# python_scraper.py
import requests
from bs4 import BeautifulSoup
import pandas as pd
import json # For SerpAPI mock

# Note: In a real scenario, you'd use a Google Trends API wrapper or
# a more sophisticated news aggregation API. This is a simplified example.

def get_trending_news_headlines(query, num_articles=5):
    """
    Simulates fetching trending news headlines related to a query.
    In production, this would hit a proper news API or scrape specific, reliable sources.
    """
    mock_headlines = [
        f"Microsoft's Latest AI Layoffs: {i} Roles Affected",
        f"How LLMs are Reshaping Tech Jobs: Microsoft's Case Study {i}",
        f"Future of Work: AI vs. Human in 2025 - Lessons from Microsoft {i}",
        f"Beyond Microsoft: Industries Embracing AI Automation {i}",
        f"Upskilling for the AI Era: What Microsoft's Cuts Mean for You {i}"
    ]
    return mock_headlines[:num_articles]

def get_serp_insights(query):
    """
    Simulates fetching search engine results page (SERP) insights using SerpAPI.
    This provides 'People Also Ask' or related searches.
    """
    # In a real scenario:
    # from serpapi import GoogleSearch
    # params = {"q": query, "api_key": "YOUR_SERPAPI_KEY"}
    # search = GoogleSearch(params)
    # results = search.get_dict()
    # return results.get("related_searches", [])

    # Mock SerpAPI output for demonstration
    mock_serp_data = {
        "related_searches": [
            {"query": "AI job replacement statistics 2025"},
            {"query": "Microsoft AI strategy employment"},
            {"query": "How to future-proof your job against AI"},
            {"query": "LLM impact on knowledge work"},
            {"query": "AI automation examples in industry"}
        ],
        "people_also_ask": [
            {"question": "Which jobs are most at risk from AI?", "answer": "Jobs with repetitive tasks..."},
            {"question": "How many jobs will AI create by 2025?", "answer": "Some estimates suggest millions..."},
        ]
    }
    return mock_serp_data

if __name__ == "__main__":
    main_query = "Microsoft AI job cuts"
    
    print(f"--- Trending News Headlines for '{main_query}' ---")
    headlines = get_trending_news_headlines(main_query)
    for i, headline in enumerate(headlines):
        print(f"{i+1}. {headline}")

    print("\n--- SERP Insights (Related Searches & PAA) ---")
    serp_insights = get_serp_insights(main_query)
    print("Related Searches:")
    for rs in serp_insights.get("related_searches", []):
        print(f"- {rs['query']}")
    print("\nPeople Also Ask:")
    for paa in serp_insights.get("people_also_ask", []):
        print(f"- {paa['question']}")

    # Combine and use these insights for content ideas
    all_ideas = [main_query] + [h for h in headlines] + \
                [rs['query'] for rs in serp_insights.get("related_searches", [])] + \
                [paa['question'] for paa in serp_insights.get("people_also_ask", [])]
    
    df_ideas = pd.DataFrame(all_ideas, columns=['Content Idea'])
    print(f"\n--- Combined Content Ideas (first 5) ---\n{df_ideas.head().to_string()}")

# llm_writer.py
from openai import OpenAI # or anthropic, or HuggingFace
import os # For API key
# from langchain.prompts import PromptTemplate # For more complex chains

# Note: Replace with your actual API key and chosen model
# os.environ["OPENAI_API_KEY"] = "YOUR_OPENAI_API_KEY"
client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))

def generate_article_draft(topic, serp_insights, related_headlines):
    """
    Generates a first draft of an article using an LLM.
    Incorporates SEO insights for better targeting.
    """
    context = f"Topic: {topic}\n\n"
    context += "Key questions from 'People Also Ask':\n"
    for q in serp_insights.get("people_also_ask", []):
        context += f"- {q['question']}\n"
    context += "\nRelated Searches for SEO enrichment:\n"
    for rs in serp_insights.get("related_searches", []):
        context += f"- {rs['query']}\n"
    context += "\nRecent headlines for current context:\n"
    for h in related_headlines:
        context += f"- {h}\n"

    prompt = f"""
    You are a professional content automation expert and technical blogger.
    Write a detailed, informative, and engaging blog post draft (approx. 800 words) on the following topic,
    incorporating the provided SEO insights and recent context.
    
    Focus on practical advice for solo content creators and developers.
    Use clear headings, bullet points, and an energetic, smart, but not hyped tone.
    The article should provide actionable steps and avoid overselling.

