爬取B站视频

最新推荐文章于 2024-04-30 19:24:04 发布

月下之颖

最新推荐文章于 2024-04-30 19:24:04 发布

阅读量345

点赞数 7

文章标签： python

本文链接：https://blog.csdn.net/weixin_43407838/article/details/135743062

版权

import requests
import re
import json
from lxml import etree


def bilibili_download(url):
    headers = {
        "Referer": "https://www.bilibili.com/",
        "User-Agent": '请求头'}

    r = requests.get(headers=headers, url=url)

    filename_data = etree.HTML(r.text)
    print("开始下载....")
    filename = filename_data.xpath("//h1/@title")[0].replace(" ", "")
    print(filename)

    html_data = re.findall(r"window.__playinfo__=(.*?)</script>", r.text)[0]

    json_data = json.loads(html_data)

    video_url = json_data["data"]["dash"]["video"][0]["baseUrl"]
    audio_url = json_data["data"]["dash"]["audio"][0]["baseUrl"]

    video_data = requests.get(url=video_url, headers=headers).content
    audio_data = requests.get(url=audio_url, headers=headers).content

    with open(fr"./video/{filename}.mp4", 'wb') as f:
        f.write(video_data)

    with open(fr"./video/{filename}.mp3", 'wb') as f:
        f.write(audio_data)

    print("完成下载....")


if __name__ == '__main__':

    url = r"B站视频网址"
    bilibili_download(url)

自己添加一个请求头就行