Python Selenium教程：定位特定文本并提取关键子串

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

from selenium import webdriver
from selenium.webdriver.common.by import By

# 假设driver已经初始化并导航到包含目标内容的页面
# driver = webdriver.Chrome()
# driver.get("your_page_url_here")

try:
    # 定位包含“Confirmation link:”的<b>元素，并获取其完整文本
    message_text_element = driver.find_element(By.XPATH, "//div[@data-test-id='message-view-body-content']//b[contains(., 'Confirmation link')]")
    full_element_text = message_text_element.text
    print(f"完整元素文本: {full_element_text}")
except Exception as e:
    print(f"未能找到元素或发生错误: {e}")
    full_element_text = "" # 设置默认值或采取其他错误处理措施

# 假设 full_element_text = "Confirmation link: https://faucetpay.io/account/confirm_account/..."

# 使用"Confirmation link:"作为分隔符进行分割
parts = full_element_text.split("Confirmation link:")
# 结果将是 ['',' https://faucetpay.io/account/confirm_account/...']
print(f"分割后的列表: {parts}")

# 获取列表的最后一个元素，即冒号后面的内容
link_from_text = parts[-1]
print(f"初步提取的链接: {link_from_text}")

# 使用strip()方法去除可能存在的首尾空格
cleaned_link = link_from_text.strip()
print(f"最终提取的链接: {cleaned_link}")

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

# 初始化WebDriver (以Chrome为例)
# 推荐使用webdriver_manager自动管理浏览器驱动
service = Service(ChromeDriverManager().install())
driver = webdriver.Chrome(service=service)

try:
    # 导航到包含目标内容的本地HTML文件或URL
    # 这里我们使用一个简单的模拟页面内容来演示
    # 实际应用中，您会导航到真实的网页
    driver.get("data:text/html," + """
        <div class="msg-body P_wpofO mq_AS" data-test-id="message-view-body-content">
            <div>
                <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/example_token_12345</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>
    """)
    time.sleep(2) # 等待页面加载

    # 1. 定位元素并获取其完整文本
    message_text_element = driver.find_element(
        By.XPATH,
        "//div[@data-test-id='message-view-body-content']//b[contains(., 'Confirmation link')]"
    )
    full_element_text = message_text_element.text
    print(f"提取到的完整文本: {full_element_text}")

    # 2. 使用split()和strip()提取链接
    # 注意：如果"Confirmation link:"不存在，split()会返回一个只包含原始字符串的列表
    # 因此，[-1]在这里是安全的，但如果确定分隔符可能不存在，需要额外的检查
    if "Confirmation link:" in full_element_text:
        link_from_text = full_element_text.split("Confirmation link:")[-1]
        cleaned_link = link_from_text.strip()
        print(f"成功提取的确认链接: {cleaned_link}")
    else:
        print("未在文本中找到 'Confirmation link:' 标识符。")

except Exception as e:
    print(f"在执行过程中发生错误: {e}")

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