import pprint import requests import re import jsonsession = requests.session() url = '你需要爬取的音视频网址' headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36 Edg/106.0.1370.37', "Referer": "https://www.bilibili.com"} resp = session.get(url,headers=headers) print(resp.text)title = re.findall(r'<title>(.*?)_哔哩哔哩_bilibili',resp.text)[0] play_info = re.findall(r'<script>window.__playinfo__=(.*?)</script>',resp.text)[0]'''print(title) print(play_info,type(play_info)) ''' json_data = json.loads(play_info) pprint.pprint(json_data) #格式化输出，便于观看 audio_url = json_data['data']['dash']['audio'][0]['backupUrl'][0] #音频地址 [0]清晰度最高 video_url = json_data['data']['dash']['video'][0]['backupUrl'][0] #视频地址 audio_content = session.get(audio_url,headers=headers).content #音频二进制内容 video_content = session.get(video_url,headers=headers).content #视频二进制内容 with open(r'E:\常用文件夹\某站爬虫\【音频】'+title+'.mp3','wb') as f:f.write(audio_content) with open(r'E:\常用文件夹\某站爬虫\【视频】'+title+'.mp4','wb') as f:f.write(video_content)