optexity-browser-use 0.9.5__py3-none-any.whl

browser_use/actor/playground/flights.py

@@ -0,0 +1,41 @@
+import asyncio
+
+from browser_use import Agent, Browser, ChatOpenAI
+
+llm = ChatOpenAI('gpt-4.1-mini')
+
+
+async def main():
+	"""
+	Main function demonstrating mixed automation with Browser-Use and Playwright.
+	"""
+	print('🚀 Mixed Automation with Browser-Use and Actor API')
+
+	browser = Browser(keep_alive=True)
+	await browser.start()
+
+	page = await browser.get_current_page() or await browser.new_page()
+
+	# Go to apple wikipedia page
+	await page.goto('https://www.google.com/travel/flights')
+
+	await asyncio.sleep(1)
+
+	round_trip_button = await page.must_get_element_by_prompt('round trip button', llm)
+	await round_trip_button.click()
+
+	one_way_button = await page.must_get_element_by_prompt('one way button', llm)
+	await one_way_button.click()
+
+	await asyncio.sleep(1)
+
+	agent = Agent(task='Find the cheapest flight from London to Paris on 2025-10-15', llm=llm, browser_session=browser)
+	await agent.run()
+
+	input('Press Enter to continue...')
+
+	await browser.stop()
+
+
+if __name__ == '__main__':
+	asyncio.run(main())

browser_use/actor/playground/mixed_automation.py

@@ -0,0 +1,54 @@
+import asyncio
+
+from pydantic import BaseModel
+
+from browser_use import Browser, ChatOpenAI
+
+TASK = """
+On the current wikipedia page, find the latest huge edit and tell me what is was about.
+"""
+
+
+class LatestEditFinder(BaseModel):
+	"""Find the latest huge edit on the current wikipedia page."""
+
+	latest_edit: str
+	edit_time: str
+	edit_author: str
+	edit_summary: str
+	edit_url: str
+
+
+llm = ChatOpenAI('gpt-4.1-mini')
+
+
+async def main():
+	"""
+	Main function demonstrating mixed automation with Browser-Use and Playwright.
+	"""
+	print('🚀 Mixed Automation with Browser-Use and Actor API')
+
+	browser = Browser(keep_alive=True)
+	await browser.start()
+
+	page = await browser.get_current_page() or await browser.new_page()
+
+	# Go to apple wikipedia page
+	await page.goto('https://browser-use.github.io/stress-tests/challenges/angularjs-form.html')
+
+	await asyncio.sleep(1)
+
+	element = await page.get_element_by_prompt('zip code input', llm)
+
+	print('Element found', element)
+
+	if element:
+		await element.click()
+	else:
+		print('No element found')
+
+	await browser.stop()
+
+
+if __name__ == '__main__':
+	asyncio.run(main())

