Python+opencv+pyaudio实现带声音屏幕录制

原文链接：https://blog.csdn.net/zhaoyun_zzz/article/details/84341801

Python+opencv+pyaudio实现带声音屏幕录制
原创luke-skyworker 发布于2018-11-28 23:05:23 阅读数 3463 收藏
展开
文章目录
声音录制
视频录制（无声音）
录制的音频与视频合成为带声音的视频

基于个人的爱好和现实的需求，决定用Python做一个屏幕录制的脚本。因为要看一些加密的视频，每次都要登录，特别麻烦，遂决定用自己写的脚本，将加密视频的播放过程全程录制下来，这样以后看自己的录播就好了。结合近期自己学习的内容，正好用Python来练练手，巩固自己的学习效果。
经过多番搜索，决定采用Python+opencv+pyaudio来实现屏幕录制。网上搜索到的录屏，基本都是不带声音的，而我要实现的是带声音的屏幕录制。下面就开始一步一步的实现吧。
声音录制
import pyaudio
import wave
import sys

CHUNK = 1024
if len(sys.argv) < 2:
print("Plays a wave file. Usage: %s filename.wav" % sys.argv[0])
sys.exit(-1)

wf = wave.open(sys.argv[1], 'rb')
p = pyaudio.PyAudio()
stream = p.open(format=p.get_format_from_width(wf.getsampwidth()),
channels=wf.getnchannels(),
rate=wf.getframerate(),
output=True)

data = wf.readframes(CHUNK)
while data != '':
stream.write(data)
data = wf.readframes(CHUNK)

stream.stop_stream()
stream.close()
p.terminate()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
简洁回调函数版音频录制

import pyaudio
import wave
import time
import sys

CHUNK = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 2
RATE = 44100
RECORD_SECONDS = 10
WAVE_OUTPUT_FILENAME = "output.wav"

p = pyaudio.PyAudio()
wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
wf.setnchannels(CHANNELS)
wf.setsampwidth(p.get_sample_size(FORMAT))
wf.setframerate(RATE)

time_count = 0
def callback(in_data, frame_count, time_info, status):
wf.writeframes(in_data)
if(time_count < 10):
return (in_data, pyaudio.paContinue)
else:
return (in_data, pyaudio.paComplete)

stream = p.open(format=p.get_format_from_width(wf.getsampwidth()),
channels=wf.getnchannels(),
rate=wf.getframerate(),
input=True,
stream_callback=callback)

stream.start_stream()
print("* recording")
while stream.is_active():
time.sleep(1)
time_count += 1

stream.stop_stream()
stream.close()
wf.close()
p.terminate()
print("* recording done!")
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
视频录制（无声音）
from PIL import ImageGrab
import numpy as np
import cv2

image = ImageGrab.grab()#获得当前屏幕
width = image.size[0]
height = image.size[1]
print("", width, "height:", height)
print("image mode:",image.mode)
k=np.zeros((width,height),np.uint8)
fourcc = cv2.VideoWriter_fourcc(*'XVID')#编码格式
video = cv2.VideoWriter('test.avi', fourcc, 25, (width, height))
#输出文件命名为test.mp4,帧率为16，可以自己设置
while True:
img_rgb = ImageGrab.grab()
img_bgr=cv2.cvtColor(np.array(img_rgb), cv2.COLOR_RGB2BGR)#转为opencv的BGR格式
video.write(img_bgr)
cv2.imshow('imm', img_bgr)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
video.release()
cv2.destroyAllWindows()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
录制的音频与视频合成为带声音的视频
录制200帧，带音频的MP4视频，单线程

import wave
from pyaudio import PyAudio,paInt16
from PIL import ImageGrab
import numpy as np
import cv2
from moviepy.editor import *
from moviepy.audio.fx import all
import time

CHUNK = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 2
RATE = 44100
WAVE_OUTPUT_FILENAME = "output.wav"

p = pyaudio.PyAudio()
wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
wf.setnchannels(CHANNELS)
wf.setsampwidth(p.get_sample_size(FORMAT))
wf.setframerate(RATE)
audio_record_flag = True
def callback(in_data, frame_count, time_info, status):
wf.writeframes(in_data)
if audio_record_flag:
return (in_data, pyaudio.paContinue)
else:
return (in_data, pyaudio.paComplete)
stream = p.open(format=p.get_format_from_width(wf.getsampwidth()),
channels=wf.getnchannels(),
rate=wf.getframerate(),
input=True,
stream_callback=callback)
image = ImageGrab.grab()#获得当前屏幕
width = image.size[0]
height = image.size[1]
print("", width, "height:", height)
print("image mode:",image.mode)
k=np.zeros((width,height),np.uint8)

fourcc = cv2.VideoWriter_fourcc(*'XVID')#编码格式
video = cv2.VideoWriter('test.mp4', fourcc, 9.5, (width, height))
#经实际测试，单线程下最高帧率为10帧/秒，且会变动，因此选择9.5帧/秒
#若设置帧率与实际帧率不一致，会导致视频时间与音频时间不一致

print("video recording!!!!!")
stream.start_stream()
print("audio recording!!!!!")
record_count = 0
while True:
img_rgb = ImageGrab.grab()
img_bgr=cv2.cvtColor(np.array(img_rgb), cv2.COLOR_RGB2BGR)#转为opencv的BGR格式
video.write(img_bgr)
record_count += 1
if(record_count > 200):
break
print(record_count, time.time())

audio_record_flag = False
while stream.is_active():
time.sleep(1)

stream.stop_stream()
stream.close()
wf.close()
p.terminate()
print("audio recording done!!!!!")

video.release()
cv2.destroyAllWindows()
print("video recording done!!!!!")

print("video audio merge!!!!!")
audioclip = AudioFileClip("output.wav")
videoclip = VideoFileClip("test.mp4")
videoclip2 = videoclip.set_audio(audioclip)
video = CompositeVideoClip([videoclip2])
video.write_videofile("test2.mp4",codec='mpeg4')
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
看来要提高帧率必须使用队列加多线程了，这一步等到以后来添加吧。不过总是觉得用OpenCV来实现视频录制，有点怪异，毕竟opencv是用来做图像与视频分析的，还是走正道认真捣鼓opencv该做的事情吧。
————————————————
版权声明：本文为CSDN博主「luke-skyworker」的原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接及本声明。