Update app.py

app.py

@@ -10,18 +10,21 @@ from urllib.parse import quote, urlencode
 import gradio as gr
 from bs4 import BeautifulSoup
 import io
+import asyncio
+import aiohttp
 
 # Configure logging
-logging.basicConfig(level=logging.INFO, 
+logging.basicConfig(level=logging.INFO,
                     format='%(asctime)s - %(levelname)s: %(message)s')
 logger = logging.getLogger(__name__)
 
+
 class PaperDownloader:
     def __init__(self, output_dir='papers'):
         self.output_dir = output_dir
         os.makedirs(output_dir, exist_ok=True)
-        
-         # Updated download sources
+
+        # Updated download sources
         self.download_sources = [
             'https://sci-hub.ee/',
             'https://sci-hub.st/',
@@ -35,15 +38,222 @@ class PaperDownloader:
         # Request headers
         self.headers = {
             'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36',
-            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8'
+            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
+            'Accept-Language': 'en-US,en;q=0.9',
         }
 
     def clean_doi(self, doi):
         """Clean and encode DOI for URL"""
         if not isinstance(doi, str):
-           return None
+            return None
         return quote(doi.strip()) if doi else None
 
+    async def fetch_with_headers(self, session, url, timeout=10):
+        """Utility method to fetch an URL with headers and timeout"""
+        try:
+            async with session.get(url, headers=self.headers, timeout=timeout, allow_redirects=True) as response:
+                response.raise_for_status()
+                return await response.text(), response.headers
+        except Exception as e:
+            logger.debug(f"Error fetching {url}: {e}")
+            return None, None
+    
+    
+    async def download_paper_direct_doi_async(self, session, doi):
+      """Attempt to download the pdf from the landing page of the doi"""
+      if not doi:
+         return None
+      
+      try:
+         doi_url = f"https://doi.org/{self.clean_doi(doi)}"
+         text, headers = await self.fetch_with_headers(session, doi_url, timeout=15)
+         if not text:
+            return None
+
+         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:
+           try:
+               pdf_response = await session.get(pdf_url, headers=self.headers, timeout=10)
+               if 'application/pdf' in pdf_response.headers.get('Content-Type', ''):
+                    logger.debug(f"Found PDF from: {pdf_url}")
+                    return await pdf_response.read()
+           except Exception as e:
+               logger.debug(f"Error downloading PDF from {pdf_url}: {e}")
+
+
+      except Exception as e:
+           logger.debug(f"Error trying to get the PDF from {doi}: {e}")
+      
+      return None
+
+    async def download_paper_scihub_async(self, session, doi):
+        """Improved method to download paper from Sci-Hub using async requests"""
+        if not doi:
+            logger.warning("DOI not provided")
+            return None
+
+        for base_url in self.download_sources:
+            try:
+                scihub_url = f"{base_url}{self.clean_doi(doi)}"
+                text, headers = await self.fetch_with_headers(session, scihub_url, timeout=15)
+                if not text:
+                    continue
+
+                # Search for multiple PDF URL patterns
+                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))
+
+                # Try downloading from found URLs
+                for pdf_url in pdf_urls:
+                    try:
+                        pdf_response = await session.get(pdf_url, headers=self.headers, timeout=10)
+                        # Verify if it's a PDF
+                        if 'application/pdf' in pdf_response.headers.get('Content-Type', ''):
+                            logger.debug(f"Found PDF from: {pdf_url}")
+                            return await pdf_response.read()
+                    except Exception as e:
+                        logger.debug(f"Error downloading PDF from {pdf_url}: {e}")
+
+            except Exception as e:
+                logger.debug(f"Error trying to download {doi} from {base_url}: {e}")
+
+        return None
+
+    async def download_paper_libgen_async(self, session, doi):
+        """Download from Libgen, handles the query and the redirection"""
+        if not doi:
+            return None
+
+        base_url = 'https://libgen.rs/scimag/'
+        try:
+            search_url = f"{base_url}?q={self.clean_doi(doi)}"
+            text, headers = await self.fetch_with_headers(session, search_url, timeout=10)
+
+            if not text or "No results" in text:
+                logger.debug(f"No results for DOI: {doi} on libgen")
+                return None
+
+            soup = BeautifulSoup(text, 'html.parser')
+
+            links = soup.select('table.c > tbody > tr:nth-child(2) > td:nth-child(1) > a')
+
+            if links:
+                link = links[0]
+                pdf_url = link['href']
+                pdf_response = await session.get(pdf_url, headers=self.headers, allow_redirects=True, timeout=10)
+                if 'application/pdf' in pdf_response.headers.get('Content-Type', ''):
+                    logger.debug(f"Found PDF from: {pdf_url}")
+                    return await pdf_response.read()
+        except Exception as e:
+            logger.debug(f"Error trying to download {doi} from libgen: {e}")