browser_use/actor/playground/playground.py

@@ -0,0 +1,236 @@
+#!/usr/bin/env python3
+"""
+Playground script to test the browser-use actor API.
+
+This script demonstrates:
+- Starting a browser session
+- Using the actor API to navigate and interact
+- Finding elements, clicking, scrolling, JavaScript evaluation
+- Testing most of the available methods
+"""
+
+import asyncio
+import json
+import logging
+
+from browser_use import Browser
+
+# Configure logging to see what's happening
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+
+async def main():
+	"""Main playground function."""
+	logger.info('🚀 Starting browser actor playground')
+
+	# Create browser session
+	browser = Browser()
+
+	try:
+		# Start the browser
+		await browser.start()
+		logger.info('✅ Browser session started')
+
+		# Navigate to Wikipedia using integrated methods
+		logger.info('📖 Navigating to Wikipedia...')
+		page = await browser.new_page('https://en.wikipedia.org')
+
+		# Get basic page info
+		url = await page.get_url()
+		title = await page.get_title()
+		logger.info(f'📄 Page loaded: {title} ({url})')
+
+		# Take a screenshot
+		logger.info('📸 Taking initial screenshot...')
+		screenshot_b64 = await page.screenshot()
+		logger.info(f'📸 Screenshot captured: {len(screenshot_b64)} bytes')
+
+		# Set viewport size
+		logger.info('🖥️ Setting viewport to 1920x1080...')
+		await page.set_viewport_size(1920, 1080)
+
+		# Execute some JavaScript to count links
+		logger.info('🔍 Counting article links using JavaScript...')
+		js_code = """() => {
+			// Find all article links on the page
+			const links = Array.from(document.querySelectorAll('a[href*="/wiki/"]:not([href*=":"])'))
+				.filter(link => !link.href.includes('Main_Page') && !link.href.includes('Special:'));
+			
+			return {
+				total: links.length,
+				sample: links.slice(0, 3).map(link => ({
+					href: link.href,
+					text: link.textContent.trim() 
+				}))
+			};
+		}"""
+
+		link_info = json.loads(await page.evaluate(js_code))
+		logger.info(f'🔗 Found {link_info["total"]} article links')
+		# Try to find and interact with links using CSS selector
+		try:
+			# Find article links on the page
+			links = await page.get_elements_by_css_selector('a[href*="/wiki/"]:not([href*=":"])')
+
+			if links:
+				logger.info(f'📋 Found {len(links)} wiki links via CSS selector')
+
+				# Pick the first link
+				link_element = links[0]
+
+				# Get link info using available methods
+				basic_info = await link_element.get_basic_info()
+				link_href = await link_element.get_attribute('href')
+
+				logger.info(f'🎯 Selected element: <{basic_info["nodeName"]}>')
+				logger.info(f'🔗 Link href: {link_href}')
+
+				if basic_info['boundingBox']:
+					bbox = basic_info['boundingBox']
+					logger.info(f'📏 Position: ({bbox["x"]}, {bbox["y"]}) Size: {bbox["width"]}x{bbox["height"]}')
+
+				# Test element interactions with robust implementations
+				logger.info('👆 Hovering over the element...')
+				await link_element.hover()
+				await asyncio.sleep(1)
+
+				logger.info('🔍 Focusing the element...')
+				await link_element.focus()
+				await asyncio.sleep(0.5)
+
+				# Click the link using robust click method
+				logger.info('🖱️ Clicking the link with robust fallbacks...')
+				await link_element.click()
+
+				# Wait for navigation
+				await asyncio.sleep(3)
+
+				# Get new page info
+				new_url = await page.get_url()
+				new_title = await page.get_title()
+				logger.info(f'📄 Navigated to: {new_title}')
+				logger.info(f'🌐 New URL: {new_url}')
+			else:
+				logger.warning('❌ No links found to interact with')
+
+		except Exception as e:
+			logger.warning(f'⚠️ Link interaction failed: {e}')
+
+		# Scroll down the page
