Files
skill-template/examples/real_desktop_rpa/scripts/service/desktop_session.py
chendelian 79d21c063d
All checks were successful
技能自动化发布 / release (push) Successful in 5s
feat: add three-surface RPA locator standards and examples
2026-07-25 10:20:45 +08:00

112 lines
3.2 KiB
Python

"""Windows 顶层窗口作用域:枚举、唯一性校验和激活。"""
from __future__ import annotations
import ctypes
import ntpath
from ctypes import wintypes
from dataclasses import dataclass
from typing import Iterable
from util.selectors import WindowSpec
class DesktopRpaError(RuntimeError):
def __init__(self, code: str, message: str) -> None:
super().__init__(f"ERROR:{code} {message}")
self.code = code
self.message = message
@dataclass(frozen=True)
class WindowCandidate:
hwnd: int
pid: int
process_name: str
class_name: str
title: str
visible: bool
user32 = ctypes.windll.user32
kernel32 = ctypes.windll.kernel32
SW_RESTORE = 9
PROCESS_QUERY_LIMITED_INFORMATION = 0x1000
def _process_name(pid: int) -> str:
handle = kernel32.OpenProcess(PROCESS_QUERY_LIMITED_INFORMATION, False, pid)
if not handle:
return ""
try:
size = wintypes.DWORD(32768)
buffer = ctypes.create_unicode_buffer(size.value)
if not kernel32.QueryFullProcessImageNameW(
handle,
0,
buffer,
ctypes.byref(size),
):
return ""
return ntpath.splitext(ntpath.basename(buffer.value))[0]
finally:
kernel32.CloseHandle(handle)
def enumerate_top_windows() -> list[WindowCandidate]:
found: list[WindowCandidate] = []
@ctypes.WINFUNCTYPE(ctypes.c_bool, wintypes.HWND, wintypes.LPARAM)
def callback(hwnd, _lparam):
pid = wintypes.DWORD()
user32.GetWindowThreadProcessId(hwnd, ctypes.byref(pid))
cls = ctypes.create_unicode_buffer(256)
user32.GetClassNameW(hwnd, cls, 256)
length = user32.GetWindowTextLengthW(hwnd)
title = ctypes.create_unicode_buffer(length + 1)
user32.GetWindowTextW(hwnd, title, length + 1)
found.append(
WindowCandidate(
hwnd=int(hwnd),
pid=int(pid.value),
process_name=_process_name(int(pid.value)),
class_name=cls.value,
title=title.value,
visible=bool(user32.IsWindowVisible(hwnd)),
)
)
return True
user32.EnumWindows(callback, 0)
return found
def resolve_unique_window(
spec: WindowSpec,
*,
candidates: Iterable[WindowCandidate] | None = None,
) -> WindowCandidate:
pool = list(candidates) if candidates is not None else enumerate_top_windows()
matched = [
item
for item in pool
if item.visible
and item.process_name.casefold() == spec.process_name.casefold()
and item.class_name == spec.class_name
and (spec.title is None or item.title == spec.title)
]
if not matched:
raise DesktopRpaError("WINDOW_NOT_FOUND", f"{spec.logical_name} 未找到")
if len(matched) != 1:
raise DesktopRpaError(
"ELEMENT_AMBIGUOUS",
f"{spec.logical_name} 匹配 {len(matched)} 个窗口,请按 PID/账号补充作用域",
)
return matched[0]
def activate_window(window: WindowCandidate) -> None:
user32.ShowWindow(window.hwnd, SW_RESTORE)
if not user32.SetForegroundWindow(window.hwnd):
raise DesktopRpaError("WINDOW_ACTIVATE_FAILED", f"无法激活 hwnd={window.hwnd}")