Python爬虫 beautifulsoup4解析html数据

pip install beautifulsoup4

from bs4 import BeautifulSoup

...
response = requests.get(url,  headers={'User-Agent':random.choice(userAgent)})

"""        
		<div class="sonspic">
               <div class="cont" style="margin-top:13px;">
                <p style="height:22px;">
                   <a target="_blank" style="font-size:18px; line-height:22px; height:22px;" href="/xxx/book_46653FD803893E4F93E5C6C3.aspx"><b>尚书</b></a>
                </p>
               </div>
        </div>
"""
        
soup = BeautifulSoup(response.text, 'html.parser')
st = soup.find_all(attrs={"class": "sonspic"})
for i in st:	
    text = i.select('a')[0].get_text()
    # "尚书"
    url = i.select('a')[0].get('href')
    # "/xxx/book_46653FD803893E4F93E5C6C3.aspx"

Tag类型可以直接转换为字符串。

st = soup.find_all(attrs={"class": "sonspic"})
print(type(st)) # <class 'bs4.element.Tag'>
print(str(st))