+		logger.info('📜 Scrolling down the page...')
+		mouse = await page.mouse
+		await mouse.scroll(x=0, y=100, delta_y=500)
+		await asyncio.sleep(1)
+
+		# Test mouse operations
+		logger.info('🖱️ Testing mouse operations...')
+		await mouse.move(x=100, y=200)
+		await mouse.click(x=150, y=250)
+
+		# Execute more JavaScript examples
+		logger.info('🧪 Testing JavaScript evaluation...')
+
+		# Simple expressions
+		page_height = await page.evaluate('() => document.body.scrollHeight')
+		current_scroll = await page.evaluate('() => window.pageYOffset')
+		logger.info(f'📏 Page height: {page_height}px, current scroll: {current_scroll}px')
+
+		# JavaScript with arguments
+		result = await page.evaluate('(x) => x * 2', 21)
+		logger.info(f'🧮 JavaScript with args: 21 * 2 = {result}')
+
+		# More complex JavaScript
+		page_stats = json.loads(
+			await page.evaluate("""() => {
+			return {
+				url: window.location.href,
+				title: document.title,
+				links: document.querySelectorAll('a').length,
+				images: document.querySelectorAll('img').length,
+				scrollTop: window.pageYOffset,
+				viewportHeight: window.innerHeight
+			};
+		}""")
+		)
+		logger.info(f'📊 Page stats: {page_stats}')
+
+		# Get page title using different methods
+		title_via_js = await page.evaluate('() => document.title')
+		title_via_api = await page.get_title()
+		logger.info(f'📝 Title via JS: "{title_via_js}"')
+		logger.info(f'📝 Title via API: "{title_via_api}"')
+
+		# Take a final screenshot
+		logger.info('📸 Taking final screenshot...')
+		final_screenshot = await page.screenshot()
+		logger.info(f'📸 Final screenshot: {len(final_screenshot)} bytes')
+
+		# Test browser navigation with error handling
+		logger.info('⬅️ Testing browser back navigation...')
+		try:
+			await page.go_back()
+			await asyncio.sleep(2)
+
+			back_url = await page.get_url()
+			back_title = await page.get_title()
+			logger.info(f'📄 After going back: {back_title}')
+			logger.info(f'🌐 Back URL: {back_url}')
+		except RuntimeError as e:
+			logger.info(f'ℹ️ Navigation back failed as expected: {e}')
+
+		# Test creating new page
+		logger.info('🆕 Creating new blank page...')
+		new_page = await browser.new_page()
+		new_page_url = await new_page.get_url()
+		logger.info(f'🆕 New page created with URL: {new_page_url}')
+
+		# Get all pages
+		all_pages = await browser.get_pages()
+		logger.info(f'📑 Total pages: {len(all_pages)}')
+
+		# Test form interaction if we can find a form
+		try:
+			# Look for search input on the page
+			search_inputs = await page.get_elements_by_css_selector('input[type="search"], input[name*="search"]')
+
+			if search_inputs:
+				search_input = search_inputs[0]
+				logger.info('🔍 Found search input, testing form interaction...')
+
+				await search_input.focus()
+				await search_input.fill('test search query')
+				await page.press('Enter')
+
+				logger.info('✅ Form interaction test completed')
+			else:
+				logger.info('ℹ️ No search inputs found for form testing')
+
+		except Exception as e:
+			logger.info(f'ℹ️ Form interaction test skipped: {e}')
+
+			# wait 2 seconds before closing the new page
+		logger.info('🕒 Waiting 2 seconds before closing the new page...')
+		await asyncio.sleep(2)
+		logger.info('🗑️ Closing new page...')
+		await browser.close_page(new_page)
+
+		logger.info('✅ Playground completed successfully!')
+
+		input('Press Enter to continue...')
+
+	except Exception as e:
+		logger.error(f'❌ Error in playground: {e}', exc_info=True)
+
+	finally:
+		# Clean up
+		logger.info('🧹 Cleaning up...')
+		try:
+			await browser.stop()
+			logger.info('✅ Browser session stopped')
+		except Exception as e:
+			logger.error(f'❌ Error stopping browser: {e}')
+
+
+if __name__ == '__main__':
+	asyncio.run(main())

