对于页面
<div class="container navigation">
<div class="row">
<div class="col nav">
<ul class="pc-nav" id="runoob-detail-nav">
<li><a href="//www.runoob.com/">首页</a></li>
<li><a href="/html/html-tutorial.html">HTML</a></li>
<li><a href="/css/css-tutorial.html">CSS</a></li>
<li><a href="/js/js-tutorial.html">JavaScript</a></li>
<li><a href="javascript:void(0);" data-id="vue">Vue</a></li>
<li><a href="/react/react-tutorial.html">React</a></li>
<!--
<li><a href="/nodejs/nodejs-tutorial.html">NodeJS</a></li>-->
<li><a href="/python3/python3-tutorial.html">Python3</a></li>
<!--
<li><a href="/python/python-tutorial.html">Python2</a></li>
-->
<li><a href="/java/java-tutorial.html">Java</a></li>
<li><a href="/cprogramming/c-tutorial.html">C</a></li>
<li><a href="/cplusplus/cpp-tutorial.html">C++</a></li>
<li><a href="/csharp/csharp-tutorial.html">
C#</a></li>
<li><a href="javascript:void(0);" data-id="aiNav">AI</a></li>
<li><a href="/go/go-tutorial.html">Go</a></li>
<li><a href="/sql/sql-tutorial.html">SQL</a></li>
<li><a href="/linux/linux-tutorial.html">Linux</a></li>
<li><a href="/vscode/vscode-tutorial.html">VS Code</a></li>
<!--<li><a href="/jquery/jquery-tutorial.html">jQuery</a></li>-->
<li><a href="javascript:void(0);" data-id="bootstrap">Bootstrap</a></li>
<li><a href="/git/git-tutorial.html">Git</a></li>
<li><a href="/browser-history">本地书签</a></li><!--
<li><a href="https://www.jyshare.com/front-end/9235/" target="_blank">AI 编程助理</a></li> -->
<!--
<li><a href="/w3cnote/knowledge-start.html" style="font-weight: bold;" onclick="_hmt.push(['_trackEvent', '星球', 'click', 'start'])" title="我的圈子">我的圈子</a></li>
<li><a href="javascript:;" class="runoob-pop">登录</a></li>
-->
</ul>
<ul class="mobile-nav">
<li><a href="//www.runoob.com/">首页</a></li>
<li><a href="/html/html-tutorial.html">HTML</a></li>
<li><a href="/css/css-tutorial.html">CSS</a></li>
<li><a href="/js/js-tutorial.html">JS</a></li>
<li><a href="/browser-history">本地书签</a></li>
<li><a href="javascript:void(0)" class="search-reveal">Search</a> </li>
</ul>
</div>
</div>
</div>
识别到的结果
C:\own\app\python_code\.venv\Scripts\python.exe C:\own\app\python_code\work\入职培训\打印点击\导航栏
识别测试.py
共
识别出 8 个导航栏
导航栏 #1: <div class='container navigation'>
导航栏 #2: <div class='col nav'>
导航栏 #3: <ul class='pc-nav'>
导航栏 #4: <ul class='mobile-nav'>
导航栏 #5: <div class='container navigation'>
导航栏 #6: <div class='container navigation'>
导航栏 #7: <div class='row'>
导航栏 #8: <div class='col nav'>
Process finished with exit code 0
识别不全啊
from selenium import webdriver
from selenium.webdriver.common.by import By
driver = webdriver.Chrome()
driver.get("file:///C:/own/app/python_code/work/入职培训/打印点击/111.html")
def is_navigation_bar(element, max_depth=5, current_depth=0):
try:
if current_depth > max_depth:
return False
if element.tag_name.lower() == 'nav':
return True
role = element.get_attribute('role')
if role and role.lower() == 'navigation':
return True
class_name = element.get_attribute('class')
if class_name:
class_name = class_name.lower()
if any(keyword in class_name for keyword in ['nav', 'navbar', 'navigation', 'menu', 'bar']):
return True
if contains_navigation_structure(element):
return True
try:
parent = element.find_element(By.XPATH, '..')
return is_navigation_bar(parent, max_depth, current_depth + 1)
except:
return False
except Exception as e:
print(f"[导航栏
识别] 出错: {e}")
return False
def contains_navigation_structure(element):
"""增强结构
识别：查找是否有多个 <a>、<p> 或 <li>，支持深层嵌套结构"""
links = element.find_elements(By.XPATH, './/a | .//p | .//li')
link_count = 0
for el in links:
if el.tag_name == 'a':
href = el.get_attribute('href')
if href and href != 'javascript:void(0);':
link_count += 1
elif el.tag_name in ['p', 'li']:
text = el.text.strip()
if text:
link_count += 1
if link_count >= 2:
return True
lists = element.find_elements(By.XPATH, './/ul | .//ol')
if len(lists) >= 1:
return True
return False
# ✅ 使用 CSS 选择器查找所有可能的候选
元素
def find_all_navigation_bars(driver):
candidates = []
# 1. 查找 <nav> 标签
nav_elements = driver.find_elements(By.TAG_NAME, 'nav')
candidates.extend(nav_elements)
# 2. 查找 role="navigation"
role_navs = driver.find_elements(By.XPATH, '//*[@role="navigation"]')
candidates.extend(role_navs)
# 3. 查找常见 class 名称的
元素
class_keywords = ['nav', 'navbar', 'navigation', 'menu', 'bar']
for keyword in class_keywords:
elements = driver.find_elements(By.CSS_SELECTOR, f'[class*="{keyword}"]')
candidates.extend(elements)
# 4. 查找包含 ul/li 结构的容器
list_containers = driver.find_elements(By.XPATH, '//div[.//ul] | //div[.//ol] | //nav[.//ul] | //nav[.//ol]')
candidates.extend(list_containers)
# 去重 + 筛选
unique_candidates = []
seen = set()
for el in candidates:
id_ = id(el)
if id_ not in seen:
seen.add(id_)
if is_navigation_bar(el):
unique_candidates.append(el)
return unique_candidates
# ✅ 主程序入口
nav_bars = find_all_navigation_bars(driver)
print(f"共
识别出 {len(nav_bars)} 个导航栏")
for i, nav in enumerate(nav_bars):
try:
tag = nav.tag_name
class_name = nav.get_attribute('class')
print(f"导航栏 #{i+1}: <{tag} class='{class_name}'>")
except Exception as e:
print(f"导航栏 #{i+1}:
无法获取信息", e)
driver.quit()
扫一扫
5962
到【灌水乐园】发言
