# web-automation

Automated web browsing and scraping using Playwright with Camoufox anti-detection browser.

## What this skill is for

- Automating web workflows
- Authenticated session flows (logins/cookies)
- Extracting page content to markdown
- Working with bot-protected or dynamic pages

## Routing rule

- For one-shot page extraction from a single URL, prefer `playwright-safe`
- Use `web-automation` only when the task needs interactive browser control, multi-step navigation, or authenticated flows

## Requirements

- Node.js 20+
- `pnpm`
- Network access to download browser binaries

## First-time setup

```bash
cd ~/.openclaw/workspace/skills/web-automation/scripts
pnpm install
npx camoufox-js fetch
pnpm approve-builds
pnpm rebuild better-sqlite3 esbuild
```

## System libraries (for OpenClaw Docker builds)

```bash
export OPENCLAW_DOCKER_APT_PACKAGES="ffmpeg jq curl libnss3 libatk1.0-0 libatk-bridge2.0-0 libcups2 libdrm2 libxkbcommon0 libxcomposite1 libxdamage1 libxfixes3 libxrandr2 libgbm1 libasound2"
```

## Native module note

If `pnpm install` warns that build scripts were ignored for native modules such as `better-sqlite3` or `esbuild`, run:

```bash
pnpm approve-builds
pnpm rebuild better-sqlite3 esbuild
```

Without this, `browse.ts` and `scrape.ts` may fail before launch because the native bindings are missing.

## Common commands

```bash
# Browse a page
npx tsx browse.ts --url "https://example.com"

# Scrape markdown
npx tsx scrape.ts --url "https://example.com" --mode main --output page.md

# Authenticate flow
npx tsx auth.ts --url "https://example.com/login"

# General natural-language browser flow
npx tsx flow.ts --instruction 'go to https://search.fiorinis.com then type "pippo" then press enter then wait 2s'
```

## Natural-language flow runner (`flow.ts`)

Use `flow.ts` when you want a general command style like:

- "go to this site"
- "find this button and click it"
- "type this and press enter"

### Example

```bash
npx tsx flow.ts --instruction 'go to https://example.com then click on "Sign in" then type "stef@example.com" in #email then press enter'
```

You can also use JSON steps for deterministic runs:

```bash
npx tsx flow.ts --steps '[{"action":"goto","url":"https://example.com"},{"action":"click","text":"Sign in"}]'
```