Update app.py

app.py

@@ -263,7 +263,7 @@ class PaperDownloader:
             except Exception as e:
                 logger.debug(f"Crossref error for {doi}: {e}")
             return None
-        
+
     async def download_with_retry_async(self, doi, max_retries=3, initial_delay=2):
         """Downloads a paper using multiple strategies with exponential backoff and async requests"""
         pdf_content = None
@@ -294,36 +294,37 @@ class PaperDownloader:
         return None
     
     async def download_single_doi_async(self, doi, progress_callback):
-        """Downloads a single paper using a DOI"""
-        if not doi:
-            return None, "Error: DOI not provided", "Error: DOI not provided"
-
-        try:
-            pdf_content = await self.download_with_retry_async(doi)
-
-            if pdf_content:
-                if doi is None:
-                     return None, "Error: DOI not provided", "Error: DOI not provided"
-                filename = f"{str(doi).replace('/', '_').replace('.', '_')}.pdf"
-                filepath = os.path.join(self.output_dir, filename)
-                loop = asyncio.get_running_loop()
-                await loop.run_in_executor(self.executor, lambda: open(filepath, 'wb').write(pdf_content))
+            """Downloads a single paper using a DOI, and updates the given progress_callback"""
+            if not doi:
+                return None, "Error: DOI not provided", "Error: DOI not provided"
+    
+            try:
+                pdf_content = await self.download_with_retry_async(doi)
+    
+                if pdf_content:
+                    if doi is None:
+                        return None, "Error: DOI not provided", "Error: DOI not provided"
+                    filename = f"{str(doi).replace('/', '_').replace('.', '_')}.pdf"
+                    filepath = os.path.join(self.output_dir, filename)
 
-                logger.info(f"Successfully downloaded: {filename}")
-                progress_callback(f"Successfully downloaded: <a href='https://doi.org/{doi}'>{doi}</a>")
-                return filepath, f'<a href="https://doi.org/{doi}">{doi}</a>', ""
-            else:
-                logger.warning(f"Could not download: {doi}")
-                progress_callback(f"Could not download:  <a href='https://doi.org/{doi}'>{doi}</a>")
-                return None, f"Could not download {doi}", f'<a href="https://doi.org/{doi}">{doi}</a>'
-                
-        except Exception as e:
+                    loop = asyncio.get_running_loop()
+                    await loop.run_in_executor(self.executor, lambda: open(filepath, 'wb').write(pdf_content))
+                    
+                    logger.info(f"Successfully downloaded: {filename}")
+                    progress_callback(f"Successfully downloaded: <a href='https://doi.org/{doi}'>{doi}</a>")
+                    return filepath, f'<a href="https://doi.org/{doi}">{doi}</a>', ""
+                else:
+                    logger.warning(f"Could not download: {doi}")
+                    progress_callback(f"Could not download:  <a href='https://doi.org/{doi}'>{doi}</a>")
+                    return None, f"Could not download {doi}", f'<a href="https://doi.org/{doi}">{doi}</a>'
+    
+            except Exception as e:
                 logger.error(f"Error processing {doi}: {e}")
                 progress_callback(f"Error processing {doi}:  <a href='https://doi.org/{doi}'>{doi}</a> {e}")
                 return None, f"Error processing {doi}: {e}", f"Error processing {doi}: {e}"
     
     async def download_multiple_dois_async(self, dois_text, progress_callback):
-            """Downloads multiple papers from a list of DOIs and updates the UI using the progress_callback"""
+            """Downloads multiple papers from a list of DOIs and uses a callback for UI"""
             if not dois_text:
                 return None, "Error: No DOIs provided", "Error: No DOIs provided"
     
