第一种:

正则:

r = session.get(the_url, headers=header)
        res = r.json()
        city_list = jsonpath.jsonpath(res, "$..text")#"$..name"取所有k=name的v
        for name in city_list:
            name=name.translate(non_bmp_map)
            tags = re.compile('<.*?>',re.S)
            name=tags.sub('',name)

第二种:

借助 pyquery 将正文中的 HTML 标签去掉:

html = '''
<div class="wrap">
    <div id="container">
        <ul class="list">
             <li class="item-0">first item</li>
             <li class="item-1"><a href="link2.html">second item</a></li>
             <li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
             <li class="item-1 active"><a href="link4.html">fourth item</a></li>
             <li class="item-0"><a href="link5.html">fifth item</a></li>
         </ul>
     </div>
 </div>
'''
from pyquery import PyQuery as pq
doc = pq(html)
a = doc('.item-0.active a')
print(a)
print(a.text())