import requests import re from collections import Counter from nltk.corpus import stopwords from nltk.tokenize import word_tokenize # Function to clean and tokenize text def clean_text(text): # Convert to lowercase text = text.lower() # Remove special characters and numbers text = re.sub(r'[^a-z\s]', '', text) # Tokenize text words = word_tokenize(text) # Remove stopwords stop_words = set(stopwords.words('english')) filtered_words = [word for word in words if word not in stop_words] return filtered_words # Function to generate tags from text (e.g., YouTube title, description, or blog post content) def generate_tags(text, max_tags=10): # Clean and tokenize the input text words = clean_text(text) # Count word frequency word_counts = Counter(words) # Get the most common words (tags) tags = [tag for tag, count in word_counts.most_common(max_tags)] return tags # Function to fetch content from a Blogger post using Blogger API def fetch_blog_content(blog_id, post_id, api_key): # Blogger API endpoint url = f"https://www.googleapis.com/blogger/v3/blogs/{blog_id}/posts/{post_id}?key={api_key}" # Fetch post content response = requests.get(url) if response.status_code == 200: post_data = response.json() title = post_data['title'] content = post_data['content'] return title, content else: print(f"Error: Unable to fetch post content (Status Code: {response.status_code})") return None, None # Example usage def main(): # Replace with your Blogger API details blog_id = 'YOUR_BLOG_ID' post_id = 'YOUR_POST_ID' api_key = 'YOUR_GOOGLE_API_KEY' # Fetch the blog post content blog_title, blog_content = fetch_blog_content(blog_id, post_id, api_key) if blog_title and blog_content: # Generate tags from the blog post title and content combined_text = blog_title + " " + blog_content tags = generate_tags(combined_text) print("Generated Tags:", tags) else: print("Failed to retrieve blog content.") if __name__ == "__main__": main()