Local Authority Directory Engine

# -*- coding: utf-8 -*- """This Python script is designed to scrape business listing data from a target website. It uses the 'requests' library to fetch the webpage content and 'BeautifulSoup' to parse the HTML. Finally, it exports the extracted data into a 'data.json' file, which your directory frontend uses. This script is intended to be run in Google Colab for a zero-setup environment. """ # 1. Import necessary libraries # 'requests' is used to make HTTP requests (download webpages) # 'BeautifulSoup' (from bs4) is used to parse HTML and extract data # 'json' is used to work with JSON data (for saving our output) import requests from bs4 import BeautifulSoup import json import time # To add delays between requests, being polite to websites # 2. Define the URL of the website you want to scrape # IMPORTANT: Replace this with the actual URL of the directory or listing page you want to scrape. # For example, a local chamber of commerce directory or a public business registry. TARGET_URL = "https://example.com/local-businesses" # <--- REPLACE THIS URL # 3. Define the output JSON file name OUTPUT_FILE = "data.json" # 4. Define a list to store all the extracted business data all_businesses = [] # 5. Send an HTTP GET request to the target URL to fetch the webpage content # We use a try-except block to handle potential errors during the request (e.g., website not found) try: print(f"Fetching content from: {TARGET_URL}") response = requests.get(TARGET_URL, timeout=10) # Set a timeout for the request response.raise_for_status() # Raise an HTTPError for bad responses (4xx or 5xx) html_content = response.text print("Webpage fetched successfully.") except requests.exceptions.RequestException as e: print(f"Error fetching the webpage: {e}") print("Please check the TARGET_URL and your internet connection.") exit() # Exit the script if we can't fetch the page # 6. Parse the HTML content using BeautifulSoup # This turns the raw HTML text into a Python object that we can easily navigate and search soup = BeautifulSoup(html_content, 'html.parser') # 7. Identify the HTML elements that contain individual business listings # This is the MOST CRITICAL part and requires inspection of the target website's HTML. # You will need to use your browser's developer tools (right-click -> Inspect) to find # the common HTML tag and class/id that wraps each business listing. # # Example: If each business card is a <div> with class 'business-item', # you would use: soup.find_all('div', class_='business-item') # # For demonstration, let's assume listings are in <article> tags with class 'listing-item' # You MUST adjust this line based on the actual website structure you are scraping! listing_elements = soup.find_all('article', class_='listing-item') # <--- ADJUST THIS SELECTOR if not listing_elements: print("No listing elements found with the specified selector.") print("Please inspect the target website's HTML and update the 'listing_elements' line.") exit() print(f"Found {len(listing_elements)} potential business listings.") # 8. Loop through each identified listing element and extract the relevant data for i, listing in enumerate(listing_elements): business_data = {} # Extract Business Name # Example: If the name is in an <h2> tag with class 'business-name' inside the listing name_element = listing.find('h2', class_='business-name') # <--- ADJUST THIS SELECTOR business_data['name'] = name_element.get_text(strip=True) if name_element else f"Business {i+1}" # Extract Business URL (link to their profile/website) # Example: If the link is in an <a> tag with class 'business-link' url_element = listing.find('a', class_='business-link') # <--- ADJUST THIS SELECTOR business_data['url'] = url_element['href'] if url_element and 'href' in url_element.attrs else "#" # Extract Short Description # Example: If the description is in a <p> tag with class 'business-description' desc_element = listing.find('p', class_='business-description') # <--- ADJUST THIS SELECTOR business_data['description'] = desc_element.get_text(strip=True) if desc_element else "No description available." # Extract Image URL # Example: If the image is in an <img> tag with class 'business-logo' img_element = listing.find('img', class_='business-logo') # <--- ADJUST THIS SELECTOR business_data['imageUrl'] = img_element['src'] if img_element and 'src' in img_element.attrs else "https://via.placeholder.com/150" # Add categories (example: you might infer categories or add a default) # For a real scraper, you'd extract this from the page if available. business_data['categories'] = ["General", "Featured"] # <--- ADJUST/EXTRACT CATEGORIES # Add a unique ID (important for frontend filtering/sorting) business_data['id'] = f"biz-{i+1}" # Add a rating (example: you might extract this or set a default) business_data['rating'] = 4.5 # <--- ADJUST/EXTRACT RATING all_businesses.append(business_data) # 9. Save the extracted data to a JSON file # 'indent=4' makes the JSON file human-readable with proper indentation with open(OUTPUT_FILE, 'w', encoding='utf-8') as f: json.dump(all_businesses, f, ensure_ascii=False, indent=4) print(f" Successfully scraped {len(all_businesses)} businesses and saved to {OUTPUT_FILE}") print("You can now download 'data.json' from Colab and upload it to your Netlify project.")

# This script uses the Pillow library to create multiple Pinterest pins from a template. # You will need to upload a template image and a font file to your Colab environment. # 1. Install the necessary library !pip install Pillow from PIL import Image, ImageDraw, ImageFont import os # 2. Configuration TEMPLATE_IMAGE_PATH = 'pinterest_template.png' # Upload a 1000x1500px template image FONT_PATH = 'font.ttf' # Upload a .ttf font file (e.g., from Google Fonts) OUTPUT_DIR = 'generated_pins' # 3. List of titles for your pins (e.g., from your blog posts or listings) PIN_TITLES = [ "Find Certified Eco-Plumbers in SF", "Top 5 Solar Installers in the Bay Area", "Your Guide to Sustainable Home Renovations", "Emergency Green HVAC Repair Services", # Add up to 50 titles here ] # 4. Create output directory if it doesn't exist if not os.path.exists(OUTPUT_DIR): os.makedirs(OUTPUT_DIR) # 5. Main function to generate pins def create_pin(title, index): try: # Open the template image with Image.open(TEMPLATE_IMAGE_PATH) as img: draw = ImageDraw.Draw(img) # Load the font # Adjust font size based on title length if needed font_size = 80 font = ImageFont.truetype(FONT_PATH, font_size) # Calculate text position (centered) text_width, text_height = draw.textsize(title, font=font) x = (img.width - text_width) / 2 y = (img.height - text_height) / 2 # Add a semi-transparent background for readability draw.rectangle([x-20, y-20, x+text_width+20, y+text_height+20], fill=(0,0,0,128)) # Draw the text on the image draw.text((x, y), title, font=font, fill=(255, 255, 255)) # Save the new pin output_path = os.path.join(OUTPUT_DIR, f'pin_{index+1}.png') img.save(output_path, 'PNG') print(f"Successfully created {output_path}") except FileNotFoundError: print(f"Error: Make sure '{TEMPLATE_IMAGE_PATH}' and '{FONT_PATH}' are uploaded to Colab.") return except Exception as e: print(f"An error occurred: {e}") # 6. Loop through titles and generate a pin for each for i, title in enumerate(PIN_TITLES): create_pin(title, i) print(f" Finished generating {len(PIN_TITLES)} pins in the '{OUTPUT_DIR}' folder.")