B站视频下载技术揭秘：从浏览器抓包到FFmpeg音视频合成

import requests
import re
import jsondef get_video_info(url):"""从视频链接中获取bvid和cid"""headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'}try:response = requests.get(url, headers=headers)response.raise_for_status()# 从HTML中用正则表达式提取window.__playinfo__中的信息playinfo_text = re.search(r'window.__playinfo__=({.*?})</script>', response.text)if not playinfo_text:return None, Noneplayinfo_json = json.loads(playinfo_text.group(1))cid = playinfo_json['data']['dash']['video'][0]['cid'] # 这是一个假设的路径，实际可能变化bvid = re.search(r'BV[a-zA-Z0-9]+', url).group(0)return bvid, cidexcept Exception as e:print(f"获取视频信息失败: {e}")return None, None

def get_stream_urls(bvid, cid, sessdata_cookie):"""请求playurl接口获取音视频流URL"""api_url = f"https://api.bilibili.com/x/player/playurl"params = {'bvid': bvid,'cid': cid,'fnval': 4048, # 标志位，允许返回dash格式'fourk': 1 # 请求4K画质}headers = {'User-Agent': 'Mozilla/5.0 ...','Referer': f'https://www.bilibili.com/video/{bvid}','Cookie': f'SESSDATA={sessdata_cookie}' # 关键！}response = requests.get(api_url, params=params, headers=headers)data = response.json()# 简化选择：直接选择第一个视频流和音频流video_url = data['data']['dash']['video'][0]['baseUrl']audio_url = data['data']['dash']['audio'][0]['baseUrl']return video_url, audio_url

from tqdm import tqdm # 用于显示进度条，需 pip install tqdmdef download_file(url, filename, headers):"""带进度条的下载函数"""response = requests.get(url, headers=headers, stream=True)total_size = int(response.headers.get('content-length', 0))with open(filename, 'wb') as f, tqdm(desc=filename,total=total_size,unit='iB',unit_scale=True,unit_divisor=1024,) as bar:for chunk in response.iter_content(chunk_size=1024):size = f.write(chunk)bar.update(size)

import osdef merge_video_audio(video_file, audio_file, output_file):"""使用ffmpeg合并音视频"""print("开始合并音视频...")# -c:v copy -c:a copy 表示直接复制流，不重新编码，速度极快command = f'ffmpeg -i "{video_file}" -i "{audio_file}" -c:v copy -c:a copy "{output_file}"'result = os.system(command)if result == 0:print(f"合并成功，输出文件：{output_file}")# 清理临时文件os.remove(video_file)os.remove(audio_file)else:print("合并失败，请确保已正确安装ffmpeg并将其添加至环境变量。")

# main.py
import argparseif __name__ == '__main__':parser = argparse.ArgumentParser(description="Bilibili 视频下载脚本")parser.add_argument('url', type=str, help='B站视频链接')parser.add_argument('cookie', type=str, help='你的SESSDATA Cookie值')parser.add_argument('-o', '--output', type=str, default="output.mp4", help='输出文件名')args = parser.parse_args()bvid, cid = get_video_info(args.url)if bvid and cid:video_url, audio_url = get_stream_urls(bvid, cid, args.cookie)if video_url and audio_url:print("正在下载视频流...")download_file(video_url, "video_temp.m4s", headers={'Referer': args.url})print("正在下载音频流...")download_file(audio_url, "audio_temp.m4s", headers={'Referer': args.url})merge_video_audio("video_temp.m4s", "audio_temp.m4s", args.output)