make_blogcard_info.py

import sys
import requests
from bs4 import BeautifulSoup
import json
import os
from datetime import datetime

# Install this script in a directory like ~/hugo_root/tools/

# Configure your project paths
# there are 2 more places hard-coded in the script. change it.
DATA_FILE = "../data/blogcards.json"
IMAGE_DIR = "../assets/images/blogcards"

# Ensure directories exist
os.makedirs(IMAGE_DIR, exist_ok=True)
os.makedirs("data", exist_ok=True)

def fetch_card_data(url):
    # Generate ID based on current time (added seconds to prevent collisions)
    card_id = datetime.now().strftime("%Y%m%d%H%M%S")
    
    print(f"Fetching data for: {url}")
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)'}
    
    try:
        response = requests.get(url, headers=headers, timeout=10)
        response.raise_for_status()
        soup = BeautifulSoup(response.content, 'html.parser')
    except Exception as e:
        print(f"Error fetching URL: {e}")
        sys.exit(1)

    # 1. Extract Title
    og_title = soup.find('meta', property='og:title')
    title = og_title['content'] if og_title and og_title.get('content') else ""
    if not title:
        title = soup.title.string if soup.title else url

    # 2. Extract Description
    og_desc = soup.find('meta', property='og:description')
    if not og_desc:
        og_desc = soup.find('meta', attrs={'name': 'description'})
    desc = og_desc['content'] if og_desc and og_desc.get('content') else ""

    # 3. Extract and Download Image
    og_image = soup.find('meta', property='og:image')
    image_url = og_image['content'] if og_image and og_image.get('content') else None
    
    local_image_path = ""
    if image_url:
        # Handle relative image URLs
        if image_url.startswith('/'):
            from urllib.parse import urljoin
            image_url = urljoin(url, image_url)
            
        print(f"Downloading image: {image_url}")
        try:
            img_data = requests.get(image_url, headers=headers, timeout=10).content
            # Save as jpg in assets folder
            local_image_path = f"images/blogcards/{card_id}.jpg"
            with open(f"assets/{local_image_path}", 'wb') as handler:
                handler.write(img_data)
        except Exception as e:
            print(f"Failed to download image: {e}")

    # 4. Update the Hugo Data JSON
    if os.path.exists(DATA_FILE):
        with open(DATA_FILE, 'r', encoding='utf-8') as f:
            try:
                data = json.load(f)
            except json.JSONDecodeError:
                data = {}
    else:
        data = {}

    data[card_id] = {
        "url": url,
        "title": title.strip(),
        "description": desc.strip(),
        "image": local_image_path
    }

    with open(DATA_FILE, 'w', encoding='utf-8') as f:
        json.dump(data, f, indent=2, ensure_ascii=False)

    print(f"\nSuccess! Card ID: {card_id}")
    print(f"Markdown usage:")
    print(f"{{{{< blogcard id=\"{card_id}\" url=\"{url}\" >}}}}")
    
if __name__ == "__main__":
    if len(sys.argv) < 2:
        print("Usage: python add_card.py <URL>")
        sys.exit(1)
    
    target_url = sys.argv[1]
    fetch_card_data(target_url)