擅长:python、mysql、java
<pre><code>import bs4
html = '''
<div att0="content1">
<a href="link1">link data</a>
</div>
<div att0="content1">
<a href="link1">link data</a>
</div>
<div att0="content1">
<a href="link1">link data</a>
</div>'''
soup = bs4.BeautifulSoup(html, 'lxml')
for div in soup.find_all('div', att0=True):
out = [div['att0'], div.a['href']]
print(out)
</code></pre>
<p>输出:</p>
^{pr2}$