Initial commit: Bilibili Video Downloader v1.0.0

2026-08-28 10:12:20 +08:00
commit 7d08658757
5 changed files with 911 additions and 0 deletions
@@ -0,0 +1,385 @@
+import requests
+import time
+import hashlib
+import urllib.parse
+import json
+import os
+import subprocess
+from typing import Dict, List
+
+sessdata = '填写你的Cookie'
+class BilibiliAutoDownloader:
+    def __init__(self, ffmpeg_path="D:\\ff\\ffmpeg.exe"):
+        self.sessdata = sessdata
+        self.session = requests.Session()
+        self.ffmpeg_path = ffmpeg_path
+        
+        # 设置完整的cookie和headers，模拟真实浏览器
+        self.session.headers.update({
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
+            'Referer': 'https://www.bilibili.com',
+            'Origin': 'https://www.bilibili.com',
+            'Accept': 'application/json, text/plain, */*',
+            'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
+            'Accept-Encoding': 'gzip, deflate, br',
+            'Cache-Control': 'no-cache',
+            'Priority': 'u=1, i'
+        })
+        
+        if sessdata:
+            self.session.cookies.set('SESSDATA', sessdata, domain='.bilibili.com')
+            # 设置其他必要的cookies
+
+    def get_video_info(self, bvid: str) -> Dict:
+        """获取视频信息"""
+        api_url = "https://api.bilibili.com/x/web-interface/view"
+        params = {'bvid': bvid}
+        response = self.session.get(api_url, params=params)
+        return response.json()
+
+    def _get_wbi_keys(self) -> tuple:
+        """获取WBI加密密钥"""
+        nav_url = "https://api.bilibili.com/x/web-interface/nav"
+        response = self.session.get(nav_url)
+        data = response.json()
+        
+        if data['code'] == 0:
+            img_url = data['data']['wbi_img']['img_url']
+            sub_url = data['data']['wbi_img']['sub_url']
+            
+            img_key = img_url.split('/')[-1].split('.')[0]
+            sub_key = sub_url.split('/')[-1].split('.')[0]
+            return img_key, sub_key
+        return None, None
+
+    def _wbi_sign(self, params: Dict) -> Dict:
+        """WBI签名算法"""
+        img_key, sub_key = self._get_wbi_keys()
+        if not img_key or not sub_key:
+            return params
+            
+        mixin_key = [
+            46, 47, 18, 2, 53, 8, 23, 32, 15, 50, 10, 31, 58, 3, 45, 35, 27, 43, 5, 49,
+            33, 9, 42, 19, 29, 28, 14, 39, 12, 38, 41, 13, 37, 48, 7, 16, 24, 55, 40,
+            61, 26, 17, 0, 1, 60, 51, 30, 4, 22, 25, 54, 21, 56, 59, 6, 63, 57, 62, 11,
+            36, 20, 34, 44, 52
+        ]
+        
+        # 添加时间戳
+        params['wts'] = int(time.time())
+        
+        # 参数排序并过滤
+        params = {k: ''.join(filter(str.isalnum, str(v))) for k, v in params.items() 
+                 if k not in ['sign', 'csrf'] and v != ''}
+        params = dict(sorted(params.items()))
+        
+        # 生成待签名字符串
+        query = urllib.parse.urlencode(params)
+        
+        # 应用mixin_key
+        mixed = []
+        for key in mixin_key:
+            if key < len(query):
+                mixed.append(query[key])
+        mixed_str = ''.join(mixed)[:32]
+        
+        # 生成w_rid
+        w_rid = hashlib.md5((query + mixed_str).encode()).hexdigest()
+        params['w_rid'] = w_rid
+        
+        return params
+
+    def get_play_url_mp4(self, bvid: str, cid: int) -> Dict:
+        """获取MP4格式的播放地址（非DASH）"""
+        # 先获取avid
+        video_info = self.get_video_info(bvid)
+        if not video_info or video_info.get('code') != 0:
+            return None
+        avid = video_info['data']['aid']
+        
+        # 构建参数 - 不使用DASH格式
+        params = {
+            'qn': 112,  # 高清1080P
+            'fnval': 0,  # 设置为0表示不使用DASH格式
+            'fourk': 1,
+            'voice_balance': 1,
+            'gaia_source': 'pre-load',
+            'isGaiaAvoided': 'true',
+            'avid': avid,
+            'bvid': bvid,
+            'cid': cid,
+            'web_location': '1315873',
+        }
+        
+        # 应用WBI签名
+        signed_params = self._wbi_sign(params)
+        
+        # 使用原生API端点
+        api_url = "https://api.bilibili.com/x/player/wbi/playurl"
+        
+        response = self.session.get(api_url, params=signed_params)
+        return response.json()
+
+    def find_best_mp4_url(self, vajson: Dict) -> tuple:
+        """找到最高质量的MP4视频URL"""
+        if 'data' not in vajson or 'durl' not in vajson['data']:
+            return None, None
+        
+        durls = vajson['data']['durl']
+        
+        if not durls:
