使用属性作为ids从HTML div创建Python字典

pip install beautifulsoup4

from bs4 import BeautifulSoup

# 假设HTML文档存储在html变量中
html = '''
<div id="div1" class="class1" data-attr="value1">Content 1</div>
<div id="div2" class="class2" data-attr="value2">Content 2</div>
<div id="div3" class="class3" data-attr="value3">Content 3</div>
'''

# 创建BeautifulSoup对象
soup = BeautifulSoup(html, 'html.parser')

# 创建空字典
div_dict = {}

# 查找所有div元素
div_elements = soup.find_all('div')

# 遍历div元素
for div in div_elements:
    # 获取id属性值
    div_id = div.get('id')
    
    # 获取class属性值
    div_class = div.get('class')
    
    # 获取data-attr属性值
    div_data_attr = div.get('data-attr')
    
    # 将属性和值存储在字典中
    div_dict[div_id] = {
        'class': div_class,
        'data-attr': div_data_attr,
        'content': div.text
    }

# 打印字典
print(div_dict)

{
    'div1': {
        'class': ['class1'],
        'data-attr': 'value1',
        'content': 'Content 1'
    },
    'div2': {
        'class': ['class2'],
        'data-attr': 'value2',
        'content': 'Content 2'
    },
    'div3': {
        'class': ['class3'],
        'data-attr': 'value3',
        'content': 'Content 3'
    }
}