@@ -334,32 +335,32 @@ class PaperDownloader:
             downloaded_files = []
             failed_dois = []
             downloaded_links = []
-            
+           
             for i, doi in enumerate(dois):
                  filepath, success_message, fail_message = await self.download_single_doi_async(doi, progress_callback)
                  if filepath:
-                        # 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>')
+                    # 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:
-                        failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a>')
-
+                     failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a>')
+            
             if downloaded_files:
-                    zip_filename = 'papers.zip'
-                    loop = asyncio.get_running_loop()
-                    await loop.run_in_executor(self.executor, lambda: self.create_zip(zip_filename,downloaded_files) )
-                    logger.info(f"ZIP file created: {zip_filename}")
-
+                zip_filename = 'papers.zip'
+                loop = asyncio.get_running_loop()
+                await 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 if downloaded_files else None, "\n".join(downloaded_links), "\n".join(failed_dois)
-
+    
     def create_zip(self, zip_filename, downloaded_files):
-            with zipfile.ZipFile(zip_filename, 'w') as zipf:
+        with zipfile.ZipFile(zip_filename, 'w') as zipf:
                 for file_path in downloaded_files:
                     zipf.write(file_path, arcname=os.path.basename(file_path))
-        
+
     async def process_bibtex_async(self, bib_file, progress_callback):
             """Process BibTeX file and download papers with multiple strategies and reports UI updates using a callback"""
             # Read BibTeX file content from the uploaded object
@@ -385,25 +386,27 @@ class PaperDownloader:
             downloaded_files = []
             failed_dois = []
             downloaded_links = []
+    
+            tasks = [self.download_single_doi_async(doi, progress_callback) for doi in dois]
+            results = await asyncio.gather(*tasks)
 
-            for i, doi in enumerate(dois):
-                  filepath, success_message, fail_message = await self.download_single_doi_async(doi, progress_callback)
-                  if filepath:
-                      # 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:
-                      failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a>')
-
+            for i, (filepath, success_message, fail_message) in enumerate(results):
+                    if filepath:
+                        # Unique filename for zip
+                        filename = f"{str(dois[i]).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/{dois[i]}">{dois[i]}</a>')
+                    else:
+                        failed_dois.append(f'<a href="https://doi.org/{dois[i]}">{dois[i]}</a>')
+            
             if downloaded_files:
-                    zip_filename = 'papers.zip'
-                    loop = asyncio.get_running_loop()
-                    await loop.run_in_executor(self.executor, lambda:  self.create_zip(zip_filename,downloaded_files))
-                    logger.info(f"ZIP file created: {zip_filename}")
-
+                zip_filename = 'papers.zip'
+                loop = asyncio.get_running_loop()
+                await 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)
 
 def create_gradio_interface():
@@ -415,17 +418,19 @@ def create_gradio_interface():
                 # 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_path, downloaded_dois, failed_dois = await downloader.process_bibtex_async(bib_file, progress.update)
+
                 return zip_path, downloaded_dois, failed_dois, None
             elif doi_input:
                 filepath, message, failed_doi = await downloader.download_single_doi_async(doi_input,progress.update)
                 return None, message, failed_doi, filepath
             elif dois_input:
-                zip_path, downloaded_dois, failed_dois = await downloader.download_multiple_dois_async(dois_input, progress.update)
-                return zip_path, downloaded_dois, failed_dois, None
+                 zip_path, downloaded_dois, failed_dois = await downloader.download_multiple_dois_async(dois_input, progress.update)
+                 return zip_path, downloaded_dois, failed_dois, 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
+                 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
 
 
     # Gradio Interface
@@ -435,6 +440,7 @@ def create_gradio_interface():
             gr.File(file_types=['.bib'], label="Upload BibTeX File"),
             gr.Textbox(label="Enter Single DOI", placeholder="10.xxxx/xxxx"),
             gr.Textbox(label="Enter Multiple DOIs (one per line)", placeholder="10.xxxx/xxxx\n10.yyyy/yyyy\n...")
+           
         ],
         outputs=[
             gr.File(label="Download Papers (ZIP) or Single PDF"),