skills.rest
Kin3Xc
Kin3XcCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

web-reader

Extract structured content and metadata from web pages.

Updated Jan 15, 2026
Search Tags:#HTML#metadata#web-scraping#URL#title#content-extraction#backend-sdk
One-click install
npx skills add https://github.com/Kin3Xc/promoly --skill web-reader-kin3xc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-reader
Source: https://github.com/Kin3Xc/promoly/tree/main/skills/web-reader
Command: npx skills add https://github.com/Kin3Xc/promoly --skill web-reader-kin3xc

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables automated extraction of content and metadata from web pages, empowering apps to read, summarize, and index online material without manual review.

Core Features & Use Cases

  • Content Extraction: Retrieve the main article HTML and plain text from any URL.
  • Metadata Retrieval: Capture page title, URL, publish time, and description for indexing.
  • Use Case: Build a content processing pipeline that ingests blog posts and news articles for search and analysis.

Quick Start

Initialize the web-reader and fetch content from a URL, then inspect the returned title, HTML, 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 article text and HTML from a URL automatically?▼

To extract article text and HTML from a URL automatically, you can use a web scraping backend SDK. This approach fetches the target web page and retrieves the main content, returning the title, plain text, and original HTML.

Can I retrieve page metadata like publish time and title for web scraping?▼

Yes, you can retrieve page metadata like publish time and title during web scraping. The extraction process captures the URL, page title, publication time, and description, providing structured data for indexing and content processing pipelines.

What is the best way to build a content processing pipeline for news articles?▼

The best way to build a content processing pipeline for news articles is to automate extraction of structured content and metadata. By ingesting URLs, you can retrieve titles, publication times, and article text without manual review.

Does web content extraction work with the z-ai-web-dev-sdk?▼

Yes, web content extraction works directly with the z-ai-web-dev-sdk. This backend dependency handles the page fetching and HTML parsing, returning the extracted text, metadata, and usage tokens for your application.

How do I get publish time and usage tokens when scraping a web page?▼

To get publish time and usage tokens when scraping a web page, execute the extraction process via the backend SDK. The returned output includes the publish_time metadata and the usage tokens consumed during the fetch operation.

What are the limitations of automated web scraping for metadata retrieval?▼

Automated web scraping for metadata retrieval is limited by the target page's structure and access restrictions. If a web page lacks explicit metadata tags or blocks backend fetching, the extraction may return incomplete titles or missing publish times.

Related Skills

Explore More Content & Communication Skills→
eskoNBGeskoNBG
1

web-reader

Retrieve structured web page content and metadata from a URL.

Community
Advanced
PrimeIntellect-aiPrimeIntellect-ai
113

open_webpage

Fetch URLs and extract complete plain text from HTML and PDF documents.

Official
Intermediate
nidhalboumaiza-0nidhalboumaiza-0

web-reader

Fetch web page content and metadata via the page_reader function.

Community
Intermediate
tedtv1007-ctrltedtv1007-ctrl

cloudflare-crawl

Fetch rendered HTML from dynamic websites via the Cloudflare Browser Rendering API.

Community
Intermediate