import logging
import re
from typing import Dict, Any, Optional
from bs4 import BeautifulSoup
from datetime import datetime, date
from .horoscope_scraper import HoroscopeScraper

logger = logging.getLogger(__name__)

class HoroscopeComScraper(HoroscopeScraper):
    """Scraper for Horoscope.com daily horoscopes"""
    
    def __init__(self, timeout: int = 30):
        super().__init__(timeout)
        self.source_name = "Horoscope.com"
        self.base_url = "https://www.horoscope.com/us/horoscopes/general/horoscope-general-daily-today.aspx"
    
    def _format_url(self, base_url: str, sign: str, date_str: Optional[str] = None) -> str:
        """Format URL for horoscope.com"""
        # Map zodiac signs to their numeric ids used by horoscope.com
        sign_ids = {
            "aries": 1, "taurus": 2, "gemini": 3, "cancer": 4,
            "leo": 5, "virgo": 6, "libra": 7, "scorpio": 8,
            "sagittarius": 9, "capricorn": 10, "aquarius": 11, "pisces": 12
        }
        
        sign_id = sign_ids.get(sign.lower(), 1)
        
        if date_str:
            try:
                # Convert YYYY-MM-DD to the format needed (YYYYMMDD)
                date_obj = datetime.strptime(date_str, '%Y-%m-%d')
                formatted_date = date_obj.strftime('%Y%m%d')
                return f"{self.base_url}?sign={sign_id}&laDate={formatted_date}"
            except Exception as e:
                logger.error(f"Error formatting date: {str(e)}")
        
        # Default to current date if no date provided
        return f"{self.base_url}?sign={sign_id}"
    
    def _extract_prediction(self, soup: BeautifulSoup, text_content: str) -> str:
        """Extract horoscope prediction from horoscope.com"""
        # Horoscope.com typically has the horoscope in a div with class 'main-horoscope'
        prediction_div = soup.select('.main-horoscope p')
        
        if prediction_div:
            # Join all paragraphs in the prediction div
            prediction = ' '.join([p.get_text().strip() for p in prediction_div])
            return prediction
        
        # Alternative selector
        alt_div = soup.select('#textline')
        if alt_div:
            return alt_div[0].get_text().strip()
        
        # Fallback to generic extraction
        return super()._extract_prediction(soup, text_content)
    
    def _extract_date(self, soup: BeautifulSoup, url: str) -> str:
        """Extract horoscope date from horoscope.com"""
        # Try to get date from URL first (in the laDate parameter)
        date_match = re.search(r'laDate=(\d{8})', url)
        if date_match:
            date_str = date_match.group(1)
            try:
                parsed_date = datetime.strptime(date_str, '%Y%m%d')
                return parsed_date.strftime('%Y-%m-%d')
            except ValueError:
                pass
        
        # Look for date in typical location
        date_div = soup.select('.main-horoscope h1, .main-horoscope h2')
        if date_div:
            date_text = date_div[0].get_text().strip()
            # Try to extract date (format typically like "Taurus Daily Horoscope for May 13, 2025")
            try:
                # Try to match month day, year pattern
                match = re.search(r'(\w+)\s+(\d{1,2}),?\s+(\d{4})', date_text)
                if match:
                    month, day, year = match.groups()
                    month_dict = {
                        'january': 1, 'february': 2, 'march': 3, 'april': 4,
                        'may': 5, 'june': 6, 'july': 7, 'august': 8,
                        'september': 9, 'october': 10, 'november': 11, 'december': 12
                    }
                    month_num = month_dict.get(month.lower(), 1)
                    parsed_date = datetime(int(year), month_num, int(day))
                    return parsed_date.strftime('%Y-%m-%d')
            except Exception:
                pass
        
        # Default to today's date if no date found
        return date.today().isoformat()