app.py

import requests
from bs4 import BeautifulSoup
import gradio as gr
import os 


api_token = os.environ.get("TOKEN")
API_URL = "https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3-8B-Instruct"
headers = {"Authorization": f"Bearer {api_token}"}

url = "https://huggingface.co/posts" 


def query(payload):
    response = requests.post(API_URL, headers=headers, json=payload)
    return response.json()

def analyze_sentiment(text):
    output = query({
        "inputs": f'''
system
you are going to analyse the prompt that I'll give to you and tell me if they are either talking about "chat bot", "AI dev", or something else.

user
{text}

assistant
'''
    })

    if isinstance(output, list) and len(output) > 0:
        response = output[0].get('generated_text', '').strip().lower()
        
        if "chat bot" in response:
            return "chat bot"
        elif "ai dev" in response:
            return "AI dev"
        else:
            return "autre"
    return "autre"

def scrape_and_analyze(url):
    try:
        response = requests.get(url)
        if response.status_code != 200:
            return f"Erreur lors de la requête : {response.status_code}"
        
        soup = BeautifulSoup(response.text, 'html.parser')
        
        # Ajustez ce sélecteur selon la structure du site cible
        posts = soup.find_all('div', class_='cursor-pointer')
        
        categories = {"chat bot": 0, "AI dev": 0, "autre": 0}
        total_posts = 0
        result = ""
        
        for post in posts:
            total_posts += 1
            content = post.find('div', class_='relative').text.strip() if post.find('div', class_='relative') else "Pas de contenu"
            
            # Analyse du texte
            category = analyze_sentiment(content)
            categories[category] += 1
            
            # Affichage en temps réel
            print(f"Post {total_posts} analysé. Catégorie : {category}")
            print(f"Compteurs actuels : {categories}")
            print("---")
            
            # Ajout des résultats à la chaîne finale
            result += f"Post {total_posts} : Catégorie {category}\n"
        
        # Résultat final
        result += f"\nTotal des posts analysés : {total_posts}\n"
        for cat, count in categories.items():
            result += f"{cat} : {count}\n"
        
        return result
    except Exception as e:
        return f"Une erreur s'est produite : {str(e)}"

result = scrape_and_analyze(url)
print(result)