DeepSeek AI Integration

import requests
import os
from supacrawler import SupacrawlerClient

# Initialize clients
supacrawler = SupacrawlerClient(api_key=os.environ['SUPACRAWLER_API_KEY'])
deepseek_api_key = os.environ['DEEPSEEK_API_KEY']

def scrape_and_analyze(url, analysis_prompt):
    """Scrape content and analyze with DeepSeek"""
    
    # Step 1: Scrape content with Supacrawler
    result = supacrawler.scrape(url, format="markdown")
    content = result.content
    
    # Step 2: Process with DeepSeek AI
    deepseek_response = requests.post(
        "https://api.deepseek.com/v1/chat/completions",
        headers={
            "Authorization": f"Bearer {deepseek_api_key}",
            "Content-Type": "application/json"
        },
        json={
            "model": "deepseek-chat",
            "messages": [
                {
                    "role": "system",
                    "content": "You are an expert content analyst. Analyze the provided web content according to the user's instructions."
                },
                {
                    "role": "user", 
                    "content": f"Content from {url}:\n\n{content}\n\nAnalysis request: {analysis_prompt}"
                }
            ],
            "temperature": 0.3
        }
    )
    
    analysis = deepseek_response.json()['choices'][0]['message']['content']
    
    return {
        'url': url,
        'content': content,
        'analysis': analysis,
        'title': result.title
    }

# Example usage
result = scrape_and_analyze(
    url="https://techcrunch.com/latest-ai-news",
    analysis_prompt="Summarize the key AI developments and identify emerging trends"
)

print(f"Analysis of {result['title']}:")
print(result['analysis'])

import requests
import json

def setup_ai_content_monitoring():
    """Setup content monitoring with DeepSeek analysis"""
    
    content_sources = [
        {
            "name": "AI Research Papers",
            "url": "https://arxiv.org/list/cs.AI/recent",
            "analysis_prompt": "Identify breakthrough AI research and potential commercial applications"
        },
        {
            "name": "Competitor Blog",
            "url": "https://competitor.com/blog",
            "analysis_prompt": "Analyze product updates, strategy changes, and market positioning"
        },
        {
            "name": "Industry News",
            "url": "https://industry-news.com/latest",
            "analysis_prompt": "Extract key market trends and regulatory changes"
        }
    ]
    
    for source in content_sources:
        # Create Supacrawler watch job with webhook
        response = requests.post("https://api.supacrawler.com/api/v1/watch",
            headers={"Authorization": f"Bearer {SUPACRAWLER_API_KEY}"},
            json={
                "url": source["url"],
                "frequency": "daily",
                "selector": "article, .post, .content",
                "notification_preference": "changes_only",
                
                # Send to AI analysis webhook
                "webhook_url": "https://your-app.com/api/ai-analysis",
                "webhook_headers": {
                    "X-Source": source["name"],
                    "X-Analysis-Prompt": source["analysis_prompt"]
                },
                
                "include_html": True
            }
        )
        
        print(f"AI monitoring setup for {source['name']}")

# Webhook handler for AI analysis
from flask import Flask, request, jsonify

app = Flask(__name__)

@app.route('/api/ai-analysis', methods=['POST'])
def analyze_content_with_deepseek():
    """Process scraped content with DeepSeek AI"""
    
    data = request.json
    source_name = data.get('headers', {}).get('X-Source')
    analysis_prompt = data.get('headers', {}).get('X-Analysis-Prompt')
    
    # Extract content changes
    new_content = data.get('new_content', '')
    
    if new_content:
        # Analyze with DeepSeek
        analysis = analyze_with_deepseek(new_content, analysis_prompt)
        
        # Store results
        save_analysis_result({
            'source': source_name,
            'url': data.get('url'),
            'content': new_content,
            'analysis': analysis,
            'timestamp': data.get('timestamp')
        })
        
        # Send notifications for important insights
        if is_important_insight(analysis):
            send_priority_alert(source_name, analysis)
    
    return jsonify({'status': 'processed'})

def analyze_with_deepseek(content, prompt):
    """Send content to DeepSeek for analysis"""
    
    response = requests.post(
        "https://api.deepseek.com/v1/chat/completions",
        headers={
            "Authorization": f"Bearer {DEEPSEEK_API_KEY}",
            "Content-Type": "application/json"
        },
        json={
            "model": "deepseek-chat",
            "messages": [
                {"role": "system", "content": "You are an expert analyst. Provide concise, actionable insights."},
                {"role": "user", "content": f"Analyze this content: {content[:4000]}\n\nFocus: {prompt}"}
            ],
            "temperature": 0.2,
            "max_tokens": 1000
        }
    )
    
    return response.json()['choices'][0]['message']['content']