client-jiangchang/jiangchang-platform-kit
12
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(screencast): 自动激活窗口 / 多显示器 / 字幕独立时长

Browse Source 
基于 SDK 新模块（前两个 commit）的 screencast 工具能力升级：

- runner.py:
  · 新增 activate_window: bool = True 参数，录屏前自动调
    activate_and_maximize_jiangchang_window，避免开头几秒录到 PowerShell/桌面
  · 新增 monitor_index: Optional[int] = None 参数，透传给 ScreenRecorder
  · 自带 SDK 路径兜底 _ensure_sdk_on_path，让 record_screencast.py 直接 python
    跑时（不走 pytest conftest）也能 import jiangchang_desktop_sdk.window_win32

- recorder.py:
  · ScreenRecorder.__init__ 加 monitor_index 参数
  · _capture_loop 用 idx 选 monitor，越界兜底到 0
  · None = 旧行为（monitors[0] 所有屏合并），1 = 主屏，2+ = 第 N 屏
  · 多显示器场景推荐显式传 monitor_index=1 避免录出半边空白

- subtitle.py:
  · SubtitleEngine.process_line 支持二元组（兼容旧脚本）和三元组（每条独立 duration）
  · 长等待场景可以让某条字幕停留更久（如 30s）覆盖中间无日志的"字幕真空"

所有改动向后兼容，全部新增参数有默认值。

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
chendelian
2026-05-25 11:14:11 +08:00
parent 311441dab0
commit 43ec2d66a3
3 changed files with 68 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
tools/screencast/recorder.py
View File

@@ -4,15 +4,27 @@ from __future__ import annotations
import threading
import time
from pathlib import Path
from typing import Optional
import mss
import mss.tools
class ScreenRecorder:
def __init__(self, frames_dir: str, fps: int = 10):
def __init__(
self,
frames_dir: str,
fps: int = 10,
monitor_index: Optional[int] = None,
):
"""
Args:
monitor_index: mss 显示器索引；None=monitors[0]（所有屏合并区域，
旧行为），1=主屏，2+=第 N 屏。多显示器场景推荐显式传 1。
"""
self._frames_dir = Path(frames_dir)
self._fps = fps
self._monitor_index = monitor_index
self._stop_event = threading.Event()
self._thread: threading.Thread | None = None
self._frame_count = 0
@@ -36,7 +48,10 @@ class ScreenRecorder:
def _capture_loop(self) -> None:
interval = 1.0 / self._fps
with mss.mss() as sct:
monitor = sct.monitors[0] # 全屏（monitor[0] 是所有显示器合并区域）
idx = self._monitor_index if self._monitor_index is not None else 0
if idx < 0 or idx >= len(sct.monitors):
idx = 0 # 越界兜底
monitor = sct.monitors[idx]
while not self._stop_event.is_set():
t0 = time.perf_counter()
img = sct.grab(monitor)

36
tools/screencast/runner.py
View File

@@ -10,6 +10,24 @@ from datetime import datetime
from pathlib import Path
from typing import List, Optional, Tuple
def _ensure_sdk_on_path() -> None:
"""record_screencast.py 直接 python 跑时不走 conftest，SDK 可能不在 sys.path。
自带兜底：从 tools/screencast/runner.py 上溯到 platform-kit/src。"""
import importlib.util
if importlib.util.find_spec("jiangchang_desktop_sdk") is not None:
return
# tools/screencast/runner.py → tools/screencast → tools → platform-kit
here = Path(__file__).resolve()
src = here.parent.parent.parent / "src"
if (src / "jiangchang_desktop_sdk").is_dir():
import sys as _sys
_sys.path.insert(0, str(src))
_ensure_sdk_on_path()
from jiangchang_desktop_sdk.window_win32 import activate_and_maximize_jiangchang_window # noqa: E402
from .composer import compose_video
from .recorder import ScreenRecorder
from .subtitle import SubtitleEngine
@@ -23,6 +41,8 @@ def run_screencast(
media_assets_root: Optional[str] = None,
music_subdir: str = "music",
fps: int = 10,
activate_window: bool = True,
monitor_index: Optional[int] = None,
) -> str:
"""
录制一次技能桌面 E2E 演示视频。
@@ -36,7 +56,11 @@ def run_screencast(
不传时读 MEDIA_ASSETS_ROOT 环境变量，
再不存在则用默认值 D:\\OpenClaw\\client-commons\\media-assets
music_subdir: music_assets_root 下音乐子目录，默认 "music"
fps: 截帧帧率，默认 10
fps: 截帧帧率，默认 10
activate_window: 录屏开始前是否自动激活+最大化匠厂窗口（默认 True；
Windows 走 ctypes，非 Windows 走 jiangchang:// 协议）
monitor_index: 指定录哪个显示器；None=所有显示器合并（旧行为），
1=主屏，2+=第 N 屏（推荐多显示器场景显式传 1）
Returns:
输出 MP4 的绝对路径
@@ -59,7 +83,15 @@ def run_screencast(
engine = SubtitleEngine(subtitle_script)
with tempfile.TemporaryDirectory(prefix="screencast_frames_") as frames_dir:
recorder = ScreenRecorder(frames_dir, fps=fps)
recorder = ScreenRecorder(frames_dir, fps=fps, monitor_index=monitor_index)
if activate_window:
ok = activate_and_maximize_jiangchang_window()
if ok:
print("[screencast] 已激活+最大化匠厂窗口")
time.sleep(2) # 等窗口浮起稳定
else:
print("[screencast] 未能激活匠厂窗口，继续录制（可能录到桌面边角）")
print(f"[screencast] 启动录制 → {output_mp4.name}")
recorder.start()

21
tools/screencast/subtitle.py
View File

@@ -15,9 +15,15 @@ class _Entry:
class SubtitleEngine:
def __init__(self, script: List[Tuple[str, str]], default_duration: float = 5.0):
def __init__(
self,
script: List[Tuple],
default_duration: float = 5.0,
):
"""
script: [(关键词, 字幕文案), ...]
script: [(关键词, 字幕文案) | (关键词, 字幕文案, 显示时长秒), ...]
- 二元组：用 default_duration（向后兼容）
- 三元组：本条字幕独立指定显示秒数（用于长等待场景延长字幕停留）
关键词大小写不敏感，每个关键词只触发一次。
"""
self._script = script
@@ -31,12 +37,19 @@ class SubtitleEngine:
def process_line(self, line: str) -> None:
lower = line.lower()
for keyword, text in self._script:
for entry_tuple in self._script:
if len(entry_tuple) == 2:
keyword, text = entry_tuple
duration = self._default_duration
elif len(entry_tuple) == 3:
keyword, text, duration = entry_tuple
else:
continue
if keyword in self._matched:
continue
if keyword.lower() in lower:
elapsed = time.time() - self._t0
self._entries.append(_Entry(start=elapsed, text=text, duration=self._default_duration))
self._entries.append(_Entry(start=elapsed, text=text, duration=float(duration)))
self._matched.add(keyword)
def generate_srt(self, output_path: str) -> None: