Selenium中提取HTML标签内所有直接文本节点内容的高级技巧

<td id="td_id">
  <p>Name</p>
                    <div class="aritcle_card">
                        <a class="aritcle_card_img" href="/ai/2373">
                            <img src="https://img.php.cn/upload/ai_manual/001/246/273/176239923777053.png" alt="论小文">
                        </a>
                        <div class="aritcle_card_info">
                            <a href="/ai/2373">论小文</a>
                            <p>可靠的论文写作助手，包含11种学术写作类型，万字论文一键生成，可降重降AIGC，参考文献真实可标注，图表代码均可自定义添加。</p>
                            <div class="">
                                <img src="/static/images/card_xiazai.png" alt="论小文">
                                <span>431</span>
                            </div>
                        </div>
                        <a href="/ai/2373" class="aritcle_card_btn">
                            <span>查看详情</span>
                            <img src="/static/images/cardxiayige-3.png" alt="论小文">
                        </a>
                    </div>
                <p><span>立即学习</span>“<a href="https://pan.quark.cn/s/cb6835dc7db1" style="text-decoration: underline !important; color: blue; font-weight: bolder;" rel="nofollow" target="_blank">前端免费学习笔记（深入）</a>”；</p>
  <div>
    <span>agdsf</span>
  </div>
  John Smith
  <span>dfsdf</span>
  Address:
  <br>
  NewYork
</td>

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元素的页面
# driver = webdriver.Chrome()
# driver.get("your_page_url.html")

# 为了演示，我们模拟一个 driver 和 td_tag
class MockWebElement:
    def __init__(self, element_id):
        self.id = element_id

    def find_element(self, by, value):
        if by == By.ID and value == "td_id":
            return self
        raise Exception("Element not found")

    def execute_script(self, script, element):
        # 模拟浏览器执行JS并返回结果
        if element.id == "td_id":
            # 这里的JS会根据上面提供的DOM结构进行模拟计算
            # 实际浏览器会直接执行并返回
            dom_structure = """
            <td id="td_id">
              <p>Name</p><p><span>立即学习</span>“<a href="https://pan.quark.cn/s/cb6835dc7db1" style="text-decoration: underline !important; color: blue; font-weight: bolder;" rel="nofollow" target="_blank">前端免费学习笔记（深入）</a>”；</p>
              <div>
                <span>agdsf</span>
              </div>
              John Smith
              <span>dfsdf</span>
              Address:
              <br>
              NewYork
            </td>
            """
            # 简化模拟，直接返回预期结果
            return "John Smith Address: NewYork"
        return ""

# 真实场景下，您会这样初始化 driver
driver = webdriver.Chrome() # 或其他浏览器驱动
driver.get("file:///path/to/your/html/file.html") # 替换为您的HTML文件路径或网页URL

# 定位目标 td 元素
td_tag = driver.find_element(By.ID, "td_id")

# 执行JavaScript代码来提取所有直接文本节点
all_direct_text = driver.execute_script("""
    var node = arguments[0]; // 获取Selenium传递过来的元素
    var text = '';
    // 遍历目标元素的所有直接子节点
    for (var child = node.firstChild; child; child = child.nextSibling) {
        // 检查子节点是否为文本节点 (Node.TEXT_NODE === 3)
        if (child.nodeType === Node.TEXT_NODE) {
            // 如果是文本节点，则将其内容添加到结果字符串中，并去除首尾空白
            text += child.textContent.trim() + ' ';
        }
    }
    // 返回最终结果，并去除末尾可能多余的空格
    return text.trim();
""", td_tag)

print(f"提取到的直接文本内容: \"{all_direct_text}\"")

# 完成后关闭浏览器
driver.quit()