Updated regex
Browse files
app/services/ocr_service.py
CHANGED
|
@@ -52,7 +52,7 @@ class OCRService:
|
|
| 52 |
text = pytesseract.image_to_string(top_left, config="--psm 6 --oem 3")
|
| 53 |
print("IS_EVOLVED OCR RAW:", repr(text))
|
| 54 |
|
| 55 |
-
if re.search(r'stage[\s.\-_]*[12]', text, re.IGNORECASE):
|
| 56 |
return True
|
| 57 |
|
| 58 |
# Fallback: check for "Evolves from" text which only appears on evolved cards
|
|
@@ -185,8 +185,8 @@ class OCRService:
|
|
| 185 |
text = pytesseract.image_to_string(region, config="--psm 6 --oem 3")
|
| 186 |
print("WEIGHT OCR RAW:", repr(text))
|
| 187 |
|
| 188 |
-
# Primary: match "Weight: 76
|
| 189 |
-
match = re.search(r"Weight[:\s]+([\d.]+
|
| 190 |
if match:
|
| 191 |
return match.group(1).strip()
|
| 192 |
|
|
|
|
| 52 |
text = pytesseract.image_to_string(top_left, config="--psm 6 --oem 3")
|
| 53 |
print("IS_EVOLVED OCR RAW:", repr(text))
|
| 54 |
|
| 55 |
+
if re.search(r'stage[\s.\-_]*[12|I]', text, re.IGNORECASE):
|
| 56 |
return True
|
| 57 |
|
| 58 |
# Fallback: check for "Evolves from" text which only appears on evolved cards
|
|
|
|
| 185 |
text = pytesseract.image_to_string(region, config="--psm 6 --oem 3")
|
| 186 |
print("WEIGHT OCR RAW:", repr(text))
|
| 187 |
|
| 188 |
+
# Primary: match "Weight: 76." with flexible spacing/punctuation
|
| 189 |
+
match = re.search(r"Weight[:\s]+([\d.]+)", text, re.IGNORECASE)
|
| 190 |
if match:
|
| 191 |
return match.group(1).strip()
|
| 192 |
|