Spaces:
Paused
Paused
File size: 2,568 Bytes
6eb9915 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 | import pdb
import pyperclip
from typing import Optional, Type
from pydantic import BaseModel
from browser_use.agent.views import ActionResult
from browser_use.browser.context import BrowserContext
from browser_use.controller.service import Controller, DoneAction
from main_content_extractor import MainContentExtractor
from browser_use.controller.views import (
ClickElementAction,
DoneAction,
ExtractPageContentAction,
GoToUrlAction,
InputTextAction,
OpenTabAction,
ScrollAction,
SearchGoogleAction,
SendKeysAction,
SwitchTabAction,
)
import logging
logger = logging.getLogger(__name__)
class CustomController(Controller):
def __init__(self, exclude_actions: list[str] = [],
output_model: Optional[Type[BaseModel]] = None
):
super().__init__(exclude_actions=exclude_actions, output_model=output_model)
self._register_custom_actions()
def _register_custom_actions(self):
"""Register all custom browser actions"""
@self.registry.action("Copy text to clipboard")
def copy_to_clipboard(text: str):
pyperclip.copy(text)
return ActionResult(extracted_content=text)
@self.registry.action("Paste text from clipboard", requires_browser=True)
async def paste_from_clipboard(browser: BrowserContext):
text = pyperclip.paste()
# send text to browser
page = await browser.get_current_page()
await page.keyboard.type(text)
return ActionResult(extracted_content=text)
@self.registry.action(
'Extract page content to get the pure text or markdown with links if include_links is set to true',
param_model=ExtractPageContentAction,
requires_browser=True,
)
async def extract_content(params: ExtractPageContentAction, browser: BrowserContext):
page = await browser.get_current_page()
# use jina reader
url = page.url
jina_url = f"https://r.jina.ai/{url}"
await page.goto(jina_url)
output_format = 'markdown' if params.include_links else 'text'
content = MainContentExtractor.extract( # type: ignore
html=await page.content(),
output_format=output_format,
)
# go back to org url
await page.go_back()
msg = f'Extracted page content:\n {content}\n'
logger.info(msg)
return ActionResult(extracted_content=msg)
|