爬取b站用户信息

Pythonnewers

RT
可爬取"mid",'名字','性别','头像地址','等级','大会员'

1. import requests
   
2. import re
   
3. import json
   
4. from bs4 import BeautifulSoup
   
5. import xlsxwriter
   
6. import time
   
7. import random
   
8. book = xlsxwriter.Workbook(r'C:\Users\Sun\Desktop\Bilili User.xlsx')
   
9. sheet = book.add_worksheet()
   
10. word=['A','B','C','D','E','F','G','E']
    
11. oppotion=["mid",'名字','性别','头像地址','等级','大会员']
    
12. for p in range(len(oppotion)):
    
13.     l = word[p]
    
14.     sheet.write(f"{l}1",oppotion[p])
    
15. headers={"user-agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36"}
    
16. 
    
17. def excel(*x):
    
18.     for i in range(len(x)):
    
19.         l=word[i]
    
20.         sheet.write(f"{l}{ueser+2}",x[i])
    
21.     print(str(x[0])+"完成")
    
22. def mes(x):
    
23.     print(x)
    
24.     if x['code']==-404:
    
25.         return
    
26.     x=x['data']
    
27.     mid=x["mid"]
    
28.     name=x["name"]
    
29.     sex=x["sex"]
    
30.     face=x["face"]
    
31.     level=x["level"]
    
32.     vip=x['vip']['label']['text']
    
33.     excel(mid,name,sex,face,level,vip)
    
34. def req(url):
    
35.     res=requests.get(url=url,headers=headers).content.decode("utf-8")
    
36.     soup=BeautifulSoup(res,"lxml")
    
37.     dic=json.loads(soup.p.get_text())
    
38.     mes(dic)
    
39. def uid(a):
    
40.     mid=re.findall("\d+",a)[0]
    
41.     global data
    
42.     data={'mid':f'{mid}','jsonp':'jsonp'}
    
43.     url=f"https://api.bilibili.com/x/space/acc/info?mid={mid}&jsonp=jsonp"
    
44.     req(url)
    
45. def user(uesers):
    
46.     global ueser
    
47.     for ueser in range(uesers):
    
48.         url=f"https://space.bilibili.com/{ueser+1}/"
    
49.         uid(url)
    
50.         time.sleep(random.random())
    
51.     book.close()
    
52. user(100)

复制代码

↑↑↑
user这里（）写爬取多少用户（按顺序）
↑我有些打英文手滑写错了，运行后才发现拼写错误
mid应该就是uid