Update app.py

app.py

@@ -338,6 +338,7 @@ class PaperDownloader:
             logger.info(f"Starting download process for DOI: {doi}")
             
             try:
+                
                 pdf_content = await self.download_with_retry_async(doi)
                 if pdf_content:
                         logger.info(f"Downloaded PDF for DOI: {doi}")
@@ -346,9 +347,9 @@ class PaperDownloader:
 
                         # Escribir contenido del PDF
                         
-                        with open(filepath, 'wb') as f: # context is useful here
-                            f.write(pdf_content)
-                        
+                        with open(filepath, 'wb') as f:
+                           f.write(pdf_content)
+                       
                         logger.info(f"Saved PDF to file: {filepath}")
 
                         logger.info(f"Descarga exitosa: {filename}")
@@ -360,13 +361,14 @@ class PaperDownloader:
                         return None, f"No se pudo descargar {doi}", f'<a href="https://doi.org/{doi}">{doi}</a>'
             
             except CancelledError:
-                logger.info(f"Download Cancelled DOI: {doi}")
-                return None, f"Download cancelled {doi}","Download Cancelled" 
+               logger.info(f"Download Cancelled DOI: {doi}")
+               return None, f"Download cancelled {doi}","Download Cancelled"
             
             except Exception as e:
-                logger.error(f"Error processing {doi}: {e}")
-                return None, f"Error processing {doi}: {e}", f"Error processing {doi}: {e}"
-            
+               logger.error(f"Error processing {doi}: {e}")
+               return None, f"Error processing {doi}: {e}", f"Error processing {doi}: {e}"
+               
+    
     async def download_multiple_dois(self, dois_text, cancel_event):
             """Download multiple DOIs"""
             if not dois_text:
@@ -387,47 +389,46 @@ class PaperDownloader:
             
             for doi in dois:
                    
-                    result = await self._download_single_doi(doi,cancel_event)
-
+                    result = await self._download_single_doi(doi,cancel_event) #await all of it and only collect results
                     if cancel_event.is_set():
-                        logger.info("Downloads cancelled on multiple dois download")
-                        return None, "Downloads cancelled","Downloads cancelled",""  # early return on cancelled
+                         logger.info("Downloads cancelled on multiple dois download")
+                         return None, "Downloads cancelled","Downloads cancelled", ""# early return on cancelled
 
                     if result is None:
-                        continue
+                         continue
+            
 
                     if isinstance(result, Exception):
-                         # Excepción inesperada
-                         error_msg = f"Unexpected error: {str(result)}"
-                         logger.error(f"Error downloading {doi}: {error_msg}")
-                         failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a> - {error_msg}')
-                
+                        # Excepción inesperada
+                        error_msg = f"Unexpected error: {str(result)}"
+                        logger.error(f"Error downloading {doi}: {error_msg}")
+                        failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a> - {error_msg}')
+                    
                     elif result[0] is None:
-                       # Descarga fallida (resultado de download_single_doi_async)
+                        # Descarga fallida (resultado de download_single_doi_async)
                          error_msg = result[1]
                          logger.warning(f"Failed to download {doi}: {error_msg}")
                          failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a> - {error_msg}')
                     
                     else:
                          # Descarga exitosa
-                         filepath = result[0]
+                        filepath = result[0]
                          
                          # Generar nombre de archivo único
                          filename = f"{str(doi).replace('/', '_').replace('.', '_')}.pdf"
                          filepath_unique = os.path.join(self.output_dir, filename)
                          
                          try:
-                             # Renombrar archivo
+                              # Renombrar archivo
                               os.rename(filepath, filepath_unique)
-                            
-                            # Añadir a lista de archivos descargados
+                              
+                              # Añadir a lista de archivos descargados
                               downloaded_files.append(filepath_unique)
                               downloaded_links.append(f'<a href="https://doi.org/{doi}">{doi}</a>')
                         
                          except Exception as rename_error:
-                               logger.error(f"Error renaming file for {doi}: {rename_error}")
-                               failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a> - Error saving file')
-                
+                              logger.error(f"Error renaming file for {doi}: {rename_error}")
+                              failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a> - Error saving file')
 