+            return None, None
+        
+        # 获取视频质量信息
+        quality = vajson['data'].get('quality', 0)
+        format_info = vajson['data'].get('format', '')
+        description = vajson['data'].get('accept_description', [])
+        
+        print(f"🎯 找到 {len(durls)} 个MP4视频片段")
+        print(f"📊 视频质量: {quality} - {format_info}")
+        if description:
+            print(f"📋 可用质量: {', '.join(description)}")
+        
+        # 如果有多个片段，选择第一个（通常是完整的视频）
+        best_durl = durls[0]
+        video_url = best_durl.get('url', '')
+        backup_urls = best_durl.get('backup_url', [])
+        size = best_durl.get('size', 0)
+        
+        print(f"🔥 选择视频片段 - 大小: {size/(1024*1024):.2f}MB")
+        
+        # 测试主URL
+        if self.test_url_content(video_url):
+            print(f"✅ 主视频URL可用")
+            return video_url, f"MP4-{quality}"
+        
+        # 测试备用URL
+        for i, backup_url in enumerate(backup_urls):
+            if self.test_url_content(backup_url):
+                print(f"✅ 备用视频URL {i+1} 可用")
+                return backup_url, f"MP4-{quality}"
+        
+        return None, None
+
+    def test_url_content(self, url: str, min_size: int = 1024) -> bool:
+        """测试URL是否返回有效内容"""
+        try:
+            headers = {
+                'Range': 'bytes=0-8191',
+                'Referer': 'https://www.bilibili.com',
+                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
+            }
+            
+            response = self.session.get(url, headers=headers, timeout=10, stream=True)
+            
+            if response.status_code not in [200, 206]:
+                return False
+            
+            content_length = response.headers.get('content-length')
+            if content_length and int(content_length) < min_size:
+                return False
+            
+            return True
+            
+        except Exception:
+            return False
+
+    def download_with_aria2(self, url: str, filename: str, file_type: str):
+        """使用aria2多线程下载"""
+        print(f"🚀 开始高速下载{file_type}")
+        
+        cmd = [
+            'aria2c',
+            '-x', '16',
+            '-s', '16',
+            '-k', '1M',
+            '--header=Referer: https://www.bilibili.com',
+            '--check-certificate=false',
+            '--continue=true',
+            '--max-tries=5',
+            '--retry-wait=3',
+            '-o', filename,
+            url
+        ]
+        
+        try:
+            result = subprocess.run(cmd, capture_output=True)
+            if result.returncode == 0:
+                print(f"✅ {file_type}下载完成")
+                return True
+            else:
+                return False
+        except FileNotFoundError:
+            return False
+
+    def download_fast_python(self, url: str, filename: str, file_type: str):
+        """Python多线程下载"""
+        import threading
+        from concurrent.futures import ThreadPoolExecutor
+        
+        print(f"🚀 开始多线程下载{file_type}")
+        
+        def download_chunk(start_byte, end_byte, chunk_id):
+            headers = {
+                'Range': f'bytes={start_byte}-{end_byte}',
+                'Referer': 'https://www.bilibili.com',
+                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
+            }
+            
+            try:
+                response = self.session.get(url, headers=headers, stream=True, timeout=30)
+                with open(f"{filename}.part{chunk_id}", 'wb') as f:
+                    for chunk in response.iter_content(chunk_size=8192):
+                        f.write(chunk)
+                return True
+            except Exception:
+                return False
+        
+        try:
+            response = self.session.head(url, headers={'Referer': 'https://www.bilibili.com'})
+            total_size = int(response.headers.get('content-length', 0))
+        except:
+            total_size = 0
+        
+        if total_size == 0:
+            return self.download_single(url, filename, file_type)
+        
+        num_threads = 8
+        chunk_size = total_size // num_threads
+        
+        with ThreadPoolExecutor(max_workers=num_threads) as executor:
+            futures = []
+            for i in range(num_threads):
+                start_byte = i * chunk_size
+                end_byte = start_byte + chunk_size - 1 if i < num_threads - 1 else total_size - 1
+                futures.append(executor.submit(download_chunk, start_byte, end_byte, i))
+            
