inital setup and fixes changed news api

app.py

@@ -1,12 +1,11 @@
 import gradio as gr
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
-from newspaper import Article
 import nltk
 from datetime import datetime, timedelta
 import requests
 from bs4 import BeautifulSoup
-import re
+import json
 
 # Download required NLTK data
 try:
@@ -35,8 +34,9 @@ def load_models():
     
     return generator_tokenizer, generator, sentiment_analyzer, bias_detector
 
-# Function to fetch recent news
+# Simplified news fetching function
 def fetch_recent_news(query, num_articles=3):
+    # Using Google News RSS feed
     base_url = "https://news.google.com/rss/search"
     params = {
         'q': query,
@@ -46,27 +46,23 @@ def fetch_recent_news(query, num_articles=3):
     }
     
     try:
-        response = requests.get(base_url, params=params)
+        response = requests.get(base_url, params=params, timeout=5)
         soup = BeautifulSoup(response.content, 'xml')
-        items = soup.find_all('item')[:num_articles]
+        items = soup.find_all('item', limit=num_articles)
         
         news_data = []
         for item in items:
             try:
-                article = Article(item.link.text)
-                article.download()
-                article.parse()
-                article.nlp()
                 news_data.append({
-                    'title': article.title,
-                    'summary': article.summary
+                    'title': item.title.text,
+                    'description': item.description.text if item.description else ""
                 })
             except:
                 continue
         
         return news_data
     except Exception as e:
-        return [{'title': 'Error fetching news', 'summary': str(e)}]
+        return [{'title': f'Using default context due to error: {str(e)}', 'description': ''}]
 
 # Generate content with ethical oversight
 def generate_content(
@@ -87,7 +83,7 @@ def generate_content(
     
     # Get recent news for context
     news_data = fetch_recent_news(f"{product_name} {target_audience}")
-    news_context = "\n".join([f"Recent news: {item['title']}" for item in news_data])
+    news_context = "\n".join([f"Recent context: {item['title']}" for item in news_data])
     
     # Create prompt
     prompt = f"""
@@ -124,6 +120,10 @@ def generate_content(
         # Clean up text
         text = text.replace(prompt, "").strip()
         
+        # Skip if text is too short
+        if len(text) < 10:
+            continue
+            
         # Check sentiment
         sentiment = sentiment_analyzer(text)[0]
         
@@ -171,6 +171,9 @@ def create_interface():
             bias_detector
         )
         
+        if not results:
+            return "No suitable content generated. Please try again with different parameters."
+        
         output = ""
         for i, content in enumerate(results, 1):
             output += f"\nVersion {i}:\n"
@@ -185,17 +188,17 @@ def create_interface():
     iface = gr.Interface(
         fn=process_input,
         inputs=[
-            gr.Textbox(label="Product Name"),
-            gr.Textbox(label="Product Description", lines=3),
-            gr.Textbox(label="Target Audience"),
-            gr.Textbox(label="Key Features", lines=2),
-            gr.Textbox(label="Unique Benefits", lines=2),
+            gr.Textbox(label="Product Name", placeholder="Enter product name"),
+            gr.Textbox(label="Product Description", lines=3, placeholder="Brief description of your product"),
+            gr.Textbox(label="Target Audience", placeholder="Who is this product for?"),
+            gr.Textbox(label="Key Features", lines=2, placeholder="Main features of your product"),
+            gr.Textbox(label="Unique Benefits", lines=2, placeholder="What makes your product special?"),
             gr.Radio(
                 choices=["Twitter", "Instagram"],
                 label="Platform",
                 value="Twitter"
             ),
-            gr.Textbox(label="Tone (e.g., professional, casual, friendly)"),
+            gr.Textbox(label="Tone", placeholder="e.g., professional, casual, friendly"),
         ],
         outputs=gr.Textbox(label="Generated Content", lines=10),
         title="Ethimar - AI Marketing Content Generator",

requirements.txt

@@ -1,7 +1,8 @@
 gradio
 torch
 transformers
-newspaper3k
+newsapi-python
 nltk
 requests
-beautifulsoup4
+beautifulsoup4
+lxml