import io
import sys
import requests
import re
import json

#将爬到的数据消除乱码
sys.stdout = io.TextIOWrapper(sys.stdout.buffer,encoding='utf8')

#''内填入网页url
url = 'https://api.bilibili.com/x/v1/dm/list.so?oid=1634922221'
    
headers = {
        'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 Edg/128.0.0.0'
    }
    
response = requests.get(url=url,headers=headers)
response.encoding = 'utf-8'

#将需要获取的部分改为.*?
content_list = re.findall('<d p=".*?">(.*?)</d>',response.text)
content_list = json.dumps(content_list,ensure_ascii=False,indent=2)

#将爬取到的数据写为文本
with open('output.txt', 'w', encoding='utf-8') as file:
    file.write(content_list)