dec 23, 2025

Search Tags:#backend #HTML #SDK #web-scraping #content-extraction #web-reader

Ready to run

npx skills add https://github.com/mattismyname3011/school-council-election --skill web-reader-mattismyname3011

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: web-reader
Source: https://github.com/mattismyname3011/school-council-election/tree/main/skills/web-reader
Command: npx skills add https://github.com/mattismyname3011/school-council-election --skill web-reader-mattismyname3011

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Web pages often require structured extraction of title, content, and metadata for apps like content aggregators, search engines, and knowledge bases. This skill provides a backend tool to fetch a page and return well-structured data for downstream processing.

Core Features & Use Cases

Web-page reading and content extraction via the z-ai-web-dev-sdk
Metadata retrieval: title, URL, publish time, and description
Use Case: Build a content aggregator that collects summaries and links from multiple sources daily.

Quick Start

Use the web-reader to fetch a page by URL and inspect the structured result.

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?▼

You can extract structured content from web pages by using a backend tool that fetches HTML and parses out the title, URL, publishedTime, and text. This returns a clean data object ready for downstream processing.

What is the best way to process batch URLs for content extraction in SEO workflows?▼

Batch URL processing for content extraction is handled by applying a backend web reader across multiple URLs. It retrieves metadata and text from each page simultaneously, enabling ongoing content monitoring across multiple sites.

Can I use the z-ai-web-dev-sdk to fetch HTML and build a content aggregator?▼

Yes, you can use the z-ai-web-dev-sdk to fetch HTML and build a content aggregator. The SDK implements a backend page reader that retrieves page summaries, links, and metadata for daily collection workflows.

Does web scraping with a backend reader return token usage data?▼

Web scraping with this backend reader does return token usage data alongside the extracted content. The structured response includes the title, URL, publish time, and a token usage report for tracking API consumption.

What data fields are included when extracting published content from HTML?▼

When extracting published content from HTML, the returned data object includes the page title, source URL, publishedTime, and the main text content. These fields provide structured metadata for knowledge management.