Update app.py

app.py

@@ -5,6 +5,7 @@ from docx import Document
 from datetime import datetime
 from xml.etree import ElementTree as ET
 
+# Fetch articles from PubMed
 def fetch_pubmed_articles(query, max_results, page, sort_by, journal_filter, min_year, max_year):
     if not query or query.strip() == "":
         return "❌ Please enter a search query.", "", pd.DataFrame()
@@ -55,6 +56,7 @@ def fetch_pubmed_articles(query, max_results, page, sort_by, journal_filter, min
         df = pd.DataFrame(articles)
         if df.empty:
             return "❌ No results could be parsed.", "", pd.DataFrame()
+        # Filter
         if journal_filter:
             df = df[df["Journal"].str.contains(journal_filter, case=False, na=False)]
         if min_year and str(min_year).isdigit():
@@ -63,26 +65,26 @@ def fetch_pubmed_articles(query, max_results, page, sort_by, journal_filter, min
             df = df[df["Year"] <= int(max_year)]
         if df.empty:
             return "❌ No results matched your filters.", "", pd.DataFrame()
+        # Sort
         if sort_by == "Year":
             df = df.sort_values(by="Year", ascending=False, na_position='last')
         elif sort_by == "Title":
             df = df.sort_values(by="Title", ascending=True, na_position='last')
         elif sort_by == "Journal":
             df = df.sort_values(by="Journal", ascending=True, na_position='last')
-        result_text = f"### ✅ Showing {len(df)} result(s):\n\n"
+        # Markdown rendering
+        result_text = f"**Showing {len(df)} results:**\n\n"
         for _, row in df.iterrows():
             pmid_url = f"https://pubmed.ncbi.nlm.nih.gov/{row['PMID']}/"
             result_text += f"#### [{row['Title']}]({pmid_url})\n"
             result_text += f"**Journal:** {row['Journal']}  \n"
             result_text += f"**Year:** {row['Year']}  \n"
             result_text += f"**Abstract:** {row['Abstract']}\n\n---\n"
-        return "✅ Search complete!", result_text, df.reset_index(drop=True)
-    except Exception as e:
-        return f"❌ Error: {str(e)}", "", pd.DataFrame()
+        return "✅ Search complete!", result_text, df
 
-def export_results(df_dict, file_type):
-    df = pd.DataFrame(df_dict)
-    if df.empty:
+# Export results
+def export_results(df, file_type):
+    if df is None or df.empty:
         return None
     now = datetime.now().strftime("%Y%m%d_%H%M%S")
     if file_type == "CSV":
@@ -104,40 +106,32 @@ def export_results(df_dict, file_type):
         return path
     return None
 
+# Gradio Interface
 with gr.Blocks(theme="soft") as app:
     gr.Markdown("""
-    # 🔬 **PubMed Article Search Tool**
-    Search biomedical literature from PubMed using keywords and filters.
-
-    ✅ Supports filters by journal, year range, and sorting by year/title/journal.  
-    📥 Export search results to CSV or DOCX.
-
-    ---
-
-    ### 📘 How to use:
-    1. Enter your search keywords (e.g., `brain inflammation`).
-    2. Adjust filters (journal name, min/max year, etc.).
-    3. Click **🔍 Search PubMed** to view articles.
-    4. Use buttons to **download results**.
-
-    ---
+    # 🔬 PubMed Article Search Tool
+    **Instructions:**
+    - Enter a biomedical search term (e.g., `autism risk factors`)
+    - Adjust optional filters below
+    - Click **Search PubMed** to retrieve articles
+    - Use export buttons to download results
     """)
 
     with gr.Row():
         with gr.Column():
             query_input = gr.Textbox(label="Search Query", placeholder="e.g., brain inflammation", lines=2)
-            max_results_input = gr.Number(label="Max Results", value=20, minimum=1, maximum=100)
+            max_results_input = gr.Number(label="Max Results (1–100)", value=20, minimum=1, maximum=100)
             page_input = gr.Number(label="Page Number", value=1, minimum=1)
             sort_input = gr.Dropdown(["Year", "Title", "Journal"], value="Year", label="Sort By")
             journal_filter_input = gr.Textbox(label="Journal Filter (optional)")
             min_year_input = gr.Number(label="Min Year", value=2000, minimum=1800, maximum=2100)
             max_year_input = gr.Number(label="Max Year", value=2025, minimum=1800, maximum=2100)
             search_button = gr.Button("🔍 Search PubMed")
-            status_output = gr.Markdown()
+            status_output = gr.Markdown(value="")
         with gr.Column():
-            markdown_output = gr.Markdown("ℹ️ Search results will appear here.")
-            table_output = gr.DataFrame(label="Results Table", interactive=False)
-            df_state = gr.State({})  # Store as dictionary
+            markdown_output = gr.Markdown(value="Results will appear here.")
+            table_output = gr.DataFrame(label="Results Table", visible=True, interactive=False)
+            export_df = gr.Dataframe(visible=False)  # hidden for internal export
 
     with gr.Row():
         export_csv_button = gr.Button("⬇️ Export CSV")
@@ -145,19 +139,21 @@ with gr.Blocks(theme="soft") as app:
         export_csv_output = gr.File(label="Download CSV")
         export_docx_output = gr.File(label="Download DOCX")
 
+    # Logic
     def run_search(query, max_results, page, sort_by, journal_filter, min_year, max_year):
         status, md, df = fetch_pubmed_articles(query, max_results, page, sort_by, journal_filter, min_year, max_year)
-        return status, md, df, df.to_dict()
+        return status, md, df, df
 
     search_button.click(
         fn=run_search,
         inputs=[query_input, max_results_input, page_input, sort_input, journal_filter_input, min_year_input, max_year_input],
-        outputs=[status_output, markdown_output, table_output, df_state]
+        outputs=[status_output, markdown_output, table_output, export_df]
     )
 
-    export_csv_button.click(fn=lambda df_dict: export_results(df_dict, "CSV"), inputs=[df_state], outputs=[export_csv_output])
-    export_docx_button.click(fn=lambda df_dict: export_results(df_dict, "DOCX"), inputs=[df_state], outputs=[export_docx_output])
+    export_csv_button.click(lambda df: export_results(df, "CSV"), inputs=[export_df], outputs=[export_csv_output])
+    export_docx_button.click(lambda df: export_results(df, "DOCX"), inputs=[export_df], outputs=[export_docx_output])
 
 app.launch()
 
 
+