    {context}

    Article Title: {topic} - Leveraging AI for Content Creation
    """

    try:
        response = client.chat.completions.create(
            model="gpt-4o-2024-05-13", # Assuming GPT-4o or similar as latest in 2025
            messages=[
                {"role": "system", "content": "You are a helpful AI content writer."},
                {"role": "user", "content": prompt}
            ],
            temperature=0.7,
            max_tokens=2000
        )
        return response.choices[0].message.content
    except Exception as e:
        print(f"Error generating content: {e}")
        return "Content generation failed."

if __name__ == "__main__":
    # Mocking data from the previous scraping step
    mock_topic = "Microsoft’s AI Job Cuts: 6,500 Roles Replaced by LLMs - An Opportunity for Creators"
    mock_serp_insights = {
        "related_searches": [{"query": "AI job replacement statistics 2025"}],
        "people_also_ask": [{"question": "Which jobs are most at risk from AI?"}],
    }
    mock_headlines = ["Microsoft AI Layoffs Spark Debate"]

    print(f"Generating draft for: '{mock_topic}'...")
    article_draft = generate_article_draft(mock_topic, mock_serp_insights, mock_headlines)
    print("\n--- Generated Article Draft (partial) ---")
    print(article_draft[:700] + "...\n[Full article continues, approx. 800 words]")

# wordpress_publisher.py
from wordpress_xmlrpc import Client, WordPressPost
from wordpress_xmlrpc.methods.posts import NewPost, EditPost
from wordpress_xmlrpc.methods.media import UploadFile
import os

# Note: Replace with your WordPress site details and credentials
# Always use environment variables or a secure configuration method for credentials!
WORDPRESS_URL = os.getenv('WORDPRESS_URL', 'http://your-wordpress-site.com/xmlrpc.php')
WORDPRESS_USERNAME = os.getenv('WORDPRESS_USERNAME', 'your_wp_username')
WORDPRESS_PASSWORD = os.getenv('WORDPRESS_PASSWORD', 'your_wp_password')

def post_to_wordpress(title, content, categories=None, tags=None, status='publish', featured_image_path=None):
    """
    Publishes an article to WordPress via XML-RPC.
    """
    try:
        client = Client(WORDPRESS_URL, WORDPRESS_USERNAME, WORDPRESS_PASSWORD)
        
        post = WordPressPost()
        post.title = title
        post.content = content
        post.post_status = status # 'publish', 'draft', 'pending'

        if categories:
            post.terms_names = {'category': categories}
        if tags:
            post.terms_names['post_tag'] = tags

        post_id = client.call(NewPost(post))
        print(f"Successfully created post with ID: {post_id}")

        if featured_image_path:
            # Upload featured image
            data = {
                'name': os.path.basename(featured_image_path),
                'type': 'image/jpeg', # Adjust type based on image file
            }
            with open(featured_image_path, 'rb') as f:
                data['bits'] = f.read()

            upload_result = client.call(UploadFile(data))
            attachment_id = upload_result['id']
            
            # Set as featured image
            post.id = post_id
            post.thumbnail = attachment_id
            client.call(EditPost(post_id, post))
            print(f"Set featured image {os.path.basename(featured_image_path)} for post {post_id}")

        return post_id

    except Exception as e:
        print(f"Error posting to WordPress: {e}")
        return None

if __name__ == "__main__":
    # Mock data from our LLM writer
    mock_article_title = "Leveraging AI for Content: A Solo Creator's Guide in 2025"
    mock_article_content = """
    This is a generated article about how solo creators can leverage AI, especially after Microsoft's recent job cuts.
    It covers content ideation, automated writing with GPT-5, and programmatic publishing.
    """
    mock_categories = ['AI Blogging', 'Automation', 'Monetization']
    mock_tags = ['AI 2025', 'GPT', 'WordPress Automation', 'Solo Creator']
    
    # Create a dummy image file for demonstration
    dummy_image_path = 'dummy_featured_image.jpg'
    with open(dummy_image_path, 'wb') as f:
        f.write(b'\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x01\x00\x00\x00\x01\x08\x06\x00\x00\x00\x1f\x15\xc4\x89\x00\x00\x00\x0cIDATx\xda\xed\xc1\x01\x01\x00\x00\x00\xc2\xa0\xf7Om\x00\x00\x00\x00IEND\xaeB`\x82') # Minimal valid PNG

    print(f"Attempting to post '{mock_article_title}' to WordPress...")
    post_id = post_to_wordpress(
        title=mock_article_title,
        content=mock_article_content,
        categories=mock_categories,
        tags=mock_tags,
        featured_image_path=dummy_image_path
    )
    
    if post_id:
        print(f"Post successful! Check your WordPress site for post ID: {post_id}")
    
    # Clean up dummy image
    if os.path.exists(dummy_image_path):
        os.remove(dummy_image_path)