Update app.py

app.py

@@ -1,16 +1,12 @@
 import requests
-from bs4 import BeautifulSoup
-import gradio as gr
-import os 
-
+import json
+import os
 
+# Votre analyseur de post
 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()
@@ -19,66 +15,115 @@ 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.
+You're going to deeply analyze the texts I'm going to give you and you're only going to tell me which category they belong to by answering only the words that correspond to the following categories:
+For posts that talk about chat models/LLM, return "Chatmodel/LLM"
+For posts that talk about image generation models, return "image_generation"
+For texts that ask for information from the community, return "questions"
+For posts about fine-tuning or model adjustment, return "fine_tuning"
+For posts related to ethics and bias in AI, return "ethics_bias"
+For posts about datasets and data preparation, return "datasets"
+For posts about tools and libraries, return "tools_libraries"
+For posts containing tutorials and guides, return "tutorials_guides"
+For posts about debugging and problem-solving, return "debugging"
+Respond only with the category name, without any additional explanation or text.
 
 user
 {text}
 
 assistant
+
 '''
     })
 
     if isinstance(output, list) and len(output) > 0:
         response = output[0].get('generated_text', '').strip().lower()
+        return response
+
+    return "Erreur: Réponse vide ou non valide"
+
+def fetch_posts(limit=10, max_posts=50):
+    url = "https://huggingface.co/api/posts"
+    params = {'limit': limit}
+    offset = 0
+    all_posts = []
+
+    while len(all_posts) < max_posts:
+        params['offset'] = offset
+        response = requests.get(url, params=params)
+        data = response.json()
         
-        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"
+        if not data['socialPosts']:
+            break
         
-        return result
-    except Exception as e:
-        return f"Une erreur s'est produite : {str(e)}"
+        all_posts.extend(data['socialPosts'])
+        offset += len(data['socialPosts'])
+
+    return all_posts[:max_posts]
+
+def display_post(post):
+    print(f"\n{'=' * 50}")
+    print(f"Contenu:\n{post['rawContent']}")
+    print(f"Likes: {sum(reaction['count'] for reaction in post['reactions'])}")
+    print(f"URL: {post['url']}")
+    print(f"Analyse: {post.get('analysis', 'Analyse non disponible')}")
+    print(f"Catégorie: {post.get('category', 'Non analysé')}")
+    print(f"{'=' * 50}\n")
+
+# Récupérer les posts
+posts = fetch_posts(limit=10, max_posts=30)  # Récupère jusqu'à 30 posts
+
+# Stocker les posts dans des variables différentes
+post_variables = {f'post_{i}': post for i, post in enumerate(posts)}
+
+# Dictionnaire pour compter les catégories
+category_count = {
+    'questions': 0,
+    'Chatmodel/LLM': 0,
+    'image_generation': 0,
+    'fine_tuning': 0,
+    'ethics_bias': 0,
+    'datasets': 0,
+    'tools_libraries': 0,
+    'tutorials_guides': 0,
+    'debugging': 0,
+    'Erreur: Réponse ambiguë': 0,
+    'Erreur: Réponse vide ou non valide': 0
+}
+
+# Analyser chaque post et ajouter les résultats de l'analyse au dictionnaire
+for key in post_variables:
+    category = analyze_sentiment(post_variables[key]['rawContent'])
+    
+    if category == 'questions':
+        category_count['questions'] += 2
+    elif category == 'Chatmodel/LLM':
+        category_count['Chatmodel/LLM'] += 2
+    elif category == 'image_generation':
+        category_count['image_generation'] += 2
+    elif category == 'fine_tuning':
+        category_count['fine_tuning'] += 2
+    elif category == 'ethics_bias':
+        category_count['ethics_bias'] += 2
+    elif category == 'datasets':
+        category_count['datasets'] += 2
+    elif category == 'tools_libraries':
+        category_count['tools_libraries'] += 2
+    elif category == 'tutorials_guides':
+        category_count['tutorials_guides'] += 2
+    elif category == 'debugging':
+        category_count['debugging'] += 2
+    elif category == "Erreur: Réponse ambiguë":
+        category_count["Erreur: Réponse ambiguë"] += 2
+    elif category == "Erreur: Réponse vide ou non valide":
+        category_count["Erreur: Réponse vide ou non valide"] += 2
+
+    post_variables[key]['category'] = category
 
-result = scrape_and_analyze(url)
-print(result)
+# Imprimer un post spécifique
+post_to_print = 'post_2'  # Par exemple, le troisième post (index 2)
+display_post(post_variables[post_to_print])
 
+# Afficher le nombre de posts par catégorie
+print("\nNombre de posts par catégorie:")
+for category, count in category_count.items():
+    print(f"{category}: {count}")