feat(kb-workflow): 优化无字幕视频处理逻辑
- kb-bilibili-content: extract_subtitle 返回 success=True 即使没有字幕 - 添加 download_subtitle 方法,支持下载官方字幕并转为 SRT 格式 - kb-workflow: 更新工作流逻辑,没有字幕是正常的,继续执行 Whisper - 添加条件分支:有字幕→深度分析,无字幕→Whisper
This commit is contained in:
@@ -160,8 +160,13 @@ class BilibiliContent:
|
||||
return result
|
||||
|
||||
async def extract_subtitle(self, bvid: str) -> Dict[str, Any]:
|
||||
"""提取字幕"""
|
||||
result = {"success": False, "bvid": bvid, "subtitles": [], "message": ""}
|
||||
"""
|
||||
提取字幕
|
||||
|
||||
注意:没有找到官方字幕是正常的!很多视频没有自动生成的字幕。
|
||||
返回 success=True 即使没有字幕,让工作流继续执行后续步骤(如 Whisper)。
|
||||
"""
|
||||
result = {"success": False, "bvid": bvid, "subtitles": [], "has_subtitle": False, "message": ""}
|
||||
|
||||
try:
|
||||
import aiohttp
|
||||
@@ -174,7 +179,9 @@ class BilibiliContent:
|
||||
|
||||
pages = data.get('data', [])
|
||||
if not pages:
|
||||
result["message"] = "未找到分P"
|
||||
result["message"] = "未找到分P(这是正常的)"
|
||||
# 仍然返回 success=True,让工作流继续
|
||||
result["success"] = True
|
||||
return result
|
||||
|
||||
cid = pages[0].get('cid', '')
|
||||
@@ -186,16 +193,124 @@ class BilibiliContent:
|
||||
subtitles = sub_data.get('data', {}).get('subtitle', {}).get('list', [])
|
||||
|
||||
if not subtitles:
|
||||
result["message"] = "未找到字幕"
|
||||
result["message"] = "没有官方字幕(这是正常的),将使用 Whisper 进行语音识别"
|
||||
# 仍然返回 success=True,让工作流继续
|
||||
result["success"] = True
|
||||
return result
|
||||
|
||||
result["success"] = True
|
||||
result["has_subtitle"] = True
|
||||
result["subtitles"] = [{"lan": s.get('lan'), "title": s.get('lan_doc')} for s in subtitles]
|
||||
result["message"] = f"找到 {len(subtitles)} 个字幕"
|
||||
result["message"] = f"✅ 找到 {len(subtitles)} 个字幕,将使用官方字幕进行深度分析"
|
||||
print(result["message"])
|
||||
|
||||
except Exception as e:
|
||||
result["message"] = f"错误: {str(e)}"
|
||||
result["message"] = f"获取字幕出错(这是正常的),将使用 Whisper: {str(e)}"
|
||||
# 出错时也返回 success=True,让工作流继续
|
||||
result["success"] = True
|
||||
|
||||
return result
|
||||
|
||||
async def download_subtitle(self, bvid: str) -> Dict[str, Any]:
|
||||
"""
|
||||
下载字幕并转换为 SRT 格式
|
||||
|
||||
如果没有官方字幕,返回 success=True 但 has_subtitle=False,
|
||||
让工作流继续使用 Whisper 进行语音识别。
|
||||
"""
|
||||
result = {"success": False, "bvid": bvid, "filepath": None, "has_subtitle": False, "message": ""}
|
||||
|
||||
try:
|
||||
import aiohttp
|
||||
|
||||
# 获取 CID
|
||||
api_url = f"https://api.bilibili.com/x/player/pagelist?bvid={bvid}"
|
||||
|
||||
async with aiohttp.ClientSession() as session:
|
||||
async with session.get(api_url) as resp:
|
||||
data = await resp.json()
|
||||
|
||||
pages = data.get('data', [])
|
||||
if not pages:
|
||||
result["message"] = "未找到分P,将使用 Whisper 进行语音识别"
|
||||
result["success"] = True
|
||||
return result
|
||||
|
||||
cid = pages[0].get('cid', '')
|
||||
|
||||
# 获取字幕列表
|
||||
async with aiohttp.ClientSession() as session:
|
||||
async with session.get(f"https://api.bilibili.com/x/player/v2?bvid={bvid}&cid={cid}") as resp:
|
||||
sub_data = await resp.json()
|
||||
|
||||
subtitles = sub_data.get('data', {}).get('subtitle', {}).get('list', [])
|
||||
|
||||
if not subtitles:
|
||||
result["message"] = "没有官方字幕,将使用 Whisper 进行语音识别"
|
||||
result["success"] = True
|
||||
return result
|
||||
|
||||
# 选择中文字幕,如果没有则选第一个
|
||||
zh_sub = None
|
||||
for s in subtitles:
|
||||
if s.get('lan') in ('ai-zh', 'zh-CN', 'zh'):
|
||||
zh_sub = s
|
