Get the xpath of an element. This is useful for creating selectors for selenium.

selenium_extractor.py

from typing import List

from selenium.common import InvalidSelectorException
from selenium.webdriver.common.by import By
from selenium.webdriver.remote.webelement import WebElement


def get_xpath_for_selenium_element(element: WebElement, use_index: bool = True,
                                   attributes: List[str] = ['id']) -> str:
    """Get the xpath of an element. This is useful for creating selectors for selenium.

    :param element: The element to get the xpath of.
    :param use_index: Whether to use the index of the element in the xpath.
    :param attributes: The attributes to use in the xpath.

    :return: The xpath of the element.
    """
    xpath_parts: List[str] = []

    while element:
        # Get the attributes selector of the element
        attributes_selector = get_attributes_selector(element, attributes)

        tag_name = element.tag_name

        if attributes_selector:
            # If there are attribute parts, add them to the xpath
            xpath_parts.insert(0, f"{tag_name}{attributes_selector}")
        elif use_index:
            # Find all sibling elements with the same tag name
            previous_elements = element.find_elements(By.XPATH, f"preceding-sibling::{tag_name}")
            next_elements = element.find_elements(By.XPATH, f"following-sibling::{tag_name}")
            index = len(previous_elements) + 1

            if previous_elements or next_elements:
                xpath_parts.insert(0, f"{tag_name}[{index}]")
            else:
                xpath_parts.insert(0, f"{tag_name}")
        else:
            xpath_parts.insert(0, f"{tag_name}")

        # Try to find the parent element
        try:
            element = element.find_element(By.XPATH, "..")
        except InvalidSelectorException:
            break

    return "/" + "/".join(xpath_parts)


def get_attributes_selector(element: WebElement, attributes: List[str]) -> str:
    """Get the attributes selector of an element.

    :param element: The element to get the attributes selector of.
    :param attributes: The attributes to use in the selector.

    :return: The attributes selector of the element.
    """

    attributes_parts = [
        f"[@{attribute}='{escaped_value}']"
        for attribute in attributes
        if (value := element.get_attribute(attribute)) and (escaped_value := value.replace("'", "\\'"))
    ]

    return "".join(attributes_parts)

Example usage:

>>> element = driver.find_element(By.XPATH, "//*[@id='dijit_ProgressBar_2']/img")

>>> get_xpath_for_selenium_element(element)
'/html/body/div[3]/table/tbody/tr/td/div[2]/div[@id='dijit_ProgressBar_2']/img'

>>> get_xpath_for_selenium_element(element, use_index=False)
'/html/body/div/table/tbody/tr/td/div/div[@id='dijit_ProgressBar_2']'

>>> get_xpath_for_selenium_element(element, attributes=['class'])
"/html[@class='dj_webkit dj_chrome dj_contentbox']/body[@class='claro']/div[@class='splashscreen']/table/tbody/tr/td/div/div[@class='dijitProgressBar dijitProgressBarEmpty']/img[@class='dijitProgressBarIndeterminateHighContrastImage']"