utils.py

"""
Utility functions for Vinted scraper.
"""

import re
from typing import Optional, Tuple
from urllib.parse import urlencode, urljoin

from config import BASE_URL, CATALOG_URL, CATEGORIES


def build_search_url(
    search_text: str = "",
    category: str = "",
    page: int = 1,
    min_price: Optional[float] = None,
    max_price: Optional[float] = None,
    condition: Optional[str] = None,
    order: str = "relevance"
) -> str:
    """Build a Vinted catalog search URL with filters."""
    params = {}

    if search_text:
        params["search_text"] = search_text

    if category and category in CATEGORIES:
        params["catalog[]"] = CATEGORIES[category]["id"]

    if page > 1:
        params["page"] = page

    if min_price is not None:
        params["price_from"] = min_price

    if max_price is not None:
        params["price_to"] = max_price

    if condition:
        params["status[]"] = condition

    if order and order != "relevance":
        params["order"] = order

    query_string = urlencode(params, doseq=True)
    return f"{CATALOG_URL}?{query_string}" if query_string else CATALOG_URL


def parse_alt_text(alt_text: str) -> dict:
    """
    Parse the image alt text to extract structured data.

    Format examples:
    - "Title, brand: Brand, condition: Condition, size: Size, $10.00, $12.00 includes Buyer Protection"
    - "Title, brand: Brand, condition: Condition, $10.00, $12.00 includes Buyer Protection"
    """
    result = {
        "title": "",
        "brand": "",
        "condition": "",
        "size": "",
        "price": "",
        "price_with_protection": ""
    }

    if not alt_text:
        return result

    # Extract brand
    brand_match = re.search(r'brand:\s*([^,]+)', alt_text)
    if brand_match:
        result["brand"] = brand_match.group(1).strip()

    # Extract condition
    condition_match = re.search(r'condition:\s*([^,]+)', alt_text)
    if condition_match:
        result["condition"] = condition_match.group(1).strip()

    # Extract size
    size_match = re.search(r'size:\s*([^,]+)', alt_text)
    if size_match:
        result["size"] = size_match.group(1).strip()

    # Extract prices - format: $X.XX, $Y.YY includes Buyer Protection
    price_match = re.search(r'\$([0-9,.]+),\s*\$([0-9,.]+)\s*includes?\s*Buyer\s*Protection', alt_text)
    if price_match:
        result["price"] = f"${price_match.group(1)}"
        result["price_with_protection"] = f"${price_match.group(2)}"

    # Extract title (everything before "brand:")
    title_match = re.match(r'^(.+?),\s*brand:', alt_text)
    if title_match:
        result["title"] = title_match.group(1).strip()

    return result


def extract_item_id(url: str) -> str:
    """Extract item ID from Vinted URL."""
    # URL format: /items/1234567890-item-slug
    match = re.search(r'/items/(\d+)', url)
    return match.group(1) if match else ""


def extract_favorites_count(aria_label: str) -> int:
    """Extract favorites count from button aria-label."""
    # Format: "Add to favorites, favorited by X users"
    match = re.search(r'favorited by (\d+)', aria_label)
    return int(match.group(1)) if match else 0


def make_absolute_url(url: str) -> str:
    """Convert relative URL to absolute URL."""
    if url.startswith("http"):
        return url
    return urljoin(BASE_URL, url)


def clean_price(price_str: str) -> str:
    """Clean and format price string."""
    if not price_str:
        return ""
    # Remove extra whitespace and normalize
    return price_str.strip()