initial

finn_eiendom/parser.py

@@ -0,0 +1,88 @@
+"""Normalization and parsing helpers."""
+
+import re
+
+
+def normalize_price(price_str: str | None) -> int | None:
+    """
+    Normalize Norwegian formatted price to integer.
+    Example: "7 200 991 kr" -> 7200991
+    """
+    if not price_str:
+        return None
+    # Remove "kr" and spaces, keep only digits
+    normalized = re.sub(r"[^\d]", "", price_str)
+    try:
+        return int(normalized) if normalized else None
+    except ValueError:
+        return None
+
+
+def normalize_area(area_str: str | None) -> int | None:
+    """
+    Normalize area string to integer.
+    Example: "77 m²" -> 77
+    """
+    if not area_str:
+        return None
+    cleaned = area_str.replace(" ", "")
+    match = re.search(r"(\d+(?:[.,]\d+)?)", cleaned)
+    if match:
+        value = match.group(1).replace(",", ".")
+        try:
+            return int(float(value))
+        except ValueError:
+            return None
+    return None
+
+
+def normalize_number(num_str: str | None) -> int | None:
+    """
+    Normalize Norwegian formatted number to integer.
+    Handles text like "3 500 kr/mnd" and "7,2".
+    """
+    if not num_str:
+        return None
+    cleaned = re.sub(r"[^\d,\.]", "", num_str)
+    cleaned = cleaned.replace(" ", "")
+    if "," in cleaned:
+        cleaned = cleaned.replace(".", "").replace(",", ".")
+    else:
+        cleaned = cleaned.replace(".", "")
+    try:
+        return int(float(cleaned)) if cleaned else None
+    except ValueError:
+        return None
+
+
+def normalize_finnkode(finnkode: str | None) -> str | None:
+    """Normalize finnkode to string, strip whitespace."""
+    if not finnkode:
+        return None
+    return str(finnkode).strip()
+
+
+def extract_finnkode_from_url(url: str) -> str | None:
+    """
+    Extract finnkode from FINN URL.
+    Example: https://www.finn.no/realestate/homes/ad.html?finnkode=462400360 -> 462400360
+    """
+    match = re.search(r"finnkode=(\d+)", url)
+    if match:
+        return match.group(1)
+    return None
+
+
+def text_to_bool(text: str | None) -> bool:
+    """Convert text to boolean."""
+    if not text:
+        return False
+    return text.lower() in ("ja", "yes", "true", "1", "y")
+
+
+def clean_text(text: str | None) -> str | None:
+    """Clean and normalize text: strip, collapse whitespace."""
+    if not text:
+        return None
+    cleaned = " ".join(text.split())
+    return cleaned if cleaned else None