||||
break
|
||||
if not zh_sub:
|
||||
zh_sub = subtitles[0]
|
||||
|
||||
# 下载字幕文件
|
||||
sub_url = zh_sub.get('subtitle_url', '')
|
||||
if not sub_url:
|
||||
result["message"] = "字幕URL为空,将使用 Whisper"
|
||||
result["success"] = True
|
||||
return result
|
||||
|
||||
if sub_url.startswith('//'):
|
||||
sub_url = 'https:' + sub_url
|
||||
|
||||
async with aiohttp.ClientSession() as session:
|
||||
async with session.get(sub_url) as resp:
|
||||
sub_content = await resp.json()
|
||||
|
||||
# 转换为 SRT 格式
|
||||
body = sub_content.get('body', [])
|
||||
if not body:
|
||||
result["message"] = "字幕内容为空,将使用 Whisper"
|
||||
result["success"] = True
|
||||
return result
|
||||
|
||||
def format_srt_time(t: float) -> str:
|
||||
"""将秒数转换为 SRT 时间格式"""
|
||||
h = int(t // 3600)
|
||||
m = int((t % 3600) // 60)
|
||||
s = int(t % 60)
|
||||
ms = int((t - int(t)) * 1000)
|
||||
return f"{h:02d}:{m:02d}:{s:02d},{ms:03d}"
|
||||
|
||||
srt_lines = []
|
||||
for i, line in enumerate(body, 1):
|
||||
start = line.get('from', 0)
|
||||
end = line.get('to', 0)
|
||||
content = line.get('content', '')
|
||||
srt_lines.extend([str(i), f"{format_srt_time(start)} --> {format_srt_time(end)}", content, ""])
|
||||
|
||||
srt_content = "\n".join(srt_lines)
|
||||
|
||||
# 保存 SRT 文件
|
||||
output_path = self.output_dir / f"{bvid}.srt"
|
||||
with open(output_path, 'w', encoding='utf-8') as f:
|
||||
f.write(srt_content)
|
||||
|
||||
result["success"] = True
|
||||
result["has_subtitle"] = True
|
||||
result["filepath"] = str(output_path)
|
||||
result["message"] = f"✅ 官方字幕已下载: {output_path.name} ({len(body)}条)"
|
||||
print(result["message"])
|
||||
|
||||
except Exception as e:
|
||||
result["message"] = f"下载字幕出错: {str(e)},将使用 Whisper"
|
||||
result["success"] = True # 仍然返回成功,让工作流继续
|
||||
|
||||
return result
|
||||
|
||||
@@ -252,7 +367,7 @@ class BilibiliContent:
|
||||
async def main():
|
||||
parser = argparse.ArgumentParser(description='Bilibili Content Downloader')
|
||||
parser.add_argument('--id', '-i', required=True, help='B站内容ID')
|
||||
parser.add_argument('--type', '-t', required=True, choices=['video', 'subtitle', 'article'], help='内容类型')
|
||||
parser.add_argument('--type', '-t', required=True, choices=['video', 'subtitle', 'subtitle-download', 'article'], help='内容类型')
|
||||
parser.add_argument('--output', '-o', default='./output', help='输出目录')
|
||||
parser.add_argument('--quality', '-q', type=int, default=64, help='视频质量: 16=360P, 32=480P, 64=720P, 80=1080P')
|
||||
|
||||
@@ -265,6 +380,9 @@ async def main():
|
||||
result = await downloader.download_video(args.id, quality=args.quality)
|
||||
elif args.type == 'subtitle':
|
||||
result = await downloader.extract_subtitle(args.id)
|
||||
elif args.type == 'subtitle-download':
|
||||
# 下载并转换字幕为 SRT 格式
|
||||
result = await downloader.download_subtitle(args.id)
|
||||
else:
|
||||
result = await downloader.extract_article(args.id.replace('cv', ''))
|
||||
|
||||
@@ -273,6 +391,7 @@ async def main():
|
||||
output = {
|
||||
"success": True,
|
||||
"type": args.type,
|
||||
"has_subtitle": result.get("has_subtitle", False),
|
||||
"filename": Path(result.get('filepath', '')).name if result.get('filepath') else None,
|
||||
"filepath": str(Path(result.get('filepath', '')).resolve()) if result.get('filepath') else None,
|
||||
"message": result.get('message', '处理成功')
|
||||
|
||||
Reference in New Issue
Block a user