import requests import re header = {"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"} url = "http://sports.news.cn/olympicparis2024/index.html" response = requests.get(url=url, headers=header) response.encoding = 'utf-8' data = response.text list1 = re.findall("blank'>(.*?)",data) list2 = re.findall('
(.*?)。',data) content = [] content.extend(list1) content.extend(list2) print(content) for i in content: # 遍历弹幕 with open('aoyun.txt', 'a', encoding='utf-8') as f: # 打开文件准备写入 f.write(i + '\n') # 写入弹幕