爬取b站音视频以及合并弹幕

废话不多说，直接上源码

需要用到ffmpeg合并音视频，以及合并弹幕
还需要下载danmaku2ass
链接: link.
提取码：xx2t
关于danmaku2ass的使用，直接把下载好的xml格式的弹幕文件拖入danmaku中等几秒就可以生成ass格式的文件了。
需要注意的是使用ffmpeg的时候，很容易出现路径错误，找不到文件之类的，那是因为音视频以及弹幕文件的命名，不能有空格，路径中都不能出现空格，

import requests
import re
import json
import os



class BilibiliPro():
    def __init__(self):
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36 Edg/87.0.664.66',

        }
        self.BV = input('输入*：')

    def my_match(self, text, pattern):
        match = re.search(pattern, text)
        # print(match.group(1))
        # print()
        return json.loads(match.group(1))

    def download_video(self, old_video_url, video_url, audio_url, video_name):
        self.headers.update({"Referer": old_video_url})
        print("开始下载视频：%s" % video_name)
        video_content = requests.get(video_url, headers=self.headers)
        print('%s视频大小：' % video_name, video_content.headers['content-length'])
        audio_content = requests.get(audio_url, headers=self.headers)
        print('%s音频大小：' % video_name, audio_content.headers['content-length'])
        # 下载视频开始
        received_video = 0
        with open('%s_video.mp4' % video_name, 'ab') as output:
            while int(video_content.headers['content-length']) > received_video:
                self.headers['Range'] = 'bytes=' + str(received_video) + '-'
                response = requests.get(video_url, headers=self.headers)
                output.write(response.content)
                received_video += len(response.content)
        # 下载视频结束
        # 下载音频开始
        received_audio = 0
        with open('%s_audio.mp4' % video_name, 'ab') as output:
            while int(audio_content.headers['content-length']) > received_audio:
                # 视频分片下载
                self.headers['Range'] = 'bytes=' + str(received_audio) + '-'
                response = requests.get(audio_url, headers=self.headers)
                output.write(response.content)
                received_audio += len(response.content)
        # 下载音频结束
        return video_name

    def get_oid(self, url):
        # 获取cid
        response = requests.get(url=url, headers=self.headers)
        match_cid = 'cid=(.*?)&aid'
        return re.search(match_cid, response.text).group().replace('cid=', '').replace('&aid', '')

    def get_danmu(self, cid, video_name):
        # 获取弹幕的同时保存xml，为后期视频合并弹幕作准备
        url = 'https://api.bilibili.com/x/v1/dm/list.so?oid={}'.format(cid)
        R = "<d.*?>(.*?)</d>"
        response = requests.get(url=url, headers=self.headers)
        response.encoding = 'utf-8'
        with open('./%s.xml' % video_name, 'w', encoding='utf-8') as f:
            f.write(response.text)
        danmus = re.findall(R, response.text)
        return danmus

    def save(self, video_name, cid):
        # 将弹幕一条一条存放在csv文件中
        with open('./%s.csv' % video_name, 'w', encoding='utf-8') as fp:
            for i in self.get_danmu(cid, video_name):
                fp.write(i + '\n')


if __name__ == '__main__':
    bilibili = BilibiliPro()
    url = 'https://www.bilibili.com/video/{}'.format(bilibili.BV)
    cid = bilibili.get_oid(url)  # 获取Cid
    # bilibili.get_danmu(cid) # 爬取弹幕
    response = requests.get(url=url, headers=bilibili.headers)
    playinfo = bilibili.my_match(response.text, '__playinfo__=(.*?)</script><script>')
    initial_state = bilibili.my_match(response.text, r'__INITIAL_STATE__=(.*?);\(function\(\)')
    video_url = playinfo['data']['dash']['video'][0]['baseUrl']
    # 取出音频地址
    audio_url = playinfo['data']['dash']['audio'][0]['baseUrl']
    video_name = initial_state['videoData']['title']
    video_name = video_name.replace(' ', "") # 去除名字中的空格
    bilibili.save(video_name, cid)  # 存储弹幕
    print('视频名字为：', video_name)
    print('视频地址为：', video_url)
    print('音频地址为：', audio_url)
    bilibili.download_video(url, video_url, audio_url, video_name)
    audio = r'D:\\Users\\Lenovo\\PycharmProjects\\bilibili\\%s_audio.mp4' % video_name
    video = r'D:\\Users\\Lenovo\\PycharmProjects\\bilibili\\%s_video.mp4' % video_name
    COMMAND = f'E:\\FFmpeg\\ffmpeg-N\\bin\\ffmpeg -i {video} -i {audio} -c:v copy -c:a aac -strict experimental {video_name}.mp4'
    os.system(COMMAND)
    # 为视频添加弹幕
    # Merged_video = 'D:\\Users\\Lenovo\\PycharmProjects\\bilibili\\%s.mp4'%video_name
    # ass = '../bilibili/danmaku/PGONE发布新曲，疯狂Diss自己进行忏悔？《KILLTHEONE》.ass'
    # command = f'E:\\FFmpeg\\ffmpeg-N\\bin\\ffmpeg -i {Merged_video} -vf subtitles={ass} -vcodec libx264  pgone.mp4'