爬虫下载b站视频

#知识点
#Requests模块使用
#Json数据提取
#re模块使用
#os模块使用
#ffmpeg工具使用
import json
import os
import pprint
import re
from lxml import etree

#1.爬取视频页的网页源代码
import requests
headers={
    'referer':'https://www.bilibili.com',
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36'
}
def get_paly_url(url):
    r=requests.get(url,headers=headers)
    #2.提取视频和音频的播放地址
    info=re.findall('window.__playinfo__=(.*?)</script>',r.text)[0]
    video_url=json.loads(info)['data']['dash']['video'][0]['baseUrl']
    audio_url=json.loads(info)['data']['dash']['audio'][0]['baseUrl']
    html=etree.HTML(r.text)
    filename=html.xpath('//h1/text()')[0]
    # print(filename)
    return video_url,audio_url,filename
#3.下载并保存视频和音频
def download_files(video_url,audio_url,filename,path):
    print('开始下载音频和视频...')
    video_content=requests.get(video_url,headers=headers).content
    audio_content = requests.get(audio_url, headers=headers).content
    with open(f'{path}/{filename}.mp4','wb') as f:
        f.write(video_content)
        print('已下载视频部分')
    with open(f'{path}/{filename}.mp3', 'wb') as f:
        f.write(audio_content)
        print('已下载音频部分')

#4.合并视频和音频
#ffmpeg
def combine_files(filename,path):
    cmd=fr"D:\python学习笔记课后题\ffmpeg-7.0.1-full_build\ffmpeg-7.0.1-full_build\bin\ffmpeg -i {path}\{filename}.mp4 -i {path}\{filename}.mp3 -c:v copy -c:a aac -strict experimental {path}\output-{filename}.mp4 -loglevel quiet"
    os.system(cmd)
    print('已完成合并！')
    os.remove(f'{path}\{filename}.mp4')
    os.remove(f'{path}\{filename}.mp3')
    print('已删除多余文件！')
if __name__ == '__main__':
    path = 'D:\python学习笔记课后题\爬虫\实战\视频'
    url = 'https://www.bilibili.com/video/BV1AA4y1D7h2/?spm_id_from=333.337.search-card.all.click'
    video_url,audio_url,filename=get_paly_url(url)
    download_files(video_url, audio_url, filename, path)
    combine_files(filename, path)