+        return None
+
+    async def download_paper_google_scholar_async(self, session, doi):
+        """Search google scholar to find an article with the given doi, try to get the pdf"""
+        if not doi:
+            return None
+
+        try:
+            query = f'doi:"{doi}"'
+            params = {'q': query}
+            url = f'https://scholar.google.com/scholar?{urlencode(params)}'
+
+            text, headers = await self.fetch_with_headers(session, url, timeout=10)
+            if not text:
+                return None
+
+            soup = BeautifulSoup(text, 'html.parser')
+
+            # Find any links with [PDF]
+            links = soup.find_all('a', string=re.compile(r'\[PDF\]', re.IGNORECASE))
+
+            if links:
+                pdf_url = links[0]['href']
+                pdf_response = await session.get(pdf_url, headers=self.headers, timeout=10)
+                if 'application/pdf' in pdf_response.headers.get('Content-Type', ''):
+                    logger.debug(f"Found PDF from: {pdf_url}")
+                    return await pdf_response.read()
+        except Exception as e:
+            logger.debug(f"Google Scholar error for {doi}: {e}")
+
+        return None
+
+    async def download_paper_crossref_async(self, session, doi):
+        """Alternative search method using Crossref"""
+        if not doi:
+            return None
+
+        try:
+            # Search for open access link
+            url = f"https://api.crossref.org/works/{doi}"
+            response = await session.get(url, headers=self.headers, timeout=10)
+
+            if response.status == 200:
+                data = await response.json()
+                work = data.get('message', {})
+
+                # Search for open access links
+                links = work.get('link', [])
+                for link in links:
+                    if link.get('content-type') == 'application/pdf':
+                        pdf_url = link.get('URL')
+                        if pdf_url:
+                            pdf_response = await session.get(pdf_url, headers=self.headers)
+                            if 'application/pdf' in pdf_response.headers.get('Content-Type', ''):
+                                logger.debug(f"Found PDF from: {pdf_url}")
+                                return await pdf_response.read()
+
+        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
+        retries = 0
+        delay = initial_delay
+
+        async with aiohttp.ClientSession() as session:
+            while retries < max_retries and not pdf_content:
+                try:
+                    pdf_content = (
+                        await self.download_paper_direct_doi_async(session, doi) or
+                        await self.download_paper_scihub_async(session, doi) or
+                        await self.download_paper_libgen_async(session, doi) or
+                        await self.download_paper_google_scholar_async(session, doi) or
+                        await self.download_paper_crossref_async(session, doi)
+
+                    )
+                    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
+
+        return None
+
     def download_paper_scihub(self, doi):
         """Improved method to download paper from Sci-Hub"""
         if not doi:
@@ -53,102 +263,101 @@ class PaperDownloader:
         for base_url in self.download_sources:
             try:
                 scihub_url = f"{base_url}{self.clean_doi(doi)}"
-                
+
                 # Request with more tolerance
-                response = requests.get(scihub_url, 
-                                        headers=self.headers, 
-                                        allow_redirects=True, 
+                response = requests.get(scihub_url,
+                                        headers=self.headers,
+                                        allow_redirects=True,
                                         timeout=15)
-                
+
                 # Search for multiple PDF URL patterns
                 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, response.text))
-                
+
                 # Try downloading from found URLs
                 for pdf_url in pdf_urls:
                     try:
-                        pdf_response = requests.get(pdf_url, 
-                                                    headers=self.headers, 
+                        pdf_response = requests.get(pdf_url,
+                                                    headers=self.headers,
                                                     timeout=10)
-                        
+
                         # Verify if it's a PDF
                         if 'application/pdf' in pdf_response.headers.get('Content-Type', ''):
                             logger.debug(f"Found PDF from: {pdf_url}")
                             return pdf_response.content
                     except Exception as e:
                         logger.debug(f"Error downloading PDF from {pdf_url}: {e}")
-                
+
             except Exception as e:
                 logger.debug(f"Error trying to download {doi} from {base_url}: {e}")
-        
+
         return None
-    
+
     def download_paper_libgen(self, doi):
-      """Download from Libgen, handles the query and the redirection"""
-      if not doi:
-        return None
+        """Download from Libgen, handles the query and the redirection"""
+        if not doi:
+            return None
 
