MacOS:使用python捕获特定窗口的屏幕截图

Question

我正在使用MSS来捕获屏幕的屏幕截图。 (因为它捕获了更快的屏幕截图(

但是我不确定如何在Mac中捕获特定窗口，我知道他们为Windows用户提供了win32... 我现在拥有的代码只是一个捕获我的主显示器的恒定循环。

main.py ：

import cv2 as cv
import numpy as np
from time import time
from mss import mss

def window_capture():
loop_time = time()
with mss() as sct:
monitor = {"top": 40, "left": 0, "width": 800, "height": 600}
while(True):
screenshot = np.array(sct.grab(monitor))
screenshot = cv.cvtColor(screenshot, cv.COLOR_RGB2BGR)
cv.imshow('Computer Vision', screenshot)
print('FPS {}'.format(1 / (time() - loop_time)))
loop_time = time()
if cv.waitKey(1) == ord('q'):
cv.destroyAllWindows()
break

window_capture()
print('Done.')

Answer 1

我写了以下ObjectiveC，获取macOS中所有窗口的名称，所有者，窗口ID和屏幕上的位置。我将其保存为windowlist.m并使用文件顶部注释中的命令对其进行编译：

////////////////////////////////////////////////////////////////////////////////
// windowlist.m
// Mark Setchell
//
// Get list of windows with their characteristics
//
// Compile with:
// clang windowlist.m -o windowlist -framework coregraphics -framework cocoa
//
// Run with:
// ./windowlist
//
////////////////////////////////////////////////////////////////////////////////
#include <Cocoa/Cocoa.h>
#include <CoreGraphics/CGWindow.h>
int main(int argc, char **argv)
{
NSArray *windows = (NSArray *)CGWindowListCopyWindowInfo(kCGWindowListOptionOnScreenOnly,kCGNullWindowID);
for(NSDictionary *window in windows){
int WindowNum = [[window objectForKey:(NSString *)kCGWindowNumber] intValue];
NSString* OwnerName = [window objectForKey:(NSString *)kCGWindowOwnerName];
int OwnerPID = [[window objectForKey:(NSString *) kCGWindowOwnerPID] intValue];
NSString* WindowName= [window objectForKey:(NSString *)kCGWindowName];
CFDictionaryRef bounds = (CFDictionaryRef)[window objectForKey:(NSString *)kCGWindowBounds];
CGRect rect;
CGRectMakeWithDictionaryRepresentation(bounds,&rect);
printf("%s:%s:%d:%d:%f,%f,%f,%fn",[OwnerName UTF8String],[WindowName UTF8String],WindowNum,OwnerPID,rect.origin.x,rect.origin.y,rect.size.height,rect.size.width);
}
}

它给出了这样的输出，其中每行的最后 4 项是窗口左上角、高度和宽度。您可以使用 Python 的subprocess.Popen()">按原样">运行此程序并获取窗口列表，或者您可以使用 Python 模块将其转换为 PythonPyObjc：

Location Menu:Item-0:4881:1886:1043.000000,0.000000,22.000000,28.000000
Backup and sync from Google:Item-0:1214:8771:1071.000000,0.000000,22.000000,30.000000
Dropbox:Item-0:451:1924:1101.000000,0.000000,22.000000,28.000000
NordVPN IKE:Item-0:447:1966:1129.000000,0.000000,22.000000,26.000000
PromiseUtilityDaemon:Item-0:395:1918:1155.000000,0.000000,22.000000,24.000000
SystemUIServer:AppleTimeMachineExtra:415:1836:1179.000000,0.000000,22.000000,40.000000
SystemUIServer:AppleBluetoothExtra:423:1836:1219.000000,0.000000,22.000000,30.000000
SystemUIServer:AirPortExtra:409:1836:1249.000000,0.000000,22.000000,30.000000
SystemUIServer:AppleVolumeExtra:427:1836:1279.000000,0.000000,22.000000,30.000000
SystemUIServer:BatteryExtra:405:1836:1309.000000,0.000000,22.000000,67.000000
SystemUIServer:AppleClockExtra:401:1836:1376.000000,0.000000,22.000000,123.000000
SystemUIServer:AppleUser:419:1836:1499.000000,0.000000,22.000000,99.000000
Spotlight:Item-0:432:1922:1598.000000,0.000000,22.000000,36.000000
SystemUIServer:NotificationCenter:391:1836:1634.000000,0.000000,22.000000,46.000000
Window Server:Menubar:353:253:0.000000,0.000000,22.000000,1680.000000
Dock:Dock:387:1835:0.000000,0.000000,1050.000000,1680.000000
Terminal:windowlist — -bash — 140×30:4105:6214:70.000000,285.000000,658.000000,1565.000000

