Idk

process_image.py

@@ -45,7 +45,7 @@ def get_total_advanced(data, text, ocrimg, filename: Path):
 def get_total(text: str, *args, **kwargs):
     for total in re.finditer(
         r'\b(?:tota[li]|kreditkarte|total amount|[mh]astercard)'
-        r'[\sa-z]*(?:ca[ds]{1,2}|)[\s\$\'§=:]*([0-9\., :]+)',
+        r'[\sa-z«]*(?:\d[ .]{3,}|)(?:ca[ds]{1,2}|)[\s\$\'§=:]*([0-9\., :]+)',
         text,
         re.IGNORECASE,
     ):
@@ -198,7 +198,7 @@ def get_paid_by(text: str):
     last_four_digits: str = env('CARD_LAST_FOUR_DIGITS')
     # Eights sometimes come across as B in OCR
     last_four_digits = re.sub('[38]', '[38B]', last_four_digits)
-    if re.search(last_four_digits, text):
+    if re.search(f'card number.*{last_four_digits}', text, re.IGNORECASE):
         return 'Marcel'
     return 'Federica'
 
@@ -232,6 +232,7 @@ def process_image(filename: Path):
     # %%
     # TODO
     assert str(filename).endswith('.jpg')
+    print('process_image', filename)
 
     # TODO: It's not really orig anylonger
     orig = perspective_transform_by_qr(filename)
@@ -280,15 +281,14 @@ def process_image(filename: Path):
     #             output,
     #         )
 
-
     receiptCnt = None
     receipt = None
     # loop over the contours
     for i, c in enumerate(cnts):
         # approximate the contour
         # https://docs.opencv.org/3.4/dd/d49/tutorial_py_contour_features.html
         peri = cv2.arcLength(c, True)
-        approx = cv2.approxPolyDP(c, 0.003 * peri, True)
+        approx = cv2.approxPolyDP(c, 0.004 * peri, True)
         # if our approximated contour has four points, then we can
         # assume we have found the outline of the receipt
         if len(approx) > 6:
@@ -394,6 +394,7 @@ def length(line):
     paid_by = get_paid_by(text=text)
     store = get_store(text=text)
 
+    print()
     print('Store:', store)
     print('Paid by:', paid_by)
     print('Date:', date)
@@ -429,24 +430,12 @@ def length(line):
         headers={
         'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:97.0) '
             'Gecko/20100101 Firefox/97.0',
-        'Accept': 'application/json, text/javascript, */*; q=0.01',
-        'Accept-Language': 'en-US,en;q=0.5',
-        'Accept-Encoding': 'gzip, deflate, br',
+        # 'Accept': 'application/json, text/javascript, */*; q=0.01',
+        # 'Accept-Language': 'en-US,en;q=0.5',
+        # 'Accept-Encoding': 'gzip, deflate, br',
         'Referer': 'https://secure.splitwise.com/',
         'X-CSRF-Token': env('CSRF_TOKEN'),
-        # 'Content-Type': 'application/x-www-form-urlencoded',
-
-        # 'Content-Type': 'multipart/form-data',
-        # 'X-Requested-With': 'XMLHttpRequest',
-        # 'Origin': 'https://secure.splitwise.com',
-        # 'DNT': '1',
-        # 'Connection': 'keep-alive',
         'Cookie': env('COOKIE'),
-        # 'Sec-Fetch-Dest': 'empty',
-        # 'Sec-Fetch-Mode': 'cors',
-        # 'Sec-Fetch-Site': 'same-origin',
-        # 'Pragma': 'no-cache',
-        # 'Cache-Control': 'no-cache',
         },
         data=data,
         files={'receipt':