tools/search_item_ctrl_f.py

from typing import Any
from smolagents.tools import Tool
from selenium.webdriver.common.by import By

class SearchItemCtrlFTool(Tool):
    name = "search_item_ctrl_f"
    description = """
    Searches for text on the current page via Ctrl + F and jumps to the nth occurrence.
    Args:
        text: The text to search for
        nth_result: Which occurrence to jump to (default: 1)
    """
    inputs = {
        'text': {'type': 'string', 'description': 'The text to search for'},
        'nth_result': {'type': 'integer', 'description': 'Which occurrence to jump to (default: 1)', 'nullable': True}
    }
    output_type = "string"

    def __init__(self, driver: Any = None, *args, **kwargs):
        super().__init__(*args, **kwargs)
        self.driver = driver
        self.is_initialized = False

    def forward(self, text: str, nth_result: int = 1) -> str:
        if not self.driver:
            raise ValueError("WebDriver instance is required.")
        elements = self.driver.find_elements(By.XPATH, f"//*[contains(text(), '{text}')]")
        if nth_result > len(elements):
            raise Exception(f"Match n°{nth_result} not found (only {len(elements)} matches found)")
        result = f"Found {len(elements)} matches for '{text}'."
        elem = elements[nth_result - 1]
        self.driver.execute_script("arguments[0].scrollIntoView(true);", elem)
        result += f" Focused on element {nth_result} of {len(elements)}"
        return result