爬取b站用户信息
本帖最后由 Pythonnewers 于 2021-1-17 13:14 编辑RT
可爬取"mid",'名字','性别','头像地址','等级','大会员'
import requests
import re
import json
from bs4 import BeautifulSoup
import xlsxwriter
import time
import random
book = xlsxwriter.Workbook(r'C:\Users\Sun\Desktop\Bilili User.xlsx')
sheet = book.add_worksheet()
word=['A','B','C','D','E','F','G','E']
oppotion=["mid",'名字','性别','头像地址','等级','大会员']
for p in range(len(oppotion)):
l = word
sheet.write(f"{l}1",oppotion)
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"}
def excel(*x):
for i in range(len(x)):
l=word
sheet.write(f"{l}{ueser+2}",x)
print(str(x)+"完成")
def mes(x):
print(x)
if x['code']==-404:
return
x=x['data']
mid=x["mid"]
name=x["name"]
sex=x["sex"]
face=x["face"]
level=x["level"]
vip=x['vip']['label']['text']
excel(mid,name,sex,face,level,vip)
def req(url):
res=requests.get(url=url,headers=headers).content.decode("utf-8")
soup=BeautifulSoup(res,"lxml")
dic=json.loads(soup.p.get_text())
mes(dic)
def uid(a):
mid=re.findall("\d+",a)
global data
data={'mid':f'{mid}','jsonp':'jsonp'}
url=f"https://api.bilibili.com/x/space/acc/info?mid={mid}&jsonp=jsonp"
req(url)
def user(uesers):
global ueser
for ueser in range(uesers):
url=f"https://space.bilibili.com/{ueser+1}/"
uid(url)
time.sleep(random.random())
book.close()
user(100)
↑↑↑
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{:10_266:}
mid应该就是uid
页:
[1]