python+Tesseract OCR实现截屏识别文字

# 查看版本
PS D:\Program Files\Tesseract-OCR> .\tesseract.exe -v
tesseract v5.3.0.20221214
 leptonica-1.78.0
  libgif 5.1.4 : libjpeg 8d (libjpeg-turbo 1.5.3) : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libwebp 0.6.1 : libopenjp2 2.3.0
 Found AVX2
 Found AVX
 Found FMA
 Found SSE4.1
 Found libarchive 3.5.0 zlib/1.2.11 liblzma/5.2.3 bz2lib/1.0.6 liblz4/1.7.5 libzstd/1.4.5
 Found libcurl/7.77.0-DEV Schannel zlib/1.2.11 zstd/1.4.5 libidn2/2.0.4 nghttp2/1.31.0
# 查看安装的语言包
PS D:\Program Files\Tesseract-OCR> .\tesseract.exe --list-langs
List of available languages in "D:\Program Files\Tesseract-OCR/tessdata/" (4):
chi_sim
chi_sim_vert
eng
osd

pip install pyautogui
pip install pytesseract

import pyautogui
import pytesseract

# 设置Tesseract的安装路径（如果它不在默认的系统路径中）
pytesseract.pytesseract.tesseract_cmd = 'D:/Program Files/Tesseract-OCR/tesseract.exe'

# 截取屏幕截图
screenshot = pyautogui.screenshot()

# 定义区域范围（左上角x坐标，左上角y坐标，右下角x坐标，右下角y坐标）
region = (100, 100, 300, 200)

# 从屏幕截图中使用指定区域创建一个新的图像对象
custom_screenshot = screenshot.crop(region)

# 将图像对象转换为灰度图像，以帮助提高文本识别的准确性
custom_screenshot = custom_screenshot.convert('L')

# 使用pytesseract进行文字识别
text = pytesseract.image_to_string(custom_screenshot)

# 打印识别的文本
print(text)