使用lxml.html.clean.Cleaner清洗html

代码示例

# -*- coding: utf-8 -*-

from lxml.html.clean import Cleaner

html = """
<p cms-style="font-L">　　
    <strong>铁打的腾讯</strong>
    <a href="//n.sinaimg.cn/tech/crawl/115/w550h365/20200326/963a-irkazzv3237667.jpg" class="keyword f_st" target="_blank">
        <img src="//n.sinaimg.cn/tech/crawl/115/w550h365/20200326/963a-irkazzv3237667.jpg" alt="">
    </a>
</p>
"""

# 保存新闻的时候，很多属性不需要保存，不然会占用硬盘资源，所以只保留图片标签的src属性就行
safe_attrs = frozenset(['src'])

# a标签也不要，只保留里边的内容
remove_tags = frozenset([
    'a'
])

cleaner = Cleaner(safe_attrs=safe_attrs, remove_tags=remove_tags)
cleaned_html = cleaner.clean_html(html)
print(cleaned_html)

'''
<p>　　
    <strong>铁打的腾讯</strong>
    
        <img src="//n.sinaimg.cn/tech/crawl/115/w550h365/20200326/963a-irkazzv3237667.jpg">
    
</p>
'''

清洗之后内容简洁多了