In this article we are going to take a look at how we can record our screen using Python. Before getting into it, one should firstly understand what actually a video is. Basically, a video is nothing but a sequence of images (called frames) displayed at a given frequency.
So a workaround to make a screen recorder would be to capture each frame of the screen and write it as a video file. To do this python comes with handy libraries. For the screen recording we will be using OpenCV, PyAutoGUI, and Numpy.
So let's get started!
Make sure you have all the above mentioned necessary libraries installed.
-
OpenCV : To install OpenCV, run
pip install opencv-python
-
PyAutoGui : To install PyAutoGui, run
pip install pyautogui
-
Numpy : To install Numpy, run
pip install numpy
You are all set!
First step is to import all the modules needed.
import cv2 #OpenCV
import pyautogui
import numpy as np
The next step is to specify video codec using fourCC
. It is a 4 byte code used for specifying the video codec. For the sake of simplicity we can pass the FourCC
code for AVI video format which is *"XVID"
codec = cv2.VideoWriter_fourcc(*"XVID")
In the next step, we will be creating a videoWriter
object.
The video writer method of cv2 module needs 4 mandatory arguments.
First being the filename
, second being the codec
, third being the FPS (Frame per second) and the last being the video (or Screen) resolution. For a better screen recording 60 FPS is a good frame rate. You can experiment around the FPS value to get the optimum results.
out = cv2.VideoWriter("Recorded.avi", codec , 60, (1366, 768)) #Here screen resolution is 1366 x 768, you can change it depending upon your need
The next step is to implicitly create a window using namedWindow()
method with the WINDOW_NORMAL
flag so that the user can resize the window depending upon the need.
cv2.namedWindow("Recording", cv2.WINDOW_NORMAL)
cv2.resizeWindow("Recording", 480, 270) #Here we are resizing the window to 480x270 so that the program doesn't run in full screen in the beginning
Now we need to capture screenshot of each frame of the screen, write it to the video file and display the screen being recorded.
Here is the code snippet:
while True:
img = pyautogui.screenshot() #capturing screenshot
frame = np.array(img) #converting the image into numpy array representation
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB) #converting the BGR image into RGB image
out.write(frame) #writing the RBG image to file
cv2.imshow('Recording', frame) #display screen/frame being recorded
if cv2.waitKey(1) == ord('q'): #Wait for the user to press 'q' key to stop the recording
break
out.release() #closing the video file
cv2.destroyAllWindows() #destroying the recording window
Notice that the screenshot captured is in BGR format but in order to write the frame to the video file we need to convert it into RGB format using cvt.Color()
method with COLOR_BGR2RBG
flag. The condition if cv2.waitKey(1) == ord('q')
waits for the user to press 'q' key to quit the recording. Lastly we have closed the video file and destroyed the recording window by release()
and destroyAllWindows()
method respectively.
PS. Linux users please don't be happy after hearing "Destroy all Windows" ;)
You are all done!
It's time to test the results.
Maximized window: (Horrible infinite loop)
Video Demonstration:
Thanks for reading!
Top comments (6)
Very well explained and for me it worked; you really deserve kudos :-)
Only ownside, on my machine the video recorded is then played at very high speed, I need to solve this but I suppose it is another topic
Hi
Is there a way to downscale the resolution?
My 1080p screen recording is 109 MB for 5 minutes of video.
And cv2.resize() is not working.
I'm getting an output file which is 1KB.
Can you please help me with this?
I am deleting obs now 😉
Haha.. No need.. OBS is better... But yeah when it comes to low end PC, bandicam or my recorder would perform great
man that was cool
Thank you :)