---

name: web-scrape description: Intelligent web scraper with content extraction, multiple output formats, and error handling version: 3.0.0

Web Scraping Skill v3.0

Usage

Copy/web-scrape <url> [options]

Options:

• --format=markdown|json|text - Output format (default: markdown)
• --full - Include full page content (skip smart extraction)
• --screenshot - Also save a screenshot
• --scroll - Scroll to load dynamic content (infinite scroll pages)

Examples:

Copy/web-scrape https://example.com/article
/web-scrape https://news.site.com/story --format=json
/web-scrape https://spa-app.com/page --scroll --screenshot

---

Execution Flow

Phase 1: Navigate and Load

Copy1. mcp__playwright__browser_navigate
   url: "<target URL>"

2. mcp__playwright__browser_wait_for
   time: 2  (allow initial render)

If --scroll option: Execute scroll sequence to trigger lazy loading:

Copy3. mcp__playwright__browser_evaluate
   function: "async () => {
     for (let i = 0; i < 3; i++) {
       window.scrollTo(0, document.body.scrollHeight);
       await new Promise(r => setTimeout(r, 1000));
     }
     window.scrollTo(0, 0);
   }"

Phase 2: Capture Content

Copy4. mcp__playwright__browser_snapshot
   → Returns full accessibility tree with all text content

If --screenshot option:

Copy5. mcp__playwright__browser_take_screenshot
   filename: "scraped_<domain>_<timestamp>.png"
   fullPage: true

Phase 3: Close Browser

Copy6. mcp__playwright__browser_close

---

Smart Content Extraction

After getting the snapshot, apply intelligent extraction:

Step 1: Identify Content Type

Step 2: Filter Noise

ALWAYS REMOVE these elements from output:

• Navigation menus and breadcrumbs
• Footer content (copyright, links)
• Sidebars (ads, related articles, social links)
• Cookie banners and popups
• Comments section (unless specifically requested)
• Share buttons and social widgets
• Login/signup prompts

Step 3: Structure the Content

For Articles:

Copy# [Title]

**Source:** [URL]
**Date:** [if available]
**Author:** [if available]

---

[Main content in clean markdown]

For Product Pages:

Copy# [Product Name]

**Price:** [price]
**Availability:** [in stock/out of stock]

## Description
[product description]

## Specifications
| Spec | Value |
|------|-------|
| ... | ... |

---

Output Formats

Markdown (default)

Clean, readable markdown with proper headings, lists, and formatting.

JSON

Copy{
  "url": "https://...",
  "title": "Page Title",
  "type": "article|product|docs|list",
  "content": {
    "main": "...",
    "metadata": {}
  },
  "extracted_at": "ISO timestamp"
}

Text

Plain text with minimal formatting, suitable for further processing.

---

Error Handling

Navigation Errors

Recovery Actions

CopyIf page load fails:
1. Report the specific error to user
2. Suggest: "Try again?" or "Different URL?"
3. Close browser cleanly

If content is blocked:
1. Report what was detected (CAPTCHA/paywall/geo-block)
2. Extract any available preview content
3. Suggest alternatives if applicable

---

Advanced Scenarios

Single Page Applications (SPA)

Copy1. Navigate to URL
2. Wait longer (3-5 seconds) for JS hydration
3. Use browser_wait_for with specific text if known
4. Then snapshot

Infinite Scroll Pages

Copy1. Navigate
2. Execute scroll loop (see Phase 1)
3. Snapshot after scrolling completes

Pages with Click-to-Reveal Content

Copy1. Snapshot first to identify clickable elements
2. Use browser_click on "Read more" / "Show all" buttons
3. Wait briefly
4. Snapshot again for full content

Multi-page Articles

Copy1. Scrape first page
2. Identify "Next" or pagination links
3. Ask user: "Article has X pages. Scrape all?"
4. If yes, iterate through pages and combine

---

Performance Guidelines

---

Security Notes

• Never execute arbitrary JavaScript from the page
• Don't follow redirects to suspicious domains
• Don't submit forms or click login buttons
• Don't scrape pages that require authentication (unless user provides credentials flow)
• Respect robots.txt when mentioned by user

---

Quick Reference

Minimum viable scrape (4 tool calls):

Copy1. browser_navigate → 2. browser_wait_for → 3. browser_snapshot → 4. browser_close

Full-featured scrape (with scroll + screenshot):

Copy1. browser_navigate
2. browser_wait_for
3. browser_evaluate (scroll)
4. browser_snapshot
5. browser_take_screenshot
6. browser_close

Remember: The goal is to deliver clean, useful content to the user, not raw HTML/DOM dumps.