Update app.py

app.py

@@ -264,15 +264,26 @@ class PaperDownloader:
                 logger.debug(f"Crossref error for {doi}: {e}")
             return None
 
-    async def download_with_retry_async(self, doi, max_retries=3, initial_delay=2):
+    async def download_with_retry_async(self, doi, max_retries=5, initial_delay=2):
         """Downloads a paper using multiple strategies with exponential backoff and async requests"""
         pdf_content = None
         retries = 0
         delay = initial_delay
-
+    
+        # Additional download sources
+        additional_sources = [
+            f"https://sci-hub.ren/{doi}",
+            f"https://sci-hub.se/{doi}",
+            f"https://sci-hub.mksa.top/{doi}",
+            f"https://sci-hub.ru/{doi}"
+        ]
+    
         async with aiohttp.ClientSession() as session:
             while retries < max_retries and not pdf_content:
                 try:
+                    logger.info(f"Attempt {retries + 1} to download DOI: {doi}")
+                    
+                    # Try primary sources first
                     pdf_content = (
                         await self.download_paper_direct_doi_async(session, doi) or
                         await self.download_paper_scihub_async(session, doi) or
@@ -280,17 +291,47 @@ class PaperDownloader:
                         await self.download_paper_google_scholar_async(session, doi) or
                         await self.download_paper_crossref_async(session, doi)
                     )
+    
+                    # If not found, try additional Sci-Hub sources
+                    if not pdf_content and retries > 1:
+                        for source in additional_sources:
+                            try:
+                                custom_scihub = f"{source}{self.clean_doi(doi)}"
+                                logger.info(f"Trying custom source: {custom_scihub}")
+                                async with session.get(custom_scihub, headers=self.headers, timeout=15) as response:
+                                    if response.status == 200:
+                                        text = await response.text()
+                                        pdf_patterns = [
+                                            r'(https?://[^\s<>"]+?\.pdf)',
+                                            r'(https?://[^\s<>"]+?download/[^\s<>"]+)',
+                                            r'(https?://[^\s<>"]+?\/pdf\/[^\s<>"]+)',
+                                        ]
+                                        pdf_urls = []
+                                        for pattern in pdf_patterns:
+                                            pdf_urls.extend(re.findall(pattern, text))
+                                        
+                                        for pdf_url in pdf_urls:
+                                            pdf_content = await self.fetch_pdf_content(session, pdf_url)
+                                            if pdf_content:
+                                                logger.info(f"Found PDF from custom source: {pdf_url}")
+                                                break
+                            except Exception as e:
+                                logger.debug(f"Error with custom source {source}: {e}")
+    
                     if pdf_content:
                         return pdf_content
+                    
                 except Exception as e:
                     logger.error(f"Error in download attempt {retries + 1} for DOI {doi}: {e}")
-
+    
                 if not pdf_content:
                     retries += 1
                     logger.warning(f"Retry attempt {retries} for DOI: {doi} after {delay} seconds")
                     await asyncio.sleep(delay)
                     delay *= 2  # Exponential backoff
-    
+        
+        # Log detailed failure information
+        logger.warning(f"FINAL FAILURE: Could not download DOI {doi} after {max_retries} attempts")
         return None
     
     async def download_single_doi_async(self, doi, progress_callback):
@@ -515,7 +556,7 @@ def create_gradio_interface():
 
 def main():
     interface = create_gradio_interface()
-    interface.launch(share=True)
+    interface.launch()
 
 if __name__ == "__main__":
     main()