testing 3

backend/text_recog.py

@@ -20,28 +20,36 @@ def extract_ktp_info(image_path, filename):
 
     text = text.replace('\n\n\n', '\n').replace('\n\n', '\n').replace('\n', '\n')
 
-    matches = re.findall(r':\s*(.+)', text)
+    match = re.search(r'Berlaku Hingga\n(.*?)\nGol\. Darah', text, re.DOTALL)
+
+    if match:
+        extracted_text = match.group(1)
+        lines = [
+            re.sub(r'^(:|\d+)?\s*', '', line.strip()) 
+            for line in extracted_text.strip().split('\n')
+            if line.strip()
+        ]
+        print("Hasil List Bersih:")
+        print(lines)
+    
     city = re.search(r'PROVINSI\s+(.+?)\n(.+?)\n', text)
 
-    # result = {
-    #     "nik" : matches[1],
-    #     "nama" : matches[2],
-    #     "tempat_tgl_lahir" : matches[3],
-    #     "jenis_kelamin" : matches[4],
-    #     "alamat" : matches[5],
-    #     "rt_rw" : matches[6],
-    #     "kel/desa" : matches[7],
-    #     "kecamatan" : matches[8],
-    #     "provinsi" : city.group(1).strip(),
-    #     "kab/kota" : city.group(2).strip(),
-    #     "agama" : matches[9],
-    #     "pekerjaan" : matches[10],
-    #     "gol_dar" : matches[12]
-    # }
-
-    # if "WNI" in text:
-    #     result["Kewarganegaraan"] = "WNI"
+    result = {
+        "nik" : lines[0],
+        "nama" : lines[1],
+        "tempat_tgl_lahir" : lines[2],
+        "jenis_kelamin" : lines[3],
+        "alamat" : lines[4],
+        "rt_rw" : lines[5],
+        "kel/desa" : lines[6],
+        "kecamatan" : lines[7],
+        "provinsi" : lines[13],
+        "kab/kota" : lines[14],
+        "agama" : lines[8],
+        "kewarganegaraan" : lines[10],
+        "pekerjaan" : lines[9],
+    }
 
     # convert_image_to_word(result, f'KTP {filename}')
 
-    return text
+    return result