Actionbook Scraper Skill

⚠️ CRITICAL: Two-Part Verification

Every generated script MUST pass BOTH checks:

┌─────────────────────────────────────────────────────┐
│   1. Generate Script                                │
│          ↓                                          │
│   2. Execute Script                                 │
│          ↓                                          │
│   3. Check Part 1: Script runs without errors?      │
│          ↓                                          │
│   4. Check Part 2: Data content is correct?         │
│      - Not empty                                    │
│      - Not placeholder text ("Loading...")          │
│      - Not UI text ("Click to expand")              │
│      - Fields mapped correctly                      │
│          ↓                                          │
│      ┌───┴───┐                                      │
│   BOTH Pass  Either Fails                           │
│      │           │                                  │
│      │           ↓                                  │
│      │       Is it Actionbook data issue?           │
│      │           │                                  │
│      │       ┌───┴───┐                              │
│      │      Yes      No                             │
│      │       │       │                              │
│      │       ↓       ↓                              │
│      │    Log to   Fix script                       │
│      │    .actionbook-issues.log                    │
│      │       │       │                              │
│      │       └───┬───┘                              │
│      │           ↓                                  │
│      │       Retry (max 3x)                         │
│      ↓                                              │
│   Output Script                                     │
└─────────────────────────────────────────────────────┘

Default Output Format

/actionbook-scraper:generate <url>

DEFAULT = agent-browser script (bash commands)

agent-browser open "https://example.com"
agent-browser scroll down 2000
agent-browser get text ".selector"
agent-browser close

With --standalone Flag

/actionbook-scraper:generate <url> --standalone

Output = Playwright JavaScript code

Verification Requirements

Two-Part Verification

Every generated script must pass BOTH checks:

Part 1: Script Execution Check

• No runtime errors
• No timeout errors
• Browser closes properly

Part 2: Data Content Check (CRITICAL)

Verify extracted data matches the expected structure:

Expected: Company name, description, website, year founded
Actual:   "Click to expand", "Loading...", empty strings

→ FAIL: Data content incorrect, need to fix extraction logic

Data validation rules:

For agent-browser Scripts

1. Execute the generated commands
2. Check script runs without errors
3. Check data content is correct:

- Fields match expected structure - Values are actual data, not UI text - Count is reasonable

1. If failed:

- Analyze what's wrong (script error vs data error) - Fix selector, wait logic, or extraction - Re-execute

1. If success:

- Output the verified script - Show data preview with field validation

For Playwright Scripts (--standalone)

1. Write script to temp file
2. Run with node script.js
3. Check script runs without errors
4. Check output data is correct:

- JSON structure matches expected fields - Values contain actual data - Count matches expected range

1. If failed:

- Analyze error type - Fix script - Re-run

1. If success:

- Output the verified script

Architecture Overview

/generate <url>              → OUTPUT: agent-browser bash commands
/generate <url> --standalone → OUTPUT: Playwright .js file

┌─────────────────────────────────────────────────────────────┐
│                   /generate <url>                           │
│                                                             │
│   1. Search Actionbook → get selectors                      │
│   2. Generate OUTPUT:                                       │
│                                                             │
│      WITHOUT --standalone    │    WITH --standalone         │
│      ─────────────────────   │    ──────────────────        │
│      agent-browser commands  │    Playwright .js code       │
│                              │                              │
│      ```bash                 │    ```javascript             │
│      agent-browser open ...  │    const { chromium } = ...  │
│      agent-browser get ...   │    await page.goto(...)      │
│      agent-browser close     │    ```                       │
│      ```                     │                              │
└─────────────────────────────────────────────────────────────┘

Tool Priority

Workflow Rules

CRITICAL: Generate → Verify → Fix

Every generated script MUST be verified by executing it.

