Update app.py

app.py

@@ -1,15 +1,15 @@
 import gradio as gr
 import requests
 import pandas as pd
-import io
-from docx import Document
 import tempfile
+from docx import Document
 
 API_BASE_URL = "https://pubmed-api-jwfq.onrender.com/search_pubmed"
+global_df = None  # Global variable to store search results
 
-global_df = None  # Global variable to store search results for export
 
-def fetch_pubmed_articles(query, max_results=10, page=1, sort_by="Year", filter_journal="All", min_year=None, max_year=None):
+def fetch_pubmed_articles(query, max_results=10, page=1, sort_by="Year",
+                          filter_journal="All", min_year=None, max_year=None):
     """
     Fetches PubMed articles and applies sorting and filtering.
     """
@@ -21,7 +21,6 @@ def fetch_pubmed_articles(query, max_results=10, page=1, sort_by="Year", filter_
             return f"⚠️ API Error: {response.status_code} - {response.text}", None
 
         articles = response.json()
-
         if not articles:
             return "No articles found for this query.", None
 
@@ -31,17 +30,17 @@ def fetch_pubmed_articles(query, max_results=10, page=1, sort_by="Year", filter_
             except:
                 article["Year"] = 0
 
-        # Apply journal filtering
+        # Filter by journal
         if filter_journal and filter_journal != "All":
             articles = [a for a in articles if filter_journal.lower() in a['Journal'].lower()]
 
-        # Apply year filtering
+        # Filter by year
         if min_year:
             articles = [a for a in articles if a["Year"] >= int(min_year)]
         if max_year:
             articles = [a for a in articles if a["Year"] <= int(max_year)]
 
-        # Apply sorting
+        # Sorting
         if sort_by == "Year":
             articles.sort(key=lambda x: x["Year"], reverse=True)
         elif sort_by == "Title":
@@ -49,7 +48,7 @@ def fetch_pubmed_articles(query, max_results=10, page=1, sort_by="Year", filter_
         elif sort_by == "Journal":
             articles.sort(key=lambda x: x["Journal"])
 
-        # Format results
+        # Format markdown results
         formatted_results = []
         for article in articles:
             formatted_results.append(
@@ -68,65 +67,85 @@ def fetch_pubmed_articles(query, max_results=10, page=1, sort_by="Year", filter_
         return f"⚠️ Error fetching data: {str(e)}", None
 
 
-
 def export_results(df, format_type):
     """
-    Exports search results as a CSV or DOCX file.
-    - Returns the file path instead of BytesIO to avoid TypeError in Gradio.
+    Safely exports the given DataFrame to a temporary file (CSV or DOCX).
     """
+    import traceback
+
     if df is None or df.empty:
+        print("⚠️ Warning: DataFrame is empty or None. Nothing to export.")
         return None
 
-    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=f".{format_type.lower()}")
-    temp_file_path = temp_file.name  # Store the temporary file path
+    try:
+        suffix = f".{format_type.lower()}"
+        temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=suffix)
+        temp_file_path = temp_file.name
+
+        if format_type == "CSV":
+            df.to_csv(temp_file_path, index=False)
+
+        elif format_type == "DOCX":
+            doc = Document()
+            doc.add_heading("PubMed Search Results", level=1)
+            for _, row in df.iterrows():
+                doc.add_heading(row.get("Title", "Untitled"), level=2)
+                doc.add_paragraph(f"📖 Journal: {row.get('Journal', 'Unknown')} ({row.get('Year', '')})")
+                doc.add_paragraph(f"👨‍🔬 Authors: {row.get('Authors', 'N/A')}")
+                doc.add_paragraph(f"🔗 Link: {row.get('PubMed_URL', 'N/A')}")
+                doc.add_paragraph(f"📄 Abstract: {row.get('Abstract', '')}")
+                doc.add_paragraph("---")
+            doc.save(temp_file_path)
+
+        temp_file.close()
+        return temp_file_path
+
+    except Exception as e:
+        print("❌ Export failed:", str(e))
+        traceback.print_exc()
+        return None
+
+
+def export_csv():
+    if global_df is not None:
+        file_path = export_results(global_df, "CSV")
+        if isinstance(file_path, str):
+            return file_path
+    return None
 
-    if format_type == "CSV":
-        df.to_csv(temp_file_path, index=False)
-    elif format_type == "DOCX":
-        doc = Document()
-        doc.add_heading("PubMed Search Results", level=1)
-        for _, row in df.iterrows():
-            doc.add_heading(row["Title"], level=2)
-            doc.add_paragraph(f"📖 Journal: {row['Journal']} ({row['Year']})")
-            doc.add_paragraph(f"👨‍🔬 Authors: {row['Authors']}")
-            doc.add_paragraph(f"🔗 Link: {row['PubMed_URL']}")
-            doc.add_paragraph(f"📄 Abstract: {row['Abstract']}")
-            doc.add_paragraph("---")
-        doc.save(temp_file_path)
 