Answer 2

import cv2 as cv
import numpy as np
from time import time
from mss import mss
from Quartz import CGWindowListCopyWindowInfo, kCGNullWindowID, kCGWindowListOptionAll
import Quartz
windowName = "Window Name like the name written on top of the window"

def get_window_dimensions(hwnd):
window_info_list = Quartz.CGWindowListCopyWindowInfo(Quartz.kCGWindowListOptionIncludingWindow, hwnd)
for window_info in window_info_list:
window_id = window_info[Quartz.kCGWindowNumber]
if window_id == hwnd:
bounds = window_info[Quartz.kCGWindowBounds]
width = bounds['Width']
height = bounds['Height']
left = bounds['X']
top = bounds['Y']
return {"top": top, "left": left, "width": width, "height": height}
return None

def window_capture():
loop_time = time()
windowList = CGWindowListCopyWindowInfo(
kCGWindowListOptionAll, kCGNullWindowID)
for window in windowList:
print(window.get('kCGWindowName', ''))
if windowName.lower() in window.get('kCGWindowName', '').lower():
hwnd = window['kCGWindowNumber']
print('found window id %s' % hwnd)
monitor = get_window_dimensions(hwnd)
with mss() as sct:
# monitor = {"top": 40, "left": 0, "width": 800, "height": 600}
while (True):
screenshot = np.array(sct.grab(monitor))
screenshot = cv.cvtColor(screenshot, cv.COLOR_RGB2BGR)
cv.imshow('Computer Vision', screenshot)
print('FPS {}'.format(1 / (time() - loop_time)))
loop_time = time()
if cv.waitKey(1) == ord('q'):
cv.destroyAllWindows()
break

window_capture()
print('Done.')

macos问题的解决方案，很容易找到Windows的答案，但Mac则不然。所以这是代码人员。坚实的 40fps...如果你通过cv2或pyautogui做同样的事情，它会给出5fps。

Answer 3

如果你想打开Chrome浏览器，那么你可以使用Python内置的包网络浏览器。您需要提供 Chrome 应用的路径，例如：webbrowser.get('open -a /Applications/Google Chrome.app %s').open('http://docs.python.org/')

打开浏览器后，应用程序位置将位于上次中断的位置。 MSS不允许您选择该应用程序。相反，您可以抓取整个屏幕或设置的位置(如您指定monitor = {"top": 40, "left": 0, "width": 800, "height": 600}(。因此，您可能希望强制浏览器全屏显示。这可以使用pyautogui包进入热键来实现。

import webbrowser
import pyautogui
def openApp(url, appPath):
webbrowser.get(appPath).open(url)
def fullScreen():    
pyautogui.hotkey('command', 'ctrl', 'f') # hotKeys for full screen mode in MacOS
url = 'http://docs.python.org/'    
appPath = 'open -a /Applications/Google Chrome.app %s' #MacOS
#appPath = 'C:/Program Files (x86)/Google/Chrome/Application/chrome.exe %s' # Windows
#appPath = ' /usr/bin/google-chrome %s' #Linux
openApp(url, appPath)
fullScreen()
# here you can add logic to take screenshots

(注意：我只在Windows上测试过，但应该可以在MacOS上运行(