Python使用XPath进行正则表达式匹配的实战指南

<!-- 动态ID示例 -->
<div id="user-profile-1648927365"></div>
<div id="user-profile-1648927402"></div>
<!-- 随机类名示例 -->
<button class="btn-primary btn-3a7b2c"></button>
<button class="btn-primary btn-8d4f1e"></button>

# 传统contains匹配（部分包含）
driver.find_element(By.XPATH, '//div[contains(@id, "user-profile")]')

# 正则匹配（精确模式）
driver.find_element(By.XPATH, '//div[matches(@id, "^user-profile-\d+$")]')

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

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

# 匹配动态ID（Chrome扩展语法）
element = driver.find_element(
    By.XPATH, 
    '//div[starts-with(@id, "temp-") and contains(@id, "-container")]'
    # 或尝试（部分浏览器支持）：
    # '//div[@id=regexp:"temp-.*-container"]'
)

import re
from selenium import webdriver

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

# 获取所有div元素
divs = driver.find_elements(By.XPATH, '//div')

# 使用Python正则筛选
target_div = None
for div in divs:
    if re.match(r'^user-profile-\d+$', div.get_attribute('id')):
        target_div = div
        break

from lxml import html
import requests

# 获取网页内容
page = requests.get("https://example.com")
tree = html.fromstring(page.content)

# 使用XPath 3.0正则匹配
elements = tree.xpath('//div[matches(@id, "^user-profile-\d+$")]')
for el in elements:
    print(el.text_content())

<ul class="products">
  <li data-product-id="prod_7a3b9c2e">iPhone 13</li>
  <li data-product-id="prod_4d8f1a7b">MacBook Pro</li>
</ul>

products = driver.find_elements(By.XPATH, '//li[starts-with(@data-product-id, "prod_")]')
for product in products:
    product_id = re.search(r'prod_([a-f0-9]+)', product.get_attribute('data-product-id')).group(1)
    print(f"商品ID: {product_id}, 名称: {product.text}")

<button class="submit-btn btn-202304151200">提交</button>
<button class="submit-btn btn-202304160930">提交</button>

# 方法1：使用contains()组合
buttons = driver.find_elements(By.XPATH, '//button[contains(@class, "submit-btn") and contains(@class, "btn-")]')

# 方法2：Python正则处理
buttons = driver.find_elements(By.XPATH, '//button[contains(@class, "submit-btn")]')
valid_buttons = [
    btn for btn in buttons 
    if re.search(r'btn-\d{8}\d{4}', btn.get_attribute('class'))
]

<div class="alert alert-error">
  <span class="code">ERR_404</span>
  页面未找到
</div>

# 匹配包含特定错误码的提示框
error_div = driver.find_element(
    By.XPATH, 
    '//div[contains(@class, "alert") and .//span[matches(@class, "code") and text()="ERR_404"]]'
)

candidates = driver.find_elements(By.XPATH, '//div[@id]')  # 先找所有带ID的div
targets = [d for d in candidates if re.match(r'^temp-\d+$', d.get_attribute('id'))]

# 优于正则的方案
driver.find_element(By.XPATH, '//input[starts-with(@name, "user_") and contains(@name, "_email")]')

import re
pattern = re.compile(r'^user-profile-\d+$')
# 使用时直接调用 pattern.match(string)

# 替代方案1：使用CSS选择器+正则组合
elements = driver.find_elements(By.CSS_SELECTOR, 'div[id^="temp-"]')
valid_elements = [el for el in elements if re.search(r'temp-\d+-container', el.get_attribute('id'))]

# 替代方案2：使用JavaScript执行XPath（高级）

<div>订单号: ORD20230415001</div>

# 方法1：XPath 2.0+（需特定环境）
# driver.find_element(By.XPATH, '//div[matches(text(), "订单号: ORD\d{11}")]')

# 方法2：Python处理
divs = driver.find_elements(By.XPATH, '//div[contains(text(), "订单号:")]')
for div in divs:
    match = re.search(r'订单号: (ORD\d{11})', div.text)
    if match:
        print("找到订单:", match.group(1))

def generate_xpath_regex(base_path, attr_name, pattern):
    """动态生成带正则的XPath
    :param base_path: 基础路径如 '//div'
    :param attr_name: 属性名如 '@id'
    :param pattern: 正则表达式字符串
    """
    # 对于支持regexp:的浏览器
    xpath_regexp = f"{base_path}[{attr_name}=regexp:'{pattern}']"
    
    # 通用方案（Python处理）
    xpath_contains = f"{base_path}[contains({attr_name}, '{pattern.split('*')[0]}')]"
    
    return {
        'regexp_syntax': xpath_regexp,
        'contains_fallback': xpath_contains
    }

# 使用示例
paths = generate_xpath_regex('//button', '@class', 'btn-submit-*')
print("扩展语法:", paths['regexp_syntax'])
print("备用方案:", paths['contains_fallback'])