#!/usr/bin/env python3 """ Download Wikimedia Beach Photos Script Downloads authentic, location-specific photos for beaches from the greek_beaches_export.json file Uses Wikimedia Commons for public domain photos - no API key required! """ import os import requests import json import time import uuid from urllib.parse import quote def search_wikimedia_photos(beach_name, city): """Search Wikimedia Commons for beach photos""" # Create multiple search queries with different approaches search_queries = [ f"{beach_name} {city} Greece beach", f"{beach_name} beach Greece", f"{city} Greece beach", f"{beach_name} {city} Greece", f"{beach_name} {city}" ] # Set proper headers to avoid being blocked headers = { 'User-Agent': 'BeachPhotoCollector/1.0 (https://example.com/contact) Python/requests' } wikimedia_api = "https://commons.wikimedia.org/w/api.php" for search_query in search_queries: try: # Search for files on Wikimedia Commons params = { 'action': 'query', 'format': 'json', 'list': 'search', 'srsearch': f'filetype:bitmap {search_query}', 'srnamespace': 6, # File namespace 'srlimit': 10, 'srprop': 'title|snippet' } response = requests.get(wikimedia_api, params=params, headers=headers, timeout=10) response.raise_for_status() data = response.json() if 'query' in data and 'search' in data['query'] and data['query']['search']: # Get file info for the search results files = [] for result in data['query']['search'][:5]: # Top 5 results file_title = result['title'] file_info = get_file_info(file_title, wikimedia_api, headers) if file_info: # Filter out inappropriate images by title title = file_title.lower() if not any(skip_word in title for skip_word in ['map', 'flag', 'coat', 'logo', 'diagram', 'chart', 'plan']): files.append(file_info) if files: return files except Exception as e: print(f"❌ Wikimedia search failed for query '{search_query}': {str(e)}") continue return None def get_file_info(file_title, wikimedia_api, headers=None): """Get detailed information about a Wikimedia file""" try: params = { 'action': 'query', 'format': 'json', 'titles': file_title, 'prop': 'imageinfo', 'iiprop': 'url|size|mime|extmetadata', 'iiurlwidth': 800 # Get medium-sized image } if headers is None: headers = { 'User-Agent': 'BeachPhotoCollector/1.0 (https://example.com/contact) Python/requests' } response = requests.get(wikimedia_api, params=params, headers=headers, timeout=10) response.raise_for_status() data = response.json() if 'query' in data and 'pages' in data['query']: for page_id, page_data in data['query']['pages'].items(): if 'imageinfo' in page_data and page_data['imageinfo']: img_info = page_data['imageinfo'][0] # Check if it's a reasonable image (not too small, is JPEG/PNG) if (img_info.get('width', 0) >= 400 and img_info.get('height', 0) >= 300 and img_info.get('mime', '').startswith('image/')): return { 'title': file_title, 'url': img_info.get('thumburl', img_info.get('url')), 'full_url': img_info.get('url'), 'width': img_info.get('width'), 'height': img_info.get('height'), 'mime': img_info.get('mime'), 'page_url': f"https://commons.wikimedia.org/wiki/{quote(file_title)}", 'extmetadata': img_info.get('extmetadata', {}) } return None except Exception as e: print(f"❌ Failed to get file info for {file_title}: {str(e)}") return None def download_photo(photo_data, beach_name, city, upload_dir): """Download photo from Wikimedia Commons using direct URL""" try: # Use the full URL instead of the thumbnail URL to avoid 403 errors photo_url = photo_data['full_url'] # Create filename safe_beach_name = "".join(c for c in beach_name if c.isalnum() or c in (' ', '-', '_')).strip() safe_beach_name = safe_beach_name.replace(' ', '_').lower() safe_city = city.replace(' ', '_').lower() # Get file extension from mime type mime_type = photo_data.get('mime', 'image/jpeg') ext = '.jpg' if 'jpeg' in mime_type else '.png' if 'png' in mime_type else '.jpg' filename = f"{safe_beach_name}_{safe_city}_wikimedia_{uuid.uuid4().hex[:8]}{ext}" file_path = os.path.join(upload_dir, filename) # Set headers to mimic a browser request headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36' } # Download the photo response = requests.get(photo_url, headers=headers, stream=True, timeout=30) response.raise_for_status() with open(file_path, 'wb') as f: for chunk in response.iter_content(chunk_size=8192): f.write(chunk) print(f"✅ Downloaded: {filename}") return filename except Exception as e: print(f"❌ Failed to download photo: {str(e)}") return None def main(): """Main function to download authentic photos for all beaches in the JSON file""" # Load beaches from JSON file json_file_path = "greek_beaches_export.json" try: with open(json_file_path, 'r', encoding='utf-8') as f: beaches = json.load(f) except Exception as e: print(f"❌ Failed to load JSON file: {str(e)}") return print(f"🏖️ Found {len(beaches)} beaches in the database") # Create upload directory if it doesn't exist upload_dir = "backend/uploads/beach_photos" os.makedirs(upload_dir, exist_ok=True) success_count = 0 failed_count = 0 print(f"📸 Starting Wikimedia photo download process...") print("=" * 60) for i, beach in enumerate(beaches, 1): beach_name = beach['name'] city = beach['city'] print(f"\n[{i}/{len(beaches)}] Processing: {beach_name}, {city}") # Search for photos photos = search_wikimedia_photos(beach_name, city) if not photos: print(f"❌ No authentic photos found for {beach_name}") failed_count += 1 continue # Try to download the best photo photo_downloaded = False for photo_data in photos: filename = download_photo(photo_data, beach_name, city, upload_dir) if filename: photo_downloaded = True success_count += 1 break if not photo_downloaded: print(f"❌ Failed to download authentic photo for {beach_name}") failed_count += 1 # Rate limiting - be respectful to Wikimedia API time.sleep(2) # 2 second delay between requests print(f"\n📊 DOWNLOAD COMPLETE:") print(f"✅ Successful: {success_count} beaches") print(f"❌ Failed: {failed_count} beaches") print(f"📈 Success rate: {success_count/len(beaches)*100:.1f}%") if success_count > 0: print(f"\n🎉 {success_count} authentic beach photos successfully downloaded!") print(f"📁 Photos saved to: {upload_dir}") if __name__ == "__main__": main()