-    temp_file.close()  # Close the file before returning the path
-    return temp_file_path  # Return file path instead of BytesIO
+def export_docx():
+    if global_df is not None:
+        file_path = export_results(global_df, "DOCX")
+        if isinstance(file_path, str):
+            return file_path
+    return None
+
+
+def search_and_display(query, max_results, page, sort_by, journal_filter, min_year, max_year):
+    global global_df
+    result_text, df = fetch_pubmed_articles(query, max_results, page, sort_by, journal_filter, min_year, max_year)
+    global_df = df
+    print("🔍 Search completed. DataFrame loaded with", len(df) if df is not None else 0, "articles.")
+    return result_text
 
 
 with gr.Blocks() as app:
     gr.Markdown("""
-    # 🔍 **PubMed Search Tool with Advanced Features**
-
-    ## 📖 **How to Use This App**
-    1️⃣ **Enter a Search Query** *(e.g., "Deep Learning in Psychiatry")*
-    2️⃣ **Set the Number of Results & Page Number** *(Default: 10 results per page)*
-    3️⃣ **Choose Sorting Option** *(Year, Title, or Journal - Default: Year)*
-    4️⃣ **(Optional) Filter by Journal Name** *(e.g., "Nature", "JAMA")*
-    5️⃣ **(Optional) Filter by Year Range** *(Set min & max year, e.g., 2015 - 2023)*
-    6️⃣ **Click "🔍 Search" to fetch results**
-    7️⃣ **Click "📂 Export as CSV" or "📄 Export as Word DOCX" to save articles**
-    8️⃣ **Click "📄 Show Abstract" under each result to expand full abstract**
-
-    ## ⚠️ **Important Notes**
-    - **Sorting & Filtering can be combined** *(e.g., show only "Nature" articles from 2020-2024, sorted by Title)*
-    
+    # 🔍 **PubMed Search Tool with Export Options**
+    ### Search biomedical literature and export results as CSV or Word DOCX.
     """)
 
     with gr.Row():
-        query_input = gr.Textbox(label="🔎 Search Query", placeholder="Enter topic (e.g., 'Neural Networks in Psychiatry')", lines=1)
-
+        query_input = gr.Textbox(label="🔎 Search Query", placeholder="e.g., 'Deep Learning in Psychiatry'")
+    
     with gr.Row():
-        max_results_input = gr.Slider(1, 50, value=10, step=1, label="📄 Number of Results per Page")
-        page_input = gr.Slider(1, 200, value=1, step=1, label="📄 Page Number")
+        max_results_input = gr.Slider(1, 50, value=10, step=1, label="📄 Results per Page")
+        page_input = gr.Slider(1, 100, value=1, step=1, label="📄 Page Number")
 
     with gr.Row():
-        sort_input = gr.Dropdown(choices=["Year", "Title", "Journal"], value="Year", label="🔄 Sort By")
-        journal_filter_input = gr.Textbox(label="🎯 Filter by Journal (Optional)", placeholder="Enter journal name or leave blank")
+        sort_input = gr.Dropdown(["Year", "Title", "Journal"], value="Year", label="🔄 Sort By")
+        journal_filter_input = gr.Textbox(label="🎯 Filter by Journal (optional)", placeholder="e.g., Nature")
 
     with gr.Row():
         min_year_input = gr.Number(label="📅 Min Year", value=None)
@@ -139,29 +158,18 @@ with gr.Blocks() as app:
 
     results_output = gr.HTML()
     export_csv_output = gr.File(label="Download CSV")
-    export_docx_output = gr.File(label="Download Word DOCX")
-
-    def search_and_display(query, max_results, page, sort_by, journal_filter, min_year, max_year):
-        global global_df
-        result_text, df = fetch_pubmed_articles(query, max_results, page, sort_by, journal_filter, min_year, max_year)
-        global_df = df
-        return result_text
-
-    def export_csv():
-        if global_df is not None:
-            return export_results(global_df, "CSV")
-
-    def export_docx():
-        if global_df is not None:
-            return export_results(global_df, "DOCX")
+    export_docx_output = gr.File(label="Download DOCX")
 
     search_button.click(search_and_display,
-                        inputs=[query_input, max_results_input, page_input, sort_input, journal_filter_input, min_year_input, max_year_input],
+                        inputs=[query_input, max_results_input, page_input,
+                                sort_input, journal_filter_input, min_year_input, max_year_input],
                         outputs=results_output)
 
     export_csv_button.click(export_csv, outputs=export_csv_output)
     export_docx_button.click(export_docx, outputs=export_docx_output)
 
+
 if __name__ == "__main__":
-    app.launch(inbrowser=True)
+    app.launch()
+