import requests #导入必备神器requests import re #导入正则 url='http://www.jjwxc.net/onebook.php?novelid=109034&chapterid=1' response=requests.get(url) response.encoding='gb2312'#根据要爬的网页的编码进行编码 html=response.text #转换成文本 info=re.findall(r'<div style="clear:both;"></div>([\s\S]*)<div id="favoriteshow_3" style="display:none" align="center"></div>',html)[0] #使用正则进行匹配小说内容
print(info)#打印