skills.rest
Sspanwar31
Sspanwar31COMMUNITY
Explore all skills by this author →
GitHub

web-reader

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

4|1|Updated Dec 19, 2025
Search Tags:#typescript#metadata#web#web-scraping#content-extraction#backend-sdk
One-click install
npx skills add https://github.com/Sspanwar31/saanify-workspace-new- --skill web-reader-sspanwar31
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-reader
Source: https://github.com/Sspanwar31/saanify-workspace-new-/tree/main/skills/web-reader
Command: npx skills add https://github.com/Sspanwar31/saanify-workspace-new- --skill web-reader-sspanwar31

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Web content extraction for automation, enabling reliable retrieval of titles, bodies, and metadata from any web page.

Core Features & Use Cases

  • Backend page reads: fetch title, url, html, and publish time from any web page.
  • Batch processing: process multiple URLs within a single workflow and aggregate results.
  • Metadata extraction: derive author, description, and keywords from meta tags to support SEO and content analysis.

Quick Start

Use the page_reader function with a URL to fetch and return structured web 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 page content and metadata from a URL in a backend workflow?▼

To extract web page content and metadata from a URL, you can use a backend SDK to fetch title, HTML, and publication time. This enables reliable retrieval of structured data for automation without frontend rendering.

What is the best way to automate batch processing of multiple URLs for content extraction?▼

The best way to automate batch processing of multiple URLs is to use a backend web scraping script that processes each link and aggregates the results. This workflow returns structured data including titles and publish times for each page.

Can I use this web scraping approach to derive SEO keywords and author metadata?▼

Yes, you can use web scraping to derive SEO keywords and author metadata. The extraction process reads standard meta tags from the HTML, returning description and keywords directly to support content analysis.

Does web content extraction work with arbitrary URLs for backend-only operations?▼

Web content extraction works with arbitrary URLs for backend-only operations by fetching the page directly. It reliably retrieves the title, url, html, and publishedTime, returning structured data without requiring a browser environment.

What structured data format should I expect from web page metadata extraction?▼

From web page metadata extraction, you should expect structured data containing the title, url, html, publishedTime, and token usage. This format supports direct integration into downstream automation workflows.

Related Skills

Explore More Software Engineering Skills→
MO196931MO196931

web-reader

Extract title, HTML, plain text, and timestamps from public URLs.

Community
Intermediate
ComwrapUkReplyComwrapUkReply

scrape-webpage

Scrape webpages to extract content, metadata, and images for migration workflows.

Community
Advanced
Exia-thdExia-thd

performance-engineer

Profile web applications and generate k6/Artillery load testing scripts.

Community
Advanced
lvhuanidlvhuanid

web-reader

Extract text, HTML, and metadata from web pages using z-ai-web-dev-sdk.

Community
Intermediate