-      base_url = 'https://libgen.rs/scimag/'
-      try:
-        search_url = f"{base_url}?q={self.clean_doi(doi)}"
-        response = requests.get(search_url, headers=self.headers, allow_redirects=True, timeout=10)
-        response.raise_for_status()
-
-        if "No results" in response.text:
-          logger.debug(f"No results for DOI: {doi} on libgen")
-          return None
-
-        soup = BeautifulSoup(response.text, 'html.parser')
-        
-        # Find the link using a specific selector
-        links = soup.select('table.c > tbody > tr:nth-child(2) > td:nth-child(1) > a')
-
-        if links:
-          link = links[0]
-          pdf_url = link['href']
-          pdf_response = requests.get(pdf_url, headers=self.headers, allow_redirects=True, timeout=10)
-          if 'application/pdf' in pdf_response.headers.get('Content-Type', ''):
-              logger.debug(f"Found PDF from: {pdf_url}")
-              return pdf_response.content
+        base_url = 'https://libgen.rs/scimag/'
+        try:
+            search_url = f"{base_url}?q={self.clean_doi(doi)}"
+            response = requests.get(search_url, headers=self.headers, allow_redirects=True, timeout=10)
+            response.raise_for_status()
 
-      except Exception as e:
+            if "No results" in response.text:
+                logger.debug(f"No results for DOI: {doi} on libgen")
+                return None
+
+            soup = BeautifulSoup(response.text, 'html.parser')
+
+            # Find the link using a specific selector
+            links = soup.select('table.c > tbody > tr:nth-child(2) > td:nth-child(1) > a')
+
+            if links:
+                link = links[0]
+                pdf_url = link['href']
+                pdf_response = requests.get(pdf_url, headers=self.headers, allow_redirects=True, timeout=10)
+                if 'application/pdf' in pdf_response.headers.get('Content-Type', ''):
+                    logger.debug(f"Found PDF from: {pdf_url}")
+                    return pdf_response.content
+
+        except Exception as e:
             logger.debug(f"Error trying to download {doi} from libgen: {e}")
-      return None
-    
+        return None
+
     def download_paper_google_scholar(self, doi):
         """Search google scholar to find an article with the given doi, try to get the pdf"""
         if not doi:
             return None
-        
+
         try:
-           
-           query = f'doi:"{doi}"'
-           params = {'q': query}
-           url = f'https://scholar.google.com/scholar?{urlencode(params)}'
-           
-           response = requests.get(url, headers = self.headers, timeout = 10)
-           response.raise_for_status()
-           
-           soup = BeautifulSoup(response.text, 'html.parser')
-           
-           # Find any links with [PDF]
-           links = soup.find_all('a', string=re.compile(r'\[PDF\]', re.IGNORECASE))
-           
-           if links:
-               pdf_url = links[0]['href']
-               pdf_response = requests.get(pdf_url, headers = self.headers, timeout=10)
-               if 'application/pdf' in pdf_response.headers.get('Content-Type', ''):
-                   logger.debug(f"Found PDF from: {pdf_url}")
-                   return pdf_response.content
+            query = f'doi:"{doi}"'
+            params = {'q': query}
+            url = f'https://scholar.google.com/scholar?{urlencode(params)}'
+
+            response = requests.get(url, headers=self.headers, timeout=10)
