python下载b站视频

python下载b站视频源码参考

import time
import requests
import json
import re
from lxml import etree
from moviepy.editor import *



def merge_video_audio(video_path, audio_path):
    print('原始视频音频合并中，请耐心等待~')
    # 获取下载好的音频和视频文件
    vd = VideoFileClip(video_path)
    ad = AudioFileClip(audio_path)
    vd2 = vd.set_audio(ad)  # 将提取到的音频和视频文件进行合成
    output = video_path.replace('_video','')
    vd2.write_videofile(output)  # 输出新的视频文件

    # 移除原始的视频和音频
    os.remove(video_path)
    os.remove(audio_path)


def download_video(jump_url_list,keyword):
    # 遍历我们刚才获取到的所有跳转链接
    for jump_url in jump_url_list: # 先取一个视频进行测试
        print('正在下载：',jump_url)
        # 发送请求
        headers = {
            'Accept': '*/*',
            'Accept-Language': 'en-US,en;q=0.5',
            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36'
        }

        response = requests.get(jump_url, headers=headers)
        # 视频详情json
        match = re.search( '__playinfo__=(.*?)</script><script>',response.text)
        playinfo =  json.loads(match.group(1))

        # 视频内容json
        match = re.search( r'__INITIAL_STATE__=(.*?);\(function\(\)',response.text)
        initial_state = json.loads(match.group(1))

        # 视频分多种格式，直接取分辨率最高的视频 1080p
        video_url = playinfo['data']['dash']['video'][0]['baseUrl']
        # 取出音频地址
        audio_url = playinfo['data']['dash']['audio'][0]['baseUrl']
        title = initial_state['videoData']['title']
        print('视频名字：',title)
        # print('视频地址：', video_url)
        # print('音频地址：', audio_url)

        # 根据关键词创建文件夹
        if not os.path.exists(keyword):
            os.mkdir(keyword)

        # 下载视频
        headers.update({"Referer": jump_url})
        video_content = requests.get(video_url, headers=headers)
        received_video = 0
        video_path = f'./{keyword}/{title}_video.mp4'
        with open(video_path, 'ab') as output:
            while int(video_content.headers['content-length']) > received_video:
                headers['Range'] = 'bytes=' + str(received_video) + '-'
                response = requests.get(video_url, headers=headers)
                output.write(response.content)
                received_video += len(response.content)

        # 下载音频
        audio_content = requests.get(audio_url, headers=headers)
        received_audio = 0
        audio_path = f'./{keyword}/{title}_audio.mp4'
        with open(audio_path, 'ab') as output:
            while int(audio_content.headers['content-length']) > received_audio:
                # 视频分片下载
                headers['Range'] = 'bytes=' + str(received_audio) + '-'
                response = requests.get(audio_url, headers=headers)
                output.write(response.content)
                received_audio += len(response.content)

        # 合并视频和音频
        merge_video_audio(video_path, audio_path)
        print('********************这是一条隔离线***************************')

        time.sleep(1)  


if __name__ == '__main__':
    jump_url_list = ["https://www.bilibili.com/video/BV1Gb42177YX/"]
    download_video(jump_url_list, "ddd")