使用BeautifulSoup选择多个属性

<div class="container">
    <a href="https://example.com" class="link">Example</a>
    <a href="https://example2.com" class="link special">Example2</a>
</div>

from bs4 import BeautifulSoup

html_doc = """
<div class="container">
    <a href="https://example.com" class="link">Example</a>
    <a href="https://example2.com" class="link special">Example2</a>
</div>
"""

soup = BeautifulSoup(html_doc, 'html.parser')

# 选择所有 class 包含 "link" 的 a 标签
links = soup.find_all('a', class_='link')

for link in links:
    print(link['href'])  # 输出: https://example.com 和 https://example2.com

# 选择同时具有 class="link" 和 class="special" 的 a 标签
special_links = soup.find_all('a', {'class': ['link', 'special']})

for link in special_links:
    print(link['href'])  # 输出: https://example2.com

soup = BeautifulSoup(html_doc, 'lxml')

import re

# 使用正则表达式匹配包含特定文本的 class 属性
pattern = re.compile(r'special')
special_links = soup.find_all('a', class_=pattern)