refactor

ocr_scan.py

@@ -1,27 +1,29 @@
 from PIL import Image
 from pytesseract import pytesseract
 import os
+from configparser import ConfigParser
 
-#Define path to tessaract.exe #or equivalent on os
-path_to_tesseract = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
 
-#Define path to image
+def scan_document_folder():
-#path_to_image = 'input/sampletext1-ocr.png'
+    ocr_config = ConfigParser()
-#Define path to images folder
+    ocr_config.read("ocr_config.ini")
-path_to_input = r'input/'
+    
-path_to_output = r'output/'
+    ocr_settings = ocr_config['ocr']
+    path_to_tesseract = ocr_settings["path_to_tesseract"]
+    pytesseract.tesseract_cmd = path_to_tesseract
+    
+    #Get the file names in the directory
+    for root, dirs, file_names in os.walk(ocr_settings["path_to_input"]):
+        #Iterate over each file name in the folder
+        for file_name in file_names:
+            #Open image with PIL
+            img = Image.open(ocr_settings["path_to_input"] + file_name)
 
-#Point tessaract_cmd to tessaract.exe
+            #Extract text from image
-pytesseract.tesseract_cmd = path_to_tesseract
+            text = pytesseract.image_to_string(img)
 
-#Get the file names in the directory
+            print(text)
-for root, dirs, file_names in os.walk(path_to_input):
-    #Iterate over each file name in the folder
-    for file_name in file_names:
-        #Open image with PIL
-        img = Image.open(path_to_input + file_name)
 
-        #Extract text from image
-        text = pytesseract.image_to_string(img)
 
-        print(text)
+if __name__ == "__main__":
+    scan_document_folder()