                     
             # Crear archivo ZIP si hay archivos descargados
@@ -442,9 +443,10 @@ class PaperDownloader:
                     lambda: self.create_zip(zip_filename, downloaded_files)
                 )
                 logger.info(f"ZIP file created: {zip_filename}")
+                
             return  zip_filename if downloaded_files else None, "\n".join(downloaded_links),"\n".join(failed_dois), ""
-            
-    async def process_bibtex(self, bib_file, cancel_event):# removed async here
+
+    async def process_bibtex(self, bib_file, cancel_event):
             """Process BibTeX file and download papers with multiple strategies and reports UI updates using a callback"""
             # Read BibTeX file content from the uploaded object
             try:
@@ -452,7 +454,7 @@ class PaperDownloader:
                     bib_content = f.read()
             except Exception as e:
                 logger.error(f"Error reading uploaded file {bib_file.name}: {e}")
-                return None, f"Error reading uploaded file {bib_file.name}: {e}", f"Error reading uploaded file {bib_file.name}: {e}", ""
+                return None, f"Error reading uploaded file {bib_file.name}: {e}", f"Error reading uploaded file {bib_file.name}: {e}",""
 
             # Parse BibTeX data
             try:
@@ -469,47 +471,47 @@ class PaperDownloader:
             downloaded_files = []
             failed_dois = []
             downloaded_links = []
-           
+            
             for doi in dois:
-                  result = await self._download_single_doi(doi, cancel_event)
-
-                  if cancel_event.is_set():
+                    result = await self._download_single_doi(doi, cancel_event)
+                   
+                    if cancel_event.is_set():
                         logger.info("Download Cancelled in bibtex mode")
-                        return  None, "Download Cancelled", "Download Cancelled", ""#cancel if requested
-                      
-                  if result is None:
-                        continue
+                        return None, "Download Cancelled", "Download Cancelled", "" # early return on cancelled
+                                    
+                    if result is None:
+                       continue
                     
-                  if isinstance(result, Exception):
-                     # Excepción inesperada
-                     error_msg = f"Unexpected error: {str(result)}"
-                     logger.error(f"Error downloading {doi}: {error_msg}")
-                     failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a> - {error_msg}')
+                    if isinstance(result, Exception):
+                         # Excepción inesperada
+                        error_msg = f"Unexpected error: {str(result)}"
+                        logger.error(f"Error downloading {doi}: {error_msg}")
+                        failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a> - {error_msg}')
                     
-                  elif result[0] is None:
-                      # Descarga fallida (resultado de download_single_doi_async)
-                     error_msg = result[1]
-                     logger.warning(f"Failed to download {doi}: {error_msg}")
-                     failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a> - {error_msg}')
+                    elif result[0] is None:
+                        # Descarga fallida (resultado de download_single_doi_async)
+                        error_msg = result[1]
+                        logger.warning(f"Failed to download {doi}: {error_msg}")
+                        failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a> - {error_msg}')
                 
-                  else:
-                     # Descarga exitosa
-                      filepath = result[0]
-                    
-                      # Unique filename for zip
-                     filename = f"{str(doi).replace('/', '_').replace('.', '_')}_{i}.pdf"
-                     filepath_unique = os.path.join(self.output_dir, filename)
-                     os.rename(filepath, filepath_unique)
-                     downloaded_files.append(filepath_unique)
-                     downloaded_links.append(f'<a href="https://doi.org/{doi}">{doi}</a>')
-
+                    else:
+                         # Descarga exitosa
+                        filepath = result[0]
+                         
+                         # Unique filename for zip
+                        filename = f"{str(doi).replace('/', '_').replace('.', '_')}_{i}.pdf"
+                        filepath_unique = os.path.join(self.output_dir, filename)
+                        os.rename(filepath, filepath_unique)
+                        downloaded_files.append(filepath_unique)
+                        downloaded_links.append(f'<a href="https://doi.org/{doi}">{doi}</a>')
+        
             if downloaded_files:
                 zip_filename = 'papers.zip'
                 loop = asyncio.get_running_loop()
                 loop.run_in_executor(self.executor, lambda:  self.create_zip(zip_filename,downloaded_files))
                 logger.info(f"ZIP file created: {zip_filename}")
-               
-            return zip_filename, "\n".join(downloaded_links), "\n".join(failed_dois), ""
+                
+            return  zip_filename, "\n".join(downloaded_links), "\n".join(failed_dois),""
 