+            response.raise_for_status()
+
+            soup = BeautifulSoup(response.text, 'html.parser')
+
+            # Find any links with [PDF]
+            links = soup.find_all('a', string=re.compile(r'\[PDF\]', re.IGNORECASE))
+
+            if links:
+                pdf_url = links[0]['href']
+                pdf_response = requests.get(pdf_url, headers=self.headers, timeout=10)
+                if 'application/pdf' in pdf_response.headers.get('Content-Type', ''):
+                    logger.debug(f"Found PDF from: {pdf_url}")
+                    return pdf_response.content
         except Exception as e:
-             logger.debug(f"Google Scholar error for {doi}: {e}")
+            logger.debug(f"Google Scholar error for {doi}: {e}")
 
         return None
 
@@ -156,16 +365,16 @@ class PaperDownloader:
         """Alternative search method using Crossref"""
         if not doi:
             return None
-        
+
         try:
             # Search for open access link
             url = f"https://api.crossref.org/works/{doi}"
             response = requests.get(url, headers=self.headers, timeout=10)
-            
+
             if response.status_code == 200:
                 data = response.json()
                 work = data.get('message', {})
-                
+
                 # Search for open access links
                 links = work.get('link', [])
                 for link in links:
@@ -176,42 +385,41 @@ class PaperDownloader:
                             if 'application/pdf' in pdf_response.headers.get('Content-Type', ''):
                                 logger.debug(f"Found PDF from: {pdf_url}")
                                 return pdf_response.content
-        
+
         except Exception as e:
             logger.debug(f"Crossref error for {doi}: {e}")
-        
+
         return None
-    
 
     def download_with_retry(self, doi, max_retries=3, initial_delay=2):
-      """Downloads a paper using multiple strategies with exponential backoff"""
-      pdf_content = None
-      retries = 0
-      delay = initial_delay
-
-      while retries < max_retries and not pdf_content:
-          try:
-              pdf_content = (
-                 self.download_paper_scihub(doi) or
-                 self.download_paper_libgen(doi) or
-                 self.download_paper_google_scholar(doi) or
-                 self.download_paper_crossref(doi)
-                 
-              )
-
-              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")
-            time.sleep(delay)
-            delay *= 2 # Exponential backoff
-          
-      return None
-    
+        """Downloads a paper using multiple strategies with exponential backoff"""
+        pdf_content = None
+        retries = 0
+        delay = initial_delay
+
+        while retries < max_retries and not pdf_content:
+            try:
+                 pdf_content = (
+                     self.download_paper_scihub(doi) or
+                     self.download_paper_libgen(doi) or
+                     self.download_paper_google_scholar(doi) or
+                     self.download_paper_crossref(doi)
+
+                  )
+
+                 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")
+                time.sleep(delay)
+                delay *= 2  # Exponential backoff
+
+        return None
+
     def download_single_doi(self, doi):
         """Downloads a single paper using a DOI"""
         if not doi:
@@ -219,10 +427,10 @@ class PaperDownloader:
 
