# Web Content Scraper > Scrape and extract main content from webpages, including images with source attribution. Use when a user asks to scrape, fetch, extract, or grab content from a website URL. Extracts the primary article or page content while filtering out ads, headers, footers, navigation, sidebars, and site maps. Downloads relevant images and preserves their source URLs for copyright compliance. Preserves all important details and formatting from the main content. Use when this capability is needed. - Skill: `tomevault-io/web-content-scraper` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/web-content-scraper` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/web-content-scraper/raw - Safety review: pending (external: skill-scanner PASS, skillspector PASS) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Coding & Dev Tools - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/web-content-scraper --- # Web Content Scraper Skill Extract meaningful content from webpages, filtering out noise like ads, navigation, and boilerplate. ## Overview This skill fetches webpage content and extracts only the main article or informational content. It automatically filters out: - Advertisements and promotional content - Headers and footers - Navigation menus and sidebars - Site maps and link directories - Cookie notices and popups - Social media widgets ## When to Use Use this skill when a user: - Asks to "scrape" a website - Wants to "grab content" from a URL - Needs to "extract information" from a webpage - Asks to "fetch" or "get" the content of a website - Wants to copy text from a webpage ## Instructions ### Step 1: Validate the URL Before scraping, verify the URL is valid and accessible. Ensure it starts with `http://` or `https://`. ### Step 2: Fetch the Webpage Use the `fetch_webpage` tool to retrieve the page content. Set the query to focus on extracting the main article or informational content. ### Step 3: Extract Main Content Parse the content and filter out noise. The goal is to capture ALL the meaningful information while excluding structural/promotional elements. **Always Remove:** - Scripts and style blocks - Elements with classes containing: ad, ads, advertisement, banner, promo, sponsor - Navigation elements: `