解析库bs4及爬取示例

from bs4 import Beautiful
Soup
text = '''
<ul class="clearfix">
    <li>
        <a href="/tupian/26783.html" target="_blank">
            <img src="/uploads/allimg/210122/210154-16113205145cce.jpg" alt="解析库bs4及爬取示例" alt="动漫女孩 黑发 露肩 4k壁纸3840x2160" />
            <b>动漫女孩 黑发 露肩 4k壁</b>
        </a>
    </li>
    <li>
        <a href="/tupian/26780.html" target="_blank">
            <img src="/uploads/allimg/210122/195550-1611316550c9d7.jpg" alt="解析库bs4及爬取示例" alt="古风 美少女 伞 长发 女孩大长腿4k唯美动漫壁纸" />
            <b>古风 美少女 伞 长发 女</b>
        </a>
    </li>
    <li>
        <a href="/tupian/24695.html" target="_blank">
            <img src="/uploads/allimg/190824/212516-1566653116f355.jpg" alt="解析库bs4及爬取示例" alt="下午 趴在桌子的女孩4k动漫壁纸3840x2160" />
            <b>下午 趴在桌子的女孩4k动</b>
        </a>
    </li>
</ul>
'''
soup = BeautifulSoup(text,'lxml')   # 需要安装lxml库哦

# 方法二
print(type(soup.ul.descendants))
for child in soup.ul.descendants:
    print(child)from bs4 import BeautifulSoup
text = '''
<ul class="clearfix">
    <li>
        <a class="hello" href="/tupian/26783.html" target="_blank">你好</a>
        <a class="white" href="/tupian/26783.html" target="_blank">白菜</a>
        <a class="white" href="/tupian/26783.html" target="_blank">白菜</a>
        <a class="white" href="/tupian/26783.html" target="_blank">白菜</a>
        <a class="white" href="/tupian/26783.html" target="_blank">白菜</a>
        <a class="black" href="/tupian/26783.html" target="_blank">黑彩</a>
    </li>
</ul>
'''
soup = BeautifulSoup(text,'lxml')   # 需要安装lxml库哦
# 筛选出白菜
result_list = soup.find_all('a',attrs={'class':'white'})
print(type(result_list))
print('-'*50)
for result in result_list:
    print(result)