Update app.py

app.py

@@ -5,10 +5,11 @@ from docx import Document
 from datetime import datetime
 from xml.etree import ElementTree as ET
 
-# Fetch articles from PubMed
+# ------------------- PubMed Fetching Logic -------------------
 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()
+
     try:
         base_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi"
         params = {
@@ -21,9 +22,11 @@ def fetch_pubmed_articles(query, max_results, page, sort_by, journal_filter, min
         response = requests.get(base_url, params=params, timeout=15)
         if response.status_code != 200:
             return f"❌ Error: {response.status_code}", "", pd.DataFrame()
+
         id_list = response.json().get("esearchresult", {}).get("idlist", [])
         if not id_list:
             return "❌ No results found.", "", pd.DataFrame()
+
         ids = ",".join(id_list)
         fetch_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi"
         fetch_params = {
@@ -34,6 +37,7 @@ def fetch_pubmed_articles(query, max_results, page, sort_by, journal_filter, min
         fetch_response = requests.get(fetch_url, params=fetch_params, timeout=15)
         if fetch_response.status_code != 200:
             return f"❌ Error fetching details.", "", pd.DataFrame()
+
         root = ET.fromstring(fetch_response.content)
         articles = []
         for article in root.findall(".//PubmedArticle"):
@@ -53,10 +57,11 @@ def fetch_pubmed_articles(query, max_results, page, sort_by, journal_filter, min
                 })
             except Exception:
                 continue
+
         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():
@@ -65,14 +70,14 @@ 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')
+            df = df.sort_values(by="Year", ascending=False)
         elif sort_by == "Title":
-            df = df.sort_values(by="Title", ascending=True, na_position='last')
+            df = df.sort_values(by="Title", ascending=True)
         elif sort_by == "Journal":
-            df = df.sort_values(by="Journal", ascending=True, na_position='last')
-        # Markdown rendering
+            df = df.sort_values(by="Journal", ascending=True)
+
         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']}/"
@@ -80,11 +85,15 @@ def fetch_pubmed_articles(query, max_results, page, sort_by, journal_filter, min
             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
 
-# Export results
+        return "✅ Search complete!", result_text, df.reset_index(drop=True)
+
+    except Exception as e:
+        return f"❌ Error: {str(e)}", "", pd.DataFrame()
+
+# ------------------- Export Logic -------------------
 def export_results(df, file_type):
-    if df is None or df.empty:
+    if df is None or len(df) == 0:
         return None
     now = datetime.now().strftime("%Y%m%d_%H%M%S")
     if file_type == "CSV":
@@ -106,54 +115,61 @@ def export_results(df, file_type):
         return path
     return None
 
-# Gradio Interface
-with gr.Blocks(theme="soft") as app:
+# ------------------- Spinner Toggle -------------------
+def toggle_spinner(show: bool):
+    return gr.update(visible=show)
+
+# ------------------- Gradio App -------------------
+with gr.Blocks(title="PubMed Search Tool") as app:
     gr.Markdown("""
     # 🔬 PubMed Article Search Tool
+    Search biomedical literature from PubMed with filtering and export options.
+
     **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
+    1. Enter a search term like `"brain inflammation"` or `"COVID vaccine"`  
+    2. Adjust optional filters (journal name, year, sorting)  
+    3. Click **🔍 Search PubMed** to get article summaries  
+    4. Export to **CSV** or **Word** using the buttons below  
     """)
 
     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 (1–100)", value=20, minimum=1, maximum=100)
+            max_results_input = gr.Number(label="Max Results", 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)
+            min_year_input = gr.Number(label="Min Year (optional)", value=2000)
+            max_year_input = gr.Number(label="Max Year (optional)", value=2025)
             search_button = gr.Button("🔍 Search PubMed")
-            status_output = gr.Markdown(value="")
-        with gr.Column():
-            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
+            status_output = gr.Markdown()
+            spinner = gr.Markdown("⏳ Please wait...", visible=False)
 
-    with gr.Row():
-        export_csv_button = gr.Button("⬇️ Export CSV")
-        export_docx_button = gr.Button("⬇️ Export DOCX")
-        export_csv_output = gr.File(label="Download CSV")
-        export_docx_output = gr.File(label="Download DOCX")
+        with gr.Column():
+            markdown_output = gr.Markdown("Search results will appear here.")
+            table_output = gr.DataFrame(label="Results Table", interactive=False)
+            export_csv_button = gr.Button("⬇️ Export CSV")
+            export_docx_button = gr.Button("⬇️ Export DOCX")
+            export_csv_output = gr.File(label="Download CSV")
+            export_docx_output = gr.File(label="Download DOCX")
 
-    # Logic
+    # ------------- Define search and export interaction -------------
     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
+        return fetch_pubmed_articles(query, max_results, page, sort_by, journal_filter, min_year, max_year)
 
     search_button.click(
+        lambda: toggle_spinner(True), inputs=[], outputs=[spinner], show_progress=False
+    ).then(
         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, export_df]
+        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],
+        show_progress=True
+    ).then(
+        lambda: toggle_spinner(False), inputs=[], outputs=[spinner], show_progress=False
     )
 
-    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])
+    export_csv_button.click(lambda df: export_results(df, "CSV"), inputs=[table_output], outputs=[export_csv_output])
+    export_docx_button.click(lambda df: export_results(df, "DOCX"), inputs=[table_output], outputs=[export_docx_output])
 
 app.launch()
-
-
-