Update app.py

app.py

@@ -5,7 +5,6 @@ from docx import Document
 from datetime import datetime
 from xml.etree import ElementTree as ET
 
-# 1. Function to fetch PubMed articles
 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()
@@ -56,24 +55,21 @@ 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 is not None and str(min_year).isdigit():
+        if min_year and str(min_year).isdigit():
             df = df[df["Year"] >= int(min_year)]
-        if max_year is not None and str(max_year).isdigit():
+        if max_year and str(max_year).isdigit():
             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')
-        # Markdown rendering
-        result_text = f"**Showing {len(df)} results:**\n\n"
+        result_text = f"### ✅ Showing {len(df)} result(s):\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"
@@ -84,9 +80,9 @@ def fetch_pubmed_articles(query, max_results, page, sort_by, journal_filter, min
     except Exception as e:
         return f"❌ Error: {str(e)}", "", pd.DataFrame()
 
-# 2. Export results to file
-def export_results(df, file_type):
-    if df is None or len(df) == 0:
+def export_results(df_dict, file_type):
+    df = pd.DataFrame(df_dict)
+    if df.empty:
         return None
     now = datetime.now().strftime("%Y%m%d_%H%M%S")
     if file_type == "CSV":
@@ -108,16 +104,21 @@ def export_results(df, file_type):
         return path
     return None
 
-# 3. Gradio Interface
 with gr.Blocks(theme="soft") as app:
     gr.Markdown("""
-    # 🔬 PubMed Article Search Tool
+    # 🔬 **PubMed Article Search Tool**
+    Search biomedical literature from PubMed using keywords and filters.
 
-    **Instructions:**
-    1. Enter your biomedical search query (e.g., `brain inflammation`) in the Search Query box.
-    2. Adjust other filters (journal, year, sort) as needed.
-    3. Click **Search PubMed** to retrieve results.
-    4. Export results to CSV or DOCX after the search.
+    ✅ 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**.
 
     ---
     """)
@@ -125,18 +126,18 @@ with gr.Blocks(theme="soft") as app:
     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 (optional)", value=2000, minimum=1800, maximum=2100)
-            max_year_input = gr.Number(label="Max Year (optional)", value=2025, minimum=1800, maximum=2100)
-            search_button = gr.Button("🔍 Search PubMed", elem_id="search-btn")
-            status_output = gr.Markdown(value="")
+            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()
         with gr.Column():
-            markdown_output = gr.Markdown(value="Results will appear here.")
-            table_output = gr.DataFrame(value=pd.DataFrame(), label="Results Table", visible=True, interactive=False)
-            df_state = gr.State(value=pd.DataFrame())
+            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
 
     with gr.Row():
         export_csv_button = gr.Button("⬇️ Export CSV")
@@ -144,12 +145,9 @@ with gr.Blocks(theme="soft") as app:
         export_csv_output = gr.File(label="Download CSV")
         export_docx_output = gr.File(label="Download DOCX")
 
-    # 4. Logic to control buttons and flow
     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
+        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()
 
     search_button.click(
         fn=run_search,
@@ -157,8 +155,9 @@ with gr.Blocks(theme="soft") as app:
         outputs=[status_output, markdown_output, table_output, df_state]
     )
 
-    export_csv_button.click(lambda df: export_results(df, "CSV"), inputs=[df_state], outputs=[export_csv_output])
-    export_docx_button.click(lambda df: export_results(df, "DOCX"), inputs=[df_state], outputs=[export_docx_output])
+    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])
 
 app.launch()
 
+