Python使用XPath实现动态属性的精准定位

<div id="item-7f3b9a2e"></div>
<div id="item-4d8f1a7b"></div>

<div class="widget-1648927302"></div>
<div class="widget-1648927315"></div>

<button data-uid="user_1001_session_xyz"></button>

<span data-testid="product-card_3a9f2b8c"></span>

from selenium import webdriver

driver = webdriver.Chrome()
driver.get("https://example.com/dynamic-products")

# 通过可见文本定位（最稳定）
element = driver.find_element_by_xpath('//div[contains(text(), "Premium Edition")]')

# 或通过子元素文本
element = driver.find_element_by_xpath('//div[./span[text()="Price: $99"]]')

# 匹配包含特定字符串的属性
elements = driver.find_elements_by_xpath('//div[contains(@id, "item-")]')

# 匹配前缀固定的属性
elements = driver.find_elements_by_xpath('//div[starts-with(@class, "widget-")]')

# 组合多个条件（AND逻辑）
elements = driver.find_elements_by_xpath('//div[contains(@id, "item-") and contains(@class, "active")]')

from lxml import html
import requests

response = requests.get("https://example.com")
tree = html.fromstring(response.content)

# 匹配符合正则的ID属性
elements = tree.xpath('//div[matches(@id, "^item-[a-f0-9]{8}$")]')

# 提取动态数据属性中的关键信息
uids = tree.xpath('//button/@data-uid[matches(., "^user_\\d+_session_")]')

# 通过固定父元素定位
element = driver.find_element_by_xpath('//div[@class="static-parent"]/div[2]')

# 通过前一个兄弟元素定位
element = driver.find_element_by_xpath('//span[text()="Price:"]/following-sibling::span')

# 通过轴定位（更灵活的层级关系）
element = driver.find_element_by_xpath('//div[@class="header"]/following::div[contains(@class, "content")]')

<div class="product-grid">
  <div id="prod-8a3f2b9c" class="card">
    <h3>Laptop Pro</h3>
    <span class="price">$999</span>
  </div>
  <div id="prod-4d8f1a7b" class="card">
    <h3>Smartphone X</h3>
    <span class="price">$599</span>
  </div>
</div>

# 方法1：通过价格反向定位
elements = driver.find_elements_by_xpath(
    '//div[contains(@id, "prod-")]/span[@class="price"][number(translate(text(), "$", "")) < 600]/../h3'
)

# 方法2：先定位所有卡片再筛选（更清晰）
cards = driver.find_elements_by_xpath('//div[contains(@id, "prod-") and contains(@class, "card")]')
for card in cards:
    price = card.find_element_by_xpath('.//span[@class="price"]').text
    if float(price.replace('$', '')) < 600:
        print(card.find_element_by_xpath('.//h3').text)

<div data-testid="product-card_3a9f2b8c">
  <button data-testid="add-to-cart_7d2f1a9e">Add to Cart</button>
</div>

# 方法1：通过固定前缀定位
button = driver.find_element_by_xpath('//button[starts-with(@data-testid, "add-to-cart_")]')

# 方法2：通过按钮文本+父元素关系定位（更稳定）
button = driver.find_element_by_xpath('//div[contains(@data-testid, "product-card")]//button[text()="Add to Cart"]')

# 方法3：使用CSS选择器+XPath组合（Selenium特有）
from selenium.webdriver.common.by import By
button = driver.find_element(By.XPATH, '//div[contains(@data-testid, "product-card")]')
                        .find_element(By.CSS_SELECTOR, 'button[data-testid^="add-to-cart_"]')

product_name = "Smartphone X"
xpath_template = '//div[contains(@class, "product") and ./h3[text()="{name}"]]'
xpath = xpath_template.format(name=product_name)
element = driver.find_element_by_xpath(xpath)

# 精确匹配可能包含换行符的文本
element = driver.find_element_by_xpath('//div[normalize-space()="Total: $199"]')

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

# 显式等待元素出现
element = WebDriverWait(driver, 10).until(
    EC.presence_of_element_located((By.XPATH, '//div[contains(@id, "dynamic-")]'))
)

# 使用JavaScript穿透Shadow DOM（Selenium 4+）
shadow_host = driver.find_element_by_css_selector('#shadow-host')
shadow_content = driver.execute_script("return arguments[0].shadowRoot", shadow_host)
element = shadow_content.find_element_by_xpath('//div[@class="target"]')