python - 如何在 Python 中检查 Selenium Webdriver 中的单击是否更改了页面

Question

我一直在读到使用 Selenium 的 webdrivers 的 click() 是异步的，所以我一直试图让 webdriver 等待点击完成，然后再做任何其他事情。我使用 PhantomJS 作为浏览器。

我有 WebDriverWait 对象来等待页面上的元素发生更改(这就是我在单击某些内容后判断页面是否已加载/更改的方式)。我的问题是我不断从 WebDriverWait 收到 TimeoutExceptions。

点击某些内容后，我可以做些什么来等待页面加载吗？我不想使用 time.sleep(1) 因为加载时间似乎是可变的，而且我不希望它休眠太久。这就是为什么我想显式等待页面加载。

这是我的网络驱动程序代码和相应的等待:

import time
from bs4 import BeautifulSoup
from selenium import webdriver
import selenium.webdriver.support.ui as ui
import selenium.common.exceptions as exceptions

class Webdriver():

    def __init__(self, wait_time=10):
        self.driver = webdriver.PhantomJS()
        self.driver.set_window_size(1200,800)
        self.wait = wait_time

    def click(self, element_xpath, wait_xpath, sleep_time=0):
        wait = ui.WebDriverWait(self.driver, self.wait)
        old_element = self.driver.find_element_by_xpath(wait_xpath)
        old_text = old_element.text
        self.driver.find_element_by_xpath(element_xpath).click()
        wait.until(lambda driver: element_changed(driver, wait_xpath, old_text,20))
        time.sleep(sleep_time)

def element_changed(driver, element_xpath, old_element_text, timeout_seconds=10):
    pause_interval = 1
    t0 = time.time()
    while time.time() - t0 < timeout_seconds:
        try:
            element = driver.find_element_by_xpath(element_xpath)
            if element.text != old_element_text:
                return True
        except exceptions.StaleElementReferenceException:
            return True
        except exceptions.NoSuchElementException:
            pass
        time.sleep(pause_interval)
    return False

这是运行的代码:

driver = Webdriver()
url = 'http://www.atmel.com/products/microcontrollers/avr/default.aspx?tab=parameters'
wait_xpath = '//*[@id="device-columns"]/tbody/tr[2]/td[1]/div[2]/a'
driver.load(url, wait_xpath)
soup = driver.get_soup()

pages = soup('ul', class_='pagination')[0]('a')
num_pages = len(pages)
products = set()
for i in range(num_pages):
    element_xpath = '//*[@id="top-nav"]/div/ul/li[%d]/a' % (2 + i)
    driver.click(element_xpath, wait_xpath)
    soup = driver.get_soup()
    for tag in soup('td', class_='first-cell'):
        product = tag.find('div', class_='anchor')
        if not product:
            continue
        else:
            if product.find('a'):
                products.add(product.find('a')['href'])

更新

我的部分问题是我正在重新加载第一页并期望它发生变化。但即便如此，在 for 循环之后将点击线和汤线向下移动，有时会需要很长时间才能更改。

Answer 1

我没有使用 WebDriverWait，而是创建了一个函数来等待它加载。现在似乎可以工作，但我不禁觉得它不稳定并且并不总是有效。

def click(self, element_xpath, wait_xpath=None, sleep_time=0):
    if wait_xpath:
        old_element = self.driver.find_element_by_xpath(wait_xpath)
        old_text = old_element.text
    self.driver.find_element_by_xpath(element_xpath).click()
    if wait_xpath:
        if not element_changed(self.driver, wait_xpath, old_text):
            log.warn('click did not change element at %s', wait_xpath)
            return False
    time.sleep(sleep_time)
    return True

def element_changed(driver, element_xpath, old_element_text, timeout_seconds=10):
    pause_interval = 1
    t0 = time.time()
    while time.time() - t0 < timeout_seconds:
        try:
            element = driver.find_element_by_xpath(element_xpath)
            if element.text != old_element_text:
                return True
        except exceptions.StaleElementReferenceException:
            return True
        except exceptions.NoSuchElementException:
            pass
        time.sleep(pause_interval)
    return False

运行代码是这样的:

driver = Webdriver()
url = 'http://www.atmel.com/products/microcontrollers/avr/default.aspx?tab=parameters'
wait_xpath = '//*[@id="device-columns"]/tbody/tr[2]/td[1]/div[2]/a'
driver.load(url, wait_xpath)
soup = driver.get_soup()

pages = soup('ul', class_='pagination')[0]('a')
num_pages = len(pages)
products = set()
for i in range(num_pages):
    element_xpath = '//*[@id="top-nav"]/div/ul/li[%d]/a' % (2 + i)
    if i == 0:
        driver.click(element_xpath, None, 1)
    else:
        driver.click(element_xpath, wait_xpath, 1)
    soup = driver.get_soup()
    for tag in soup('td', class_='first-cell'):
        product = tag.find('div', class_='anchor')
        if not product:
            continue
        else:
            if product.find('a'):
                products.add(product.find('a')['href'])