feat(tools): add screencast recording engine

Adds tools/screencast/ — a reusable screen-recording pipeline for
skill demo videos. Wraps a pytest desktop E2E run with:
  - ScreenRecorder: mss-based full-screen frame capture (background thread)
  - SubtitleEngine: stdout keyword → timestamped SRT generation
  - compose_video: FFmpeg filter_complex merge (video + subtitles + BGM)
  - run_screencast: main orchestrator wiring all three layers

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-05-17 20:38:47 +08:00
parent 20294fd23a
commit 089f00c3ff
6 changed files with 278 additions and 0 deletions

View File

@@ -0,0 +1,71 @@
"""FFmpeg 合成:帧序列 + SRT 字幕 + 背景音乐 → MP4。"""
from __future__ import annotations
import random
import subprocess
import sys
from pathlib import Path
def compose_video(
frames_dir: str,
fps: int,
subtitle_path: str,
music_dir: str,
output_path: str,
music_volume: float = 0.15,
) -> str:
frames_dir = Path(frames_dir)
subtitle_path = Path(subtitle_path)
output_path = Path(output_path)
output_path.parent.mkdir(parents=True, exist_ok=True)
# 随机选一首背景音乐
music_files = list(Path(music_dir).rglob("*.mp3"))
if not music_files:
raise FileNotFoundError(f"music_dir 下没有找到 MP3 文件: {music_dir}")
music_file = random.choice(music_files)
print(f"[screencast] 背景音乐: {music_file.name}")
# FFmpeg 字幕路径在 Windows 下需要转义冒号subtitles 滤镜内部语法)
srt_path_str = str(subtitle_path).replace("\\", "/").replace(":", "\\:")
subtitle_filter = (
f"subtitles='{srt_path_str}'"
":force_style='FontName=Arial,FontSize=28,"
"PrimaryColour=&H00FFFFFF,OutlineColour=&H00000000,"
"Outline=2,Shadow=1,Alignment=2'"
)
# 视频和音频都放进 filter_complex避免 -vf 与 -filter_complex 混用报错
filter_complex = (
f"[0:v]{subtitle_filter}[vout];"
f"[1:a]volume={music_volume},apad[aout]"
)
cmd = [
"ffmpeg", "-y",
"-framerate", str(fps),
"-i", str(frames_dir / "frame_%06d.png"),
"-i", str(music_file),
"-filter_complex", filter_complex,
"-map", "[vout]",
"-map", "[aout]",
"-c:v", "libx264",
"-preset", "fast",
"-crf", "23",
"-c:a", "aac",
"-b:a", "128k",
"-shortest",
"-pix_fmt", "yuv420p",
str(output_path),
]
print(f"[screencast] 运行 FFmpeg 合成...")
result = subprocess.run(cmd, capture_output=True, text=True, encoding="utf-8", errors="replace")
if result.returncode != 0:
print(result.stderr, file=sys.stderr)
raise RuntimeError(f"FFmpeg 合成失败,退出码 {result.returncode}")
print(f"[screencast] 输出: {output_path}")
return str(output_path)