Python网络爬虫爬取贴吧话题热议榜单(可自定义条数)

 1 import pandas as pd
 2 import requests as rq
 3 from bs4 import BeautifulSoup
 4 url="http://tieba.baidu.com/hottopic/browse/topicList?res_type=1"
 5 def res_caputure():
 6     try:
 7         res = rq.get(url,timeout=30)
 8         res.raise_for_status()
 9         res.encoding = res.apparent_encoding
10         return res.text
11     except:
12         return "发生异常,响应码为{}".format(res.status_code)
13 if __name__ == "__main__":
14     r = res_caputure()
15     soup = BeautifulSoup(r)
16     a = soup.select('a[target]')
17     p = soup.select('span')
18     soup_p=[]
19     soup_a=[]
20     s=input("输入要查看百度贴吧话题热议榜单的条数(直接回车默认为10条,最高为30):")
21     if s=='':
22         s=10
23     else:
24         s=int(s)
25     for k in range(3,s*2+3,2):
26         soup_p.append(p[k].string)
27     for i in range(0,s):
28         soup_a.append(a[i].string)
29     dt={'排名':range(1,s+1),'标题':soup_a,'内容数':soup_p}
30     df=pd.DataFrame(dt)
31     print(df)

可自定义查看条数,按回车确定,不输入默认为10条

演示如下:

标签：__,10,30,自定义,Python,res,热议,soup,import
来源： https://www.cnblogs.com/chargecrystal/p/12540150.html