Verification Process

For agent-browser scripts:

# Execute each command
agent-browser open "https://example.com"
agent-browser wait --load networkidle
agent-browser get text ".selector"
# Check if data is returned
# If error → fix and retry
agent-browser close

For Playwright scripts (--standalone):

# Write to temp file and execute
node /tmp/scraper.js
# Check if output file has data
# If error → fix and retry

Critical Rules

1. ALWAYS verify generated scripts - Execute and check BOTH parts
2. Part 1: Script must run - No errors, no timeouts
3. Part 2: Data must be correct - Not empty, not UI text, fields mapped correctly
4. Fix errors automatically - Don't output broken scripts or wrong data
5. Use Actionbook MCP tools first - Never guess selectors
6. Include scroll handling for lazy-loaded pages
7. Include expand/collapse logic for card-based layouts
8. Always close browser - Include agent-browser close
9. Retry up to 3 times - If still failing, report the specific issue

Common Data Errors to Catch

Record Actionbook Data Issues

If Actionbook selectors are wrong or outdated, record to local file:

.actionbook-issues.log

When to record:

• Selector doesn't exist on page
• Selector returns wrong element
• Page structure has changed
• Missing selectors for key elements

Log format:

[YYYY-MM-DD HH:MM] URL: {url}
Action ID: {action_id}
Issue Type: {selector_error | outdated | missing}
Details: {description}
Selector: {selector}
Expected: {what it should select}
Actual: {what it actually selects or error}
---

Selector Priority

When Actionbook provides multiple selectors, prefer in this order:

1. data-testid - Most stable, designed for automation
2. aria-label - Accessibility-based, semantic
3. css - Class-based selectors
4. xpath - Last resort, most fragile

Commands

Data Flow

Analyze Command

1. User: /actionbook-scraper:analyze https://example.com/page
2. Extract domain from URL → "example.com"
3. search_actions("example page") → [action_ids]
4. For best match: get_action_by_id(action_id) → full selector data
5. Structure-analyzer agent formats and presents findings

Generate Command (Default: agent-browser script)

User: /actionbook-scraper:generate https://example.com/page

Step 1: Search Actionbook
  search_actions("example.com page") → action_ids

Step 2: Get selectors
  get_action_by_id(best_match) → selectors

Step 3: Generate agent-browser script
  ```bash
  agent-browser open "https://example.com/page"
  agent-browser wait --load networkidle
  agent-browser scroll down 2000
  agent-browser get text ".item-container"
  agent-browser close
  ```

Step 4: VERIFY script (REQUIRED)
  Execute the commands and check if data is extracted
  If failed → analyze error → fix script → retry (max 3x)

Step 5: Return verified script + data preview

Example Output: ````markdown

Verified Scraper (agent-browser)

Status: ✅ Verified (extracted 50 items)

Run these commands to scrape:

agent-browser open "https://example.com/page"
agent-browser wait --load networkidle
agent-browser scroll down 2000
agent-browser get text ".item-container"
agent-browser close

Data Preview

[
  {"name": "Item 1", "description": "..."},
  {"name": "Item 2", "description": "..."},
  // ... showing first 3 items
]

````

Generate Command (--standalone: Playwright script)

User: /actionbook-scraper:generate https://example.com/page --standalone

Step 1: Search Actionbook for selectors
Step 2: Get full selector data
Step 3: Generate Playwright/Puppeteer script
Step 4: VERIFY script (REQUIRED)
  Write to temp file → node /tmp/scraper.js → check output
  If failed → analyze error → fix script → retry (max 3x)
Step 5: Return verified script + data preview

Example Output: ````markdown

Verified Scraper (Playwright)

Status: ✅ Verified (extracted 50 items)

const { chromium } = require('playwright');
// ... generated code with Actionbook selectors

Usage:

npm install playwright
node scraper.js

Data Preview

[
  {"name": "Item 1", "description": "..."},
  // ... first 3 items
]

````

Request Website Command

1. User: /actionbook-scraper:request-website https://newsite.com/page
2. Launch website-requester agent (uses agent-browser)
3. Agent workflow:
   a. agent-browser open "https://actionbook.app/request-website"
   b. agent-browser snapshot -i (discover form selectors)
   c. agent-browser type <url-field> "https://newsite.com/page"
   d. agent-browser type <email-field> (optional)
   e. agent-browser type <usecase-field> (optional)
   f. agent-browser click <submit-button>
   g. agent-browser snapshot -i (verify submission)
   h. agent-browser close
4. Output: Confirmation of submission

