使用Python Selenium定位并提取页面特定文本信息

<div class="msg-body P_wpofO mq_AS" data-test-id="message-view-body-content">
    <div>
        <div>
            <div id="yiv5768405894">
                <!-- ... other content ... -->
                <b>Confirmation link: https://faucetpay.io/account/confirm_account/...</b>
                <!-- ... other content ... -->
            </div>
        </div>
    </div>
</div>

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
import time

# 假设您已经启动了WebDriver并导航到包含目标内容的页面
# 这里仅为演示目的，实际应用中请根据您的环境配置WebDriver

# 启动WebDriver
# 如果您没有手动下载ChromeDriver，可以使用webdriver_manager自动管理
service = Service(ChromeDriverManager().install())
driver = webdriver.Chrome(service=service)

try:
    # 导航到包含目标内容的页面（请替换为实际URL或加载本地HTML）
    # 为了演示，我们模拟一个包含上述HTML的页面
    driver.get("data:text/html;charset=utf-8," + """
    <div class="msg-body P_wpofO mq_AS" data-test-id="message-view-body-content">
        <div class="jb_0 X_6MGW N_6Fd5">
            <div>
                <div id="yiv5768405894">Hello,
                    <br>
                    <br>
                    Thank you for registering at FaucetPay. However, before you getting running on the site, you've to confirm your email address. Click <b><a rel="nofollow noopener noreferrer" target="_blank" href="http://email.ml.faucetpay.io/c/eJxNT7uOxCAM_JpQRmBjAgXFNfcbJ7CNklOyrHJJsX9_dLvSFPPQ2BrNLgSXgiUiI7l4FGCzZbAANqJz5AFp5pJSTc0xuEXVyeTtsc-t3KzXs7zmrZs1F5RolZhJSbVFkAW91eLrsujIzJ7X63r-Tfg1wffAZ3_IwtzvxzUY90fbzuPn7UhtpJVEkaJ6jKxYbIgQxnmEyhUkSErixzdE11C9F63JNiRoUMyZuR_HvR961u1Xx4BXWXufh_sPy8pPlQ">here</a></b> to confirm your account, or copy the link below directly to confirm your email address.
                    <br>
                    <br>
                    <b>Confirmation link: https://faucetpay.io/account/confirm_account/YOUR_UNIQUE_TOKEN</b>
                    <br>
                    <br>                
                    Regards,
                    <br>
                    FaucetPay
                    <br>
                    <br>
                    <small>If you didn't apply for an account, please ignore this email and you won't be bugged again.</small>
                </div>
            </div>
        </div>
    </div>
    """)

    # 等待页面加载完成，或等待元素可见（如果需要）
    time.sleep(2) 

    # 1. 定位元素并获取其完整文本
    # 使用XPath定位包含“Confirmation link”的<b>标签
    message_element = driver.find_element(By.XPATH, "//div[@data-test-id='message-view-body-content']//b[contains(., 'Confirmation link')]")
    message_text = message_element.text
    print(f"完整元素文本: {message_text}")

    # 2. 处理文本，提取链接部分
    # 以"Confirmation link:"为分隔符分割字符串，并取最后一个部分
    # [-1] 用于获取分割后的最后一个元素，即冒号后的内容
    link_from_text = message_text.split("Confirmation link:")[-1]

    # 使用strip()去除可能存在的首尾空白字符
    extracted_link = link_from_text.strip()

    print(f"提取到的确认链接: {extracted_link}")

except Exception as e:
    print(f"发生错误: {e}")

finally:
    # 关闭浏览器
    driver.quit()