     def create_zip(self, zip_filename, files):
         """Crea un archivo zip con los pdfs descargados"""
@@ -526,34 +528,34 @@ class PaperDownloader:
 def create_gradio_interface():
     """Create Gradio interface for Paper Downloader"""
     downloader = PaperDownloader()
+
+
     def update_progress( message="", logs=""):
-      return  gr.Textbox.update(value=f"{message}"),gr.Textbox.update(value=f"<pre>{logs}</pre>")
+        return  gr.Textbox.update(value=f"{message}"),gr.Textbox.update(value=f"<pre>{logs}</pre>")
     
 
     async def download_papers(bib_file, doi_input, dois_input, output_file, downloaded_dois_textbox,failed_dois_textbox,logs, single_file):
-            cancel_event = asyncio.Event() # Create cancellation event for every submission.
-            downloader.cancel_event = cancel_event # store the event so that it is available to stop the process
-            if bib_file:
-                # Check file type
-                 if not bib_file.name.lower().endswith('.bib'):
-                    return  None, "Error: Please upload a .bib file", "Error: Please upload a .bib file","", None
-
-                 zip_file, downloaded_dois, failed_dois, logs_text = await downloader.process_bibtex(bib_file, cancel_event)
-                
-                 return zip_file, downloaded_dois, failed_dois, logs_text, None
-            elif doi_input:
+        cancel_event = asyncio.Event() # Create cancellation event for every submission.
+        downloader.cancel_event = cancel_event # store the event so that it is available to stop the process
+        
+        if bib_file:
+             # Check file type
+                if not bib_file.name.lower().endswith('.bib'):
+                      return  None, "Error: Please upload a .bib file", "Error: Please upload a .bib file",  "", None
+                zip_file, downloaded_dois, failed_dois, logs_text= await downloader.process_bibtex(bib_file, cancel_event)
+                return  zip_file, downloaded_dois, failed_dois, logs_text, None
 
-                  filepath, message, error = await downloader._download_single_doi(doi_input,cancel_event)
+        elif doi_input:
+            filepath, message, error= await downloader._download_single_doi(doi_input,cancel_event)
+            return  None, message, error, "", filepath
 
-                  return None, message, error,"",filepath
+        elif dois_input:
+             zip_file, downloaded_dois, failed_dois, logs_text= await downloader.download_multiple_dois(dois_input,cancel_event)
+
+             return  zip_file, downloaded_dois, failed_dois, logs_text, None
            
-            elif dois_input:
-                zip_file, downloaded_dois, failed_dois, logs_text= await downloader.download_multiple_dois(dois_input, cancel_event)
-                return  zip_file, downloaded_dois, failed_dois, logs_text, None
-          
-            else:
-                  return   None, "Please provide a .bib file, a single DOI, or a list of DOIs", "Please provide a .bib file, a single DOI, or a list of DOIs", "",  None # direct return values, no callbacks
-        
+        else:
+              return  None, "Please provide a .bib file, a single DOI, or a list of DOIs", "Please provide a .bib file, a single DOI, or a list of DOIs","", None
     
     with gr.Blocks(theme="Hev832/Applio", css="""
         .gradio-container {
@@ -612,10 +614,11 @@ def create_gradio_interface():
                  stop_button.click(lambda: downloader.cancel_download(), outputs=None)  # added function in object downloader
           
             submit_button.click(
-                download_papers,
-                inputs=[bib_file, doi_input, dois_input],
-                  outputs=[output_file, downloaded_dois_textbox, failed_dois_textbox,logs, single_file ] # the new output should be a tuple and we output logs too for debugging.
+                 download_papers,
+                 inputs=[bib_file, doi_input, dois_input],
+                 outputs=[output_file, downloaded_dois_textbox, failed_dois_textbox,logs, single_file ],  # the new output should be a tuple and we output logs too for debugging.
             )
+
     interface.title="🔬 Academic Paper Batch Downloader"
     interface.description="Upload a BibTeX file or enter DOIs to download PDFs. We'll attempt to fetch PDFs from multiple sources like Sci-Hub, Libgen, Google Scholar and Crossref. You can use any of the three inputs at any moment."