Update app.py

app.py

@@ -1,10 +1,12 @@
 import streamlit as st
 from gnews import GNews
 from transformers import GPT2Tokenizer, GPT2LMHeadModel
+from transformers import pipeline
+from gnews import GNews
 
 
 def fetch_news(topic):
-    google_news = GNews(language='en', country='US')  # You can customize this
+    google_news = GNews(language='german', country='Germany')  # You can customize this
     news_list = google_news.get_news(topic)
     
     articles = []
@@ -18,26 +20,8 @@ def fetch_news(topic):
         })
     return articles
 
-from gnews import GNews
 
-# Function to fetch the content from a URL
-def get_article_content(url):
-    try:
-        response = requests.get(url)
-        response.raise_for_status()  # Raises an HTTPError if the HTTP request returned an unsuccessful status code
-        
-        # Use BeautifulSoup to parse the HTML content
-        soup = BeautifulSoup(response.content, 'html.parser')
-        
-        # Assuming article text is within <article> tags
-        article = soup.find('article')
-        # Extract text from the article tag
-        # This may vary depending on the structure of the web page
-        article_text = article.get_text(separator=' ', strip=True) if article else 'Article content could not be retrieved.'
-        return article_text
-    except requests.RequestException as e:
-        st.error(f"Error fetching article from URL: {e}")
-        return "Could not retrieve the article text."
+
 
 def page_trending_niche():
     st.title("What is trending in my niche?")
@@ -60,32 +44,30 @@ def page_trending_niche():
 
 
 
-from transformers import pipeline
+
 
 # Initialize the summarization pipeline with BART
 summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
 
-def generate_social_media_post(article_text):
-    # Ensure the article text is not too long for the model
-    article_text = article_text[:1024]  # Truncate the text to fit the model's maximum length capacity
-    summary = summarizer(article_text, max_length=130, min_length=30, do_sample=False)[0]['summary_text']
-    return summary
+# Function to generate social media post
+def generate_social_media_post(description):
+    # Generate text with GPT-2 based on the article's description
+    generated_texts = text_generator(description, max_length=200, num_return_sequences=1)
+    return generated_texts[0]['generated_text']
 
+# Define the page for social media content generation
 def page_social_media_generator():
     st.title("Social Media Content Generator")
-    
-    # Retrieve the URL saved in the session state on the trending niche page
-    article_url = st.session_state.get('selected_article_url', '')
-    
-    if article_url:
-        st.write(f"Selected Article URL: {article_url}")
-        
-        # Fetch the content of the article from the URL
-        article_text = get_article_content(article_url)
+
+    # Retrieve the description saved in the session state on the trending niche page
+    description = st.session_state.get('selected_article_description', '')
+
+    if description:
+        st.write(f"Selected Article Description: {description}")
         
-        if article_text and st.button('Generate Social Media Post'):
+        if st.button('Generate Social Media Post'):
             with st.spinner('Generating...'):
-                post_content = generate_social_media_post(article_text)
+                post_content = generate_social_media_post(description)
                 st.success('Generated Content:')
                 st.write(post_content)
     else: