skills.rest
FrankAsanteVanLaarhoven
FrankAsanteVanLaarhovenCOMMUNITY
Explore all skills by this author →
GitHub

web-reader

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

Updated Aug 23, 2026
Search Tags:#backend#sdk#metadata#web-scraping#content-extraction#web-reader#html-parsing
One-click install
npx skills add https://github.com/FrankAsanteVanLaarhoven/navarobotic-learn --skill web-reader-frankasantevanlaarhoven
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-reader
Source: https://github.com/FrankAsanteVanLaarhoven/navarobotic-learn/tree/main/skills/web-reader
Command: npx skills add https://github.com/FrankAsanteVanLaarhoven/navarobotic-learn --skill web-reader-frankasantevanlaarhoven

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Web content extraction and metadata retrieval from web pages becomes reliable, fast, and repeatable, enabling automated processing in backend services.

Core Features & Use Cases

  • Fetch: Retrieve HTML content and the page title from any URL.
  • Extract Metadata: Pull publication time, author, and keywords from the page.
  • Use Case: Build a content-monitoring or summarization service that ingests URLs and stores structured data for analytics.

Quick Start

Install and configure the backend SDK, then call page_reader with a target URL to obtain structured content.

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 multiple URLs in a backend service?▼

Web content extraction is handled by calling the page reader with target URLs to fetch HTML, titles, publish times, and token usage data. It returns structured data suitable for automated backend processing across multiple URLs.

How does HTML parsing work for retrieving article publish time and author information?▼

HTML parsing automatically identifies and pulls metadata fields like publication time, author, and keywords from web pages. The extracted metadata is returned as structured data alongside the page title and raw HTML content.

Can I use the z-ai-web-dev-sdk for automated content archiving without a frontend?▼

Yes, the SDK satisfies backend-only usage for content archiving. You install and configure the backend SDK, then call the page reader function to ingest URLs and store structured page data for analytics.

What's the best way to build a content-monitoring service that ingests URLs and stores structured data?▼

Building a content-monitoring service involves configuring the backend SDK to process URLs sequentially. The page reader retrieves page titles, HTML content, publish times, and token usage metrics, returning structured data ready for storage and analytics.

What structured data fields are returned when extracting web page content?▼

Extracted structured data includes the page title, source URL, raw HTML content, publish time, and token usage metrics. This output enables downstream tasks like article summarization, metadata retrieval, and content archiving.

Does web scraping with this SDK work for article summarization tasks?▼

Web scraping retrieves meaningful content from any web page, making it suitable for article summarization. The extracted content and metadata provide the structured input needed to feed summarization pipelines in backend services.

Related Skills

Explore More Software Engineering Skills→
skkarkiskkarki

LLM

Build LLM-driven chat experiences in Node.js backend services using the z-ai-web-dev-sdk.

Community
Intermediate
patricio0312revpatricio0312rev
5

doc-to-vector-dataset-generator

Convert documents into chunked JSONL datasets for embeddings.

Community
Advanced
skkarkiskkarki

web-reader

Extract web page content and metadata via CLI or SDK.

Community
Advanced
yasinnertenyasinnerten

test-scraper

Test HTML parsing and data extraction logic against diverse HTML structures.

Community
Basic