web-reader

Extract structured content and metadata from web pages via page_reader.

Updated Apr 28, 2026

Search Tags:#html #sdk #metadata #scraping #web #content-extraction

Ready to run

npx skills add https://github.com/ncsound919/deterministic-brain --skill web-reader-ncsound919

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: web-reader
Source: https://github.com/ncsound919/deterministic-brain/tree/main/skills/web-reader
Command: npx skills add https://github.com/ncsound919/deterministic-brain --skill web-reader-ncsound919

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Implements reliable extraction of article content and page metadata from web pages using the z-ai-web-dev-sdk, enabling automated ingestion of titles, HTML, and publication times for downstream processing.

Core Features & Use Cases

Automatic content extraction: fetches title, HTML, and publish time from web pages for quick ingestion.
Metadata retrieval and enrichment: gathers descriptions and authors to enhance search and analytics.
Backend workflow integration: supports building scraping pipelines, content analyzers, and archives in server-side apps.

Quick Start

Run a page_reader task to fetch and extract article content from a given URL.

Frequently Asked Questions about web-reader

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

FAQPage Schema

How do I extract article content and metadata from web pages automatically?▼

Web page content extraction automates the retrieval of titles, HTML, and publish times from URLs. It enables reliable scraping pipelines and metadata enrichment for downstream content analysis across multiple sites.

What is the best way to scrape multiple sites for metadata enrichment?▼

The best way to scrape multiple sites for metadata enrichment involves running a server-side page reader function that returns structured data. You can gather descriptions and authors to enhance search indexing and analytics across various web pages.

Can I use the z-ai-web-dev-sdk to fetch publish time and HTML from a URL?▼

Yes, you can use the z-ai-web-dev-sdk to fetch publish time and HTML from a URL. By invoking the page_reader function in your backend code, you retrieve the title, URL, HTML, publishedTime, and usage tokens for reliable content ingestion.

Does web scraping for content analysis require backend code?▼

Web scraping for content analysis does require backend code to invoke the page_reader function and process the returned HTML and metadata. This server-side execution ensures deterministic extraction of titles and publication times for your archives.

What metadata fields are returned when extracting web page content?▼

When extracting web page content, the returned metadata fields include the title, URL, HTML, publishedTime, and usage tokens. These structured outputs support automated ingestion, metadata enrichment, and content analysis workflows.