Update files/functions.py

files/functions.py

@@ -383,6 +383,9 @@ def extraction_data_from_image(images):
                     
                 # OCR PyTesseract | get langs of page
                 txt = pytesseract.image_to_string(img, config=custom_config)
+                txt = txt.strip().lower()
+                txt = re.sub(r" +", " ", txt) # multiple space
+                txt = re.sub(r"(\n\s*)+\n+", "\n", txt) # multiple line
                 # txt = os.popen(f'tesseract {img_filepath} - {custom_config}').read()
 
                 try:
@@ -392,6 +395,7 @@ def extraction_data_from_image(images):
                 except:
                     langs_string = "eng"
                 langs_string += '+osd'
+                print("langs_string", langs_string)
                 custom_config = f'--oem 3 --psm 3 -l {langs_string} tsv' # default config PyTesseract: --oem 3 --psm 3
 
                 # OCR PyTesseract | get data