browser_use/actor/utils.py

@@ -0,0 +1,176 @@
+"""Utility functions for actor operations."""
+
+
+class Utils:
+	"""Utility functions for actor operations."""
+
+	@staticmethod
+	def get_key_info(key: str) -> tuple[str, int | None]:
+		"""Get the code and windowsVirtualKeyCode for a key.
+
+		Args:
+			key: Key name (e.g., 'Enter', 'ArrowUp', 'a', 'A')
+
+		Returns:
+			Tuple of (code, windowsVirtualKeyCode)
+
+		Reference: Windows Virtual Key Codes
+		https://docs.microsoft.com/en-us/windows/win32/inputdev/virtual-key-codes
+		"""
+		# Complete mapping of key names to (code, virtualKeyCode)
+		# Based on standard Windows Virtual Key Codes
+		key_map = {
+			# Navigation keys
+			'Backspace': ('Backspace', 8),
+			'Tab': ('Tab', 9),
+			'Enter': ('Enter', 13),
+			'Escape': ('Escape', 27),
+			'Space': ('Space', 32),
+			' ': ('Space', 32),
+			'PageUp': ('PageUp', 33),
+			'PageDown': ('PageDown', 34),
+			'End': ('End', 35),
+			'Home': ('Home', 36),
+			'ArrowLeft': ('ArrowLeft', 37),
+			'ArrowUp': ('ArrowUp', 38),
+			'ArrowRight': ('ArrowRight', 39),
+			'ArrowDown': ('ArrowDown', 40),
+			'Insert': ('Insert', 45),
+			'Delete': ('Delete', 46),
+			# Modifier keys
+			'Shift': ('ShiftLeft', 16),
+			'ShiftLeft': ('ShiftLeft', 16),
+			'ShiftRight': ('ShiftRight', 16),
+			'Control': ('ControlLeft', 17),
+			'ControlLeft': ('ControlLeft', 17),
+			'ControlRight': ('ControlRight', 17),
+			'Alt': ('AltLeft', 18),
+			'AltLeft': ('AltLeft', 18),
+			'AltRight': ('AltRight', 18),
+			'Meta': ('MetaLeft', 91),
+			'MetaLeft': ('MetaLeft', 91),
+			'MetaRight': ('MetaRight', 92),
+			# Function keys F1-F24
+			'F1': ('F1', 112),
+			'F2': ('F2', 113),
+			'F3': ('F3', 114),
+			'F4': ('F4', 115),
+			'F5': ('F5', 116),
+			'F6': ('F6', 117),
+			'F7': ('F7', 118),
+			'F8': ('F8', 119),
+			'F9': ('F9', 120),
+			'F10': ('F10', 121),
+			'F11': ('F11', 122),
+			'F12': ('F12', 123),
+			'F13': ('F13', 124),
+			'F14': ('F14', 125),
+			'F15': ('F15', 126),
+			'F16': ('F16', 127),
+			'F17': ('F17', 128),
+			'F18': ('F18', 129),
+			'F19': ('F19', 130),
+			'F20': ('F20', 131),
+			'F21': ('F21', 132),
+			'F22': ('F22', 133),
+			'F23': ('F23', 134),
+			'F24': ('F24', 135),
+			# Numpad keys
+			'NumLock': ('NumLock', 144),
+			'Numpad0': ('Numpad0', 96),
+			'Numpad1': ('Numpad1', 97),
+			'Numpad2': ('Numpad2', 98),
+			'Numpad3': ('Numpad3', 99),
+			'Numpad4': ('Numpad4', 100),
+			'Numpad5': ('Numpad5', 101),
+			'Numpad6': ('Numpad6', 102),
+			'Numpad7': ('Numpad7', 103),
+			'Numpad8': ('Numpad8', 104),
+			'Numpad9': ('Numpad9', 105),
+			'NumpadMultiply': ('NumpadMultiply', 106),
+			'NumpadAdd': ('NumpadAdd', 107),
+			'NumpadSubtract': ('NumpadSubtract', 109),
+			'NumpadDecimal': ('NumpadDecimal', 110),
+			'NumpadDivide': ('NumpadDivide', 111),
+			# Lock keys
+			'CapsLock': ('CapsLock', 20),
+			'ScrollLock': ('ScrollLock', 145),
+			# OEM/Punctuation keys (US keyboard layout)
+			'Semicolon': ('Semicolon', 186),
+			';': ('Semicolon', 186),
+			'Equal': ('Equal', 187),
+			'=': ('Equal', 187),
+			'Comma': ('Comma', 188),
+			',': ('Comma', 188),
+			'Minus': ('Minus', 189),
+			'-': ('Minus', 189),
+			'Period': ('Period', 190),
+			'.': ('Period', 190),
+			'Slash': ('Slash', 191),
+			'/': ('Slash', 191),
+			'Backquote': ('Backquote', 192),
+			'`': ('Backquote', 192),
+			'BracketLeft': ('BracketLeft', 219),
+			'[': ('BracketLeft', 219),
+			'Backslash': ('Backslash', 220),
+			'\\': ('Backslash', 220),
+			'BracketRight': ('BracketRight', 221),
+			']': ('BracketRight', 221),
+			'Quote': ('Quote', 222),
+			"'": ('Quote', 222),
+			# Media/Browser keys
+			'AudioVolumeMute': ('AudioVolumeMute', 173),
+			'AudioVolumeDown': ('AudioVolumeDown', 174),
+			'AudioVolumeUp': ('AudioVolumeUp', 175),
+			'MediaTrackNext': ('MediaTrackNext', 176),
+			'MediaTrackPrevious': ('MediaTrackPrevious', 177),
+			'MediaStop': ('MediaStop', 178),
+			'MediaPlayPause': ('MediaPlayPause', 179),
+			'BrowserBack': ('BrowserBack', 166),
+			'BrowserForward': ('BrowserForward', 167),
+			'BrowserRefresh': ('BrowserRefresh', 168),
+			'BrowserStop': ('BrowserStop', 169),
+			'BrowserSearch': ('BrowserSearch', 170),
+			'BrowserFavorites': ('BrowserFavorites', 171),
+			'BrowserHome': ('BrowserHome', 172),
+			# Additional common keys
+			'Clear': ('Clear', 12),
+			'Pause': ('Pause', 19),
+			'Select': ('Select', 41),
+			'Print': ('Print', 42),
+			'Execute': ('Execute', 43),
+			'PrintScreen': ('PrintScreen', 44),
+			'Help': ('Help', 47),
+			'ContextMenu': ('ContextMenu', 93),
+		}
+
+		if key in key_map:
+			return key_map[key]
+
+		# Handle alphanumeric keys dynamically
+		if len(key) == 1:
+			if key.isalpha():
+				# Letter keys: A-Z have VK codes 65-90
+				return (f'Key{key.upper()}', ord(key.upper()))
+			elif key.isdigit():
+				# Digit keys: 0-9 have VK codes 48-57 (same as ASCII)
+				return (f'Digit{key}', ord(key))
+
+		# Fallback: use the key name as code, no virtual key code
+		return (key, None)
+
+
+# Backward compatibility: provide standalone function
+def get_key_info(key: str) -> tuple[str, int | None]:
+	"""Get the code and windowsVirtualKeyCode for a key.
+
+	Args:
+		key: Key name (e.g., 'Enter', 'ArrowUp', 'a', 'A')
+
+	Returns:
+		Tuple of (code, windowsVirtualKeyCode)
+
+	Reference: Windows Virtual Key Codes
+	https://docs.microsoft.com/en-us/windows/win32/inputdev/virtual-key-codes
+	"""
+	return Utils.get_key_info(key)