如何使用Python Selenium验证社交媒体图标链接的正确性

我是Python/Selenium初学者，目前在测试网站的社交媒体图标：

• 已完成图标存在性及链接有效性检查；
• 在验证图标链接是否与预期一致时遇到问题。

现有代码 #

from selenium import webdriver
import time
import urllib
from selenium.webdriver.chrome.options import Options
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
import pytest

chrome_options = Options()
chrome_options.add_argument("--start-maximized")
driver = webdriver.Chrome(options=chrome_options)
driver.get('https://www.poland4weekend.com/')

link_FB = "https://www.facebook.com/Poland4Weekend/"

time.sleep(1)
button_accept_cookies = driver.find_element(By.XPATH,'/html/body/div[2]/div/div/div[1]/button[1]')
button_accept_cookies.click()
time.sleep(1)
link = driver.find_element(By.XPATH,'//*[@id="bgLayers_comp-jsugpnao"]/div[1]')
webdriver.ActionChains(driver).move_to_element(link).perform()
driver.get_screenshot_as_file('footer_screenshot.png')

driver.find_element(By.XPATH, '//*[@id="dataItem-jsugpnbn-comp-jsugpnbl"]/a')
button_fb = driver.find_element(By.XPATH, '//*[@id="dataItem-jsugpnbn-comp-jsugpnbl"]/a')
button_fb.click()
assert button_fb is not None
print ("Link FB is active")

尝试过的有问题的代码 #

URL = self.driver.current_url
self.assertequal('https://www.facebook.com/Poland4Weekend/', URL)

if self.driver.current_url == link_FB:
    print("FB link is correct")
else:
    print("FB link is incorrect")

更优的链接验证方案 #

1. 直接读取href属性（最可靠） #

无需点击跳转后验证，直接获取图标的href属性值与预期链接比对，避免多窗口处理、重定向等干扰：

修改后的核心代码示例：

# 定位Facebook图标链接元素
fb_link_element = driver.find_element(By.XPATH, '//*[@id="dataItem-jsugpnbn-comp-jsugpnbl"]/a')

# 验证元素存在
assert fb_link_element is not None, "Facebook图标不存在"
print("Facebook图标存在")

# 获取实际链接
actual_fb_link = fb_link_element.get_attribute('href')

# 验证链接匹配
expected_fb_link = "https://www.facebook.com/Poland4Weekend/"
assert actual_fb_link == expected_fb_link, f"链接不匹配：预期{expected_fb_link}，实际{actual_fb_link}"
print("Facebook链接与预期一致")

2. 处理URL标准化问题 #

如果遇到链接带跟踪参数、协议自动转换（HTTP→HTTPS）等情况，可先标准化URL再比对：

from urllib.parse import urlparse

def normalize_url(url):
    parsed = urlparse(url)
    # 统一协议、去掉查询参数、去除末尾斜杠
    return f"{parsed.scheme}://{parsed.netloc}{parsed.path}".rstrip('/')

# 标准化后比对
normalized_actual = normalize_url(actual_fb_link)
normalized_expected = normalize_url(expected_fb_link)
assert normalized_actual == normalized_expected, f"标准化后链接不匹配：预期{normalized_expected}，实际{normalized_actual}"

3. 替换time.sleep为显式等待 #

原代码中time.sleep稳定性差，改用显式等待确保元素加载完成：

from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

wait = WebDriverWait(driver, 10)
# 等待cookie按钮可点击
button_accept_cookies = wait.until(EC.element_to_be_clickable((By.XPATH, '/html/body/div[2]/div/div/div[1]/button[1]')))
button_accept_cookies.click()

# 等待Facebook链接元素可见
fb_link_element = wait.until(EC.visibility_of_element_located((By.XPATH, '//*[@id="dataItem-jsugpnbn-comp-jsugpnbl"]/a')))

内容的提问来源于stack exchange，提问作者Ela Janowicz