+            results = [f.result() for f in futures]
+        
+        if all(results):
+            with open(filename, 'wb') as outfile:
+                for i in range(num_threads):
+                    with open(f"{filename}.part{i}", 'rb') as infile:
+                        outfile.write(infile.read())
+                    os.remove(f"{filename}.part{i}")
+            print(f"✅ {file_type}下载完成")
+            return True
+        else:
+            return False
+
+    def download_single(self, url: str, filename: str, file_type: str):
+        """单线程下载"""
+        print(f"📥 开始下载{file_type}")
+        
+        max_retries = 3
+        for attempt in range(max_retries):
+            try:
+                headers = {
+                    'Referer': 'https://www.bilibili.com',
+                    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
+                }
+                
+                response = self.session.get(url, headers=headers, stream=True, timeout=30)
+                total_size = int(response.headers.get('content-length', 0))
+                downloaded = 0
+                
+                with open(filename, 'wb') as f:
+                    for chunk in response.iter_content(chunk_size=8192):
+                        if chunk:
+                            f.write(chunk)
+                            downloaded += len(chunk)
+                            if total_size > 0:
+                                percent = (downloaded / total_size) * 100
+                                print(f"\r📊 下载进度: {percent:.1f}%", end='', flush=True)
+                
+                if os.path.exists(filename) and os.path.getsize(filename) > 1024:
+                    print(f"\n✅ {file_type}下载完成")
+                    return True
+                else:
+                    if os.path.exists(filename):
+                        os.remove(filename)
+                
+            except Exception:
+                if os.path.exists(filename):
+                    os.remove(filename)
+        
+        return False
+
+    def download_and_merge(self, bvid: str):
+        """主下载函数 - 直接下载MP4格式"""
+        bvid = bvid.rstrip('/')
+        print(f"🚀 开始处理视频: {bvid}")
+        
+        # 获取视频信息
+        video_info = self.get_video_info(bvid)
+        if not video_info or video_info.get('code') != 0:
+            print("❌ 无法获取视频信息")
+            return
+        
+        data = video_info['data']
+        cid = data['cid']
+        title = data['title']
+        print(f"📺 视频标题: {title}")
+        print(f"🔢 视频CID: {cid}")
+        
+        # 使用MP4 API获取播放信息
+        vajson = self.get_play_url_mp4(bvid, cid)
+        if not vajson or vajson.get('code') != 0:
+            print("❌ 无法获取MP4播放信息")
+            return
+        
+        print("✅ 成功获取MP4播放信息")
+        
+        # 找到MP4视频URL
+        video_url, quality_info = self.find_best_mp4_url(vajson)
+        if not video_url:
+            print("❌ 没有可用的MP4视频URL")
+            return
+        
+        print(f"🎬 已选择MP4视频 - 质量: {quality_info}")
+        
+        # 生成安全的文件名
+        safe_title = "".join(c for c in title if c.isalnum() or c in ('-', '_')).rstrip()
+        if not safe_title:
+            safe_title = "video"
+        
+        output_file = f"{safe_title}.mp4"
+        
+        # 选择下载方式
+        download_methods = [
+            ('aria2', self.download_with_aria2),
+            ('多线程', self.download_fast_python),
+            ('单线程', self.download_single)
+        ]
+        
+        # 直接下载MP4文件
+        video_success = False
+        for method_name, method_func in download_methods:
+            print(f"\n尝试使用 {method_name} 下载MP4视频...")
+            if method_func(video_url, output_file, "MP4视频"):
+                video_success = True
+                break
+        
+        if video_success:
+            print(f"\n🎉 下载完成!")
+            print(f"📹 最终文件: {output_file}")
+            print(f"🔧 视频格式: {quality_info}")
+            
+            if os.path.exists(output_file):
+                file_size = os.path.getsize(output_file)
+                print(f"📁 文件大小: {file_size / (1024*1024):.2f} MB")
+        else:
+            print("❌ 下载失败")
+
+# 🎯 主程序
+if __name__ == "__main__":
+    downloader = BilibiliAutoDownloader(ffmpeg_path=r"D:\ff\ffmpeg.exe")
+    
+    try:
+        bvid = input("📥 请输入BV号: ").strip()
+        if bvid:
+            downloader.download_and_merge(bvid)
+    except Exception as e:
+        print(f"💥 程序执行失败: {e}")
+        import traceback
+        traceback.print_exc()