Selector Data Structure

Actionbook returns selector data in this format:

{
  "url": "https://example.com/page",
  "title": "Page Title",
  "content": "## Selector Reference\n\n| Element | CSS | XPath | Type |\n..."
}

Common Selector Patterns

Card-based layouts:

Container: .card-list, .grid-container
Card item: .card, .list-item
Card name: .card__title, .card-name
Card description: .card__description
Expand button: .card__expand, button.expand

Detail extraction (dt/dd pattern):

// Common pattern for key-value pairs
const items = container.querySelectorAll('.info-item');
items.forEach(item => {
  const label = item.querySelector('dt').textContent;
  const value = item.querySelector('dd').textContent;
});

Table layouts:

Table: table, .data-table
Header: thead th, .table-header
Row: tbody tr, .table-row
Cell: td, .table-cell

Page Type Detection

Output Formats

Analysis Output

## Page Analysis: {url}

### Matched Action
- **Action ID**: {action_id}
- **Confidence**: HIGH | MEDIUM | LOW

### Available Selectors

| Element | Selector | Type | Methods |
|---------|----------|------|---------|
| {name} | {selector} | {type} | {methods} |

### Page Structure
- **Type**: {static|dynamic|spa}
- **Data Pattern**: {cards|table|list}
- **Lazy Loading**: {yes|no}
- **Expand/Collapse**: {yes|no}

### Recommendations
- Suggested template: {template}
- Special handling needed: {notes}

Generated Code Output

## Generated Scraper

**Target URL**: {url}
**Template**: {template}
**Expected Output**: {description}

### Dependencies

npm install playwright

### Code

{generated_code}

### Usage

node scraper.js

### Output
Results saved to `{output_file}`

Templates Reference

Error Handling

agent-browser Usage

For the request-website command, the plugin uses agent-browser CLI to automate form submission.

agent-browser Commands

# Open a URL
agent-browser open "https://actionbook.app/request-website"

# Get page snapshot (discover selectors)
agent-browser snapshot -i

# Type into form field
agent-browser type "input[name='url']" "https://example.com"

# Click button
agent-browser click "button[type='submit']"

# Close browser (ALWAYS do this)
agent-browser close

Selector Discovery

If form selectors are unknown, use snapshot to discover them:

agent-browser open "https://actionbook.app/request-website"
agent-browser snapshot -i  # Returns page structure with selectors

Always Close Browser

Critical: Always run agent-browser close at the end of any agent-browser session, even if errors occur.

Rate Limiting

• Actionbook MCP: No rate limit for local usage
• Target websites: Respect robots.txt and add delays between requests
• Recommended: 1-2 second delay between page requests

Examples

Example 1: Generate agent-browser Script (Default)

/actionbook-scraper:generate https://firstround.com/companies

Output: agent-browser commands

agent-browser open "https://firstround.com/companies"; agent-browser scroll down 2000 agent-browser get text ".company-list-card-small" agent-browser close

User runs these commands to scrape.

Example 2: Generate Playwright Script

/actionbook-scraper:generate https://firstround.com/companies --standalone

Output: Playwright JavaScript code

const { chromium } = require('playwright'); // ... full script

User runs: `node scraper.js`

Example 3: Analyze Page Structure

/actionbook-scraper:analyze https://example.com/products

Output: Analysis showing:
- Available selectors
- Page structure
- Recommended approach

Example 4: Request New Website

/actionbook-scraper:request-website https://newsite.com/data

Action: Submits form to actionbook.app (this command DOES execute agent-browser)

Best Practices

1. Always analyze before generating - Understand the page structure first
2. Check list-sources - Verify the site is indexed before attempting
3. Review generated code - Verify selectors match expected elements
4. Add appropriate delays - Be respectful to target servers
5. Handle edge cases - Empty states, loading states, errors
6. Test incrementally - Run on small subset before full scrape