#!/usr/bin/env python3
"""
Craigslist Scanner for Cast Iron
Scans Craigslist for cast iron cookware deals
"""
import requests
from datetime import datetime
import re
from bs4 import BeautifulSoup

def search_craigslist_cast_iron(locations=None):
    """
    Search Craigslist for cast iron items
    locations: list of Craigslist location codes
    """
    if locations is None:
        locations = [
            'atlanta', 'austin', 'boston', 'charleston', 'chicago',
            'dallas', 'denver', 'detroit', 'houston', 'kansascity',
            'lasvegas', 'losangeles', 'miami', 'minneapolis', 'nashville',
            'newjersey', 'newyork', 'orangecounty', 'philadelphia',
            'phoenix', 'pittsburgh', 'portland', 'raleigh', 'sacramento',
            'sandiego', 'sfbay', 'seattle', 'stlouis', 'tampa', 'washingtondc'
        ]
    
    items = []
    search_query = "cast iron skillet"
    
    headers = {
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36',
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
    }
    
    # Scan first 10 locations to avoid rate limiting
    for location in locations[:10]:
        try:
            url = f"https://{location}.craigslist.org/search/sss?query={search_query.replace(' ', '%20')}"
            
            response = requests.get(url, headers=headers, timeout=10)
            
            if response.status_code == 200:
                soup = BeautifulSoup(response.text, 'html.parser')
                
                # Craigslist uses different class names - try multiple selectors
                results = []
                
                # Try new Craigslist layout
                results = soup.find_all('li', class_='result-row')
                
                # Fallback to old layout
                if not results:
                    results = soup.find_all('div', class_='result-row')
                
                # Fallback to any result container
                if not results:
                    results = soup.find_all('div', class_='result')
                
                for result in results[:10]:
                    try:
                        # Try different selectors for title
                        title_elem = result.find('a', class_='result-title')
                        if not title_elem:
                            title_elem = result.find('a', class_='result-title hdr')
                        if not title_elem:
                            title_elem = result.find('a')
                        
                        if not title_elem:
                            continue
                        
                        title = title_elem.text.strip()
                        link = title_elem.get('href', '')
                        
                        if not link or not title:
                            continue
                        
                        # Extract price
                        price_elem = result.find('span', class_='result-price')
                        price = 0
                        if price_elem:
                            price_match = re.search(r'\$?([\d,]+)', price_elem.text)
                            if price_match:
                                price = float(price_match.group(1).replace(',', ''))
                        
                        # Extract location
                        loc_elem = result.find('span', class_='result-hood')
                        loc = loc_elem.text.strip() if loc_elem else location
                        
                        # Clean up link if relative
                        if link.startswith('/'):
                            link = f"https://{location}.craigslist.org{link}"
                        
                        items.append({
                            'title': title,
                            'price': price,
                            'link': link,
                            'source': f'Craigslist ({location})',
                            'location': loc,
                            'found_at': datetime.now().isoformat()
                        })
                    except Exception as e:
                        continue
                        
        except Exception as e:
            print(f"Craigslist {location} error: {e}")
    
    return items

if __name__ == "__main__":
    print("🔍 Scanning Craigslist for cast iron...")
    items = search_craigslist_cast_iron()
    print(f"Found {len(items)} items")
    for item in items[:5]:
        print(f"  - {item['title'][:50]} - ${item['price']} ({item['source']})")