47 lines
1.3 KiB
Python
47 lines
1.3 KiB
Python
|
import os
|
||
|
|
import cv2
|
||
|
|
import easyocr
|
||
|
|
|
||
|
|
def perform_ocr(image_path):
|
||
|
|
# Read the image using OpenCV
|
||
|
|
img = cv2.imread(image_path)
|
||
|
|
|
||
|
|
# Initialize the OCR reader
|
||
|
|
reader = easyocr.Reader(['en']) # Use English language
|
||
|
|
|
||
|
|
# Perform text extraction
|
||
|
|
result = reader.readtext(img)
|
||
|
|
|
||
|
|
# Extract the text from the result
|
||
|
|
text = "\n".join([entry[1] for entry in result])
|
||
|
|
|
||
|
|
return text
|
||
|
|
|
||
|
|
def main():
|
||
|
|
screenshot_dir = 'screenshots'
|
||
|
|
output_dir = 'ocr_results'
|
||
|
|
|
||
|
|
# Create output directory if it doesn't exist
|
||
|
|
if not os.path.exists(output_dir):
|
||
|
|
os.makedirs(output_dir)
|
||
|
|
|
||
|
|
# Process all PNG files in the screenshots directory
|
||
|
|
for filename in os.listdir(screenshot_dir):
|
||
|
|
if filename.endswith('.png'):
|
||
|
|
image_path = os.path.join(screenshot_dir, filename)
|
||
|
|
|
||
|
|
# Perform OCR
|
||
|
|
extracted_text = perform_ocr(image_path)
|
||
|
|
|
||
|
|
# Save the extracted text
|
||
|
|
output_filename = os.path.splitext(filename)[0] + '.txt'
|
||
|
|
output_path = os.path.join(output_dir, output_filename)
|
||
|
|
|
||
|
|
with open(output_path, 'w', encoding='utf-8') as f:
|
||
|
|
f.write(extracted_text)
|
||
|
|
|
||
|
|
print(f"Processed {filename}, saved result to {output_filename}")
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
main()
|