developed the media analysis UI and also solved the url loading issue

app.py

@@ -146,25 +146,23 @@ def initialize_local_llm(hf_token=None):
 
 # --- DATA LOADING HELPER ---
 def load_data(file_obj, gsheet_url):
-    """Loads a DataFrame from either an uploaded file or a Google Sheets URL."""
+    """Loads a DataFrame from an uploaded file or a direct Google Sheets CSV URL."""
     if file_obj is not None:
         logging.info(f"Loading data from uploaded file: {file_obj.name}")
         return pd.read_csv(file_obj.name)
     elif gsheet_url and gsheet_url.strip():
-        logging.info(f"Loading data from Google Sheets URL.")
+        logging.info(f"Loading data directly from URL: {gsheet_url}")
         try:
-            # Manipulate the URL for direct CSV export
-            csv_url = gsheet_url.replace('/edit?usp=sharing', '/export?format=csv&gid=0')
-            response = requests.get(csv_url)
+            # FIX: Removed the unreliable .replace() logic.
+            # We now expect a direct CSV link from the user.
+            response = requests.get(gsheet_url)
             response.raise_for_status() # Raise an exception for bad status codes
             return pd.read_csv(StringIO(response.text))
         except Exception as e:
-            raise ValueError(f"Failed to load from Google Sheets URL. Please ensure the link is correct and publicly accessible. Error: {e}")
+            raise ValueError(f"Failed to load from URL. Please ensure it is a direct CSV link. Error: {e}")
     else:
         raise ValueError("Please upload a CSV file or provide a public Google Sheets URL.")
 
-print("✅ App branding, LLM initialization, and data loading functions appended to app.py")
-
 # --- MAIN ANALYSIS ENGINE ---
 
 # We will define the AI agent in the next cell. For now, this is a placeholder.
@@ -498,26 +496,28 @@ def generate_temporal_plot(date_column, progress=gr.Progress()):
         return None
 
 def generate_media_analysis(media_column):
-    """Generates a bar chart for media source analysis."""
+    """Generates a horizontal bar chart for media source analysis to prevent label overlap."""
     if not media_column:
         gr.Warning("Please select a media column to analyze.")
         return None
     df = APP_STATE.get("df")
     if df is None or media_column not in df.columns:
         return None
-
-    counts = df[media_column].value_counts().nlargest(20) # Get top 20 sources
-
-    # Using Gradio's built-in plotting for simplicity
+    
+    counts = df[media_column].value_counts().nlargest(20).sort_values() # Get top 20 and sort for a nice plot
+    
     plot_df = pd.DataFrame({'Media Source': counts.index, 'Article Count': counts.values})
+    
+    # FIX: Swapped x and y to create a horizontal plot.
     return gr.BarPlot(
         plot_df,
-        x='Media Source',
-        y='Article Count',
-        title=f'Top 20 Media Sources by Article Count',
+        x='Article Count', # The numeric value is now on the x-axis
+        y='Media Source',  # The categorical labels are now on the y-axis
+        title='Top 20 Media Sources by Article Count',
         tooltip=['Media Source', 'Article Count'],
         height=500,
-        vertical_guides=[{'value': counts.mean(), 'label': 'Average'}]
+        # FIX: Changed to horizontal_guides
+        horizontal_guides=[{'value': counts.mean(), 'label': 'Average'}]
     )
 
 def finalize_and_save():
@@ -563,7 +563,9 @@ with gr.Blocks(theme=gr.themes.Soft(), title=APP_TITLE) as app:
                 with gr.Column(scale=1):
                     gr.Markdown("### 1. Data Input")
                     file_upload = gr.File(label="Upload CSV File", file_types=[".csv"])
-                    gsheet_url = gr.Textbox(label="Or Paste Google Sheets URL", placeholder="https://docs.google.com/spreadsheets/d/...")
+                    gsheet_url = gr.Textbox(label="Or Paste Google Sheets URL",placeholder="https://docs.google.com/spreadsheets/d/e/2PACX-1vTn-mRrOCk6fww892XfziUk63pJu9g8uOdy4nHjygKXcN7oO3EAhXLMD7WZAatvoLubSPpMdQ5ymouz/pub?output=csv",
+    # FIX: Added clear instructions for the user.
+    info="How to get the link: In Google Sheets, go to File > Share > Publish to web. Select 'Comma-separated values (.csv)' and copy the generated link. for example: use this url "https://docs.google.com/spreadsheets/d/e/2PACX-1vTn-mRrOCk6fww892XfziUk63pJu9g8uOdy4nHjygKXcN7oO3EAhXLMD7WZAatvoLubSPpMdQ5ymouz/pub?output=csv")
 
                     gr.Markdown("### 2. Select Columns")
                     text_columns_checkboxgroup = gr.CheckboxGroup(label="Select Text Columns for Analysis", interactive=True)