         try:
             pdf_content = self.download_with_retry(doi)
-            
+
             if pdf_content:
                 if doi is None:
-                     return None, "Error: DOI not provided", "Error: DOI not provided"
+                    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)
                 with open(filepath, 'wb') as f:
@@ -236,12 +444,12 @@ class PaperDownloader:
         except Exception as e:
             logger.error(f"Error processing {doi}: {e}")
             return None, f"Error processing {doi}: {e}", f"Error processing {doi}: {e}"
-    
+
     def download_multiple_dois(self, dois_text):
         """Downloads multiple papers from a list of DOIs"""
         if not dois_text:
             return None, "Error: No DOIs provided", "Error: No DOIs provided"
-        
+
         dois = [doi.strip() for doi in dois_text.split('\n') if doi.strip()]
         if not dois:
             return None, "Error: No valid DOIs provided", "Error: No valid DOIs provided"
@@ -252,12 +460,12 @@ class PaperDownloader:
         for i, doi in enumerate(tqdm(dois, desc="Downloading papers")):
             filepath, success_message, fail_message = self.download_single_doi(doi)
             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>')
@@ -271,23 +479,22 @@ class PaperDownloader:
 
         return zip_filename if downloaded_files else None, "\n".join(downloaded_links), "\n".join(failed_dois)
 
-
     def process_bibtex(self, bib_file):
         """Process BibTeX file and download papers with multiple strategies"""
         # Read BibTeX file content from the uploaded object
         try:
             with open(bib_file.name, 'r', encoding='utf-8') as f:
-                 bib_content = f.read()
+                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}", None
+            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}", None
 
         # Parse BibTeX data
         try:
             bib_database = bibtexparser.loads(bib_content)
         except Exception as e:
-             logger.error(f"Error parsing BibTeX data: {e}")
-             return None, f"Error parsing BibTeX data: {e}", f"Error parsing BibTeX data: {e}", None
+            logger.error(f"Error parsing BibTeX data: {e}")
+            return None, f"Error parsing BibTeX data: {e}", f"Error parsing BibTeX data: {e}", None
 
         # Extract DOIs
         dois = [entry.get('doi') for entry in bib_database.entries if entry.get('doi')]
@@ -303,17 +510,79 @@ class PaperDownloader:
             try:
                 # Try to download with multiple methods with retries
                 pdf_content = self.download_with_retry(doi)
-                
+
                 # Save PDF
                 if pdf_content:
                     if doi is None:
                         return None, "Error: DOI not provided", "Error: DOI not provided", None
                     filename = f"{str(doi).replace('/', '_').replace('.', '_')}.pdf"
                     filepath = os.path.join(self.output_dir, filename)
-                    
+
                     with open(filepath, 'wb') as f:
                         f.write(pdf_content)
-                    
+
+                    downloaded_files.append(filepath)
+                    downloaded_links.append(f'<a href="https://doi.org/{doi}">{doi}</a>')
+                    logger.info(f"Successfully downloaded: {filename}")
+                else:
+                    failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a>')
+
+            except Exception as e:
+                failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a>')
+                logger.error(f"Error processing {doi}: {e}")
+
+        # Create ZIP of downloaded papers
+        if downloaded_files:
+            zip_filename = 'papers.zip'
+            with zipfile.ZipFile(zip_filename, 'w') as zipf:
+                for file_path in downloaded_files:
+                    zipf.write(file_path, arcname=os.path.basename(file_path))
+            logger.info(f"ZIP file created: {zip_filename}")
+
+        return zip_filename, "\n".join(downloaded_links), "\n".join(failed_dois), None
+
+    async def process_bibtex_async(self, bib_file):
+        """Process BibTeX file and download papers with multiple strategies"""
+        # Read BibTeX file content from the uploaded object
+        try:
+            with open(bib_file.name, 'r', encoding='utf-8') as f:
+                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}", None
+
+        # Parse BibTeX data
+        try:
+            bib_database = bibtexparser.loads(bib_content)
+        except Exception as e:
+            logger.error(f"Error parsing BibTeX data: {e}")
+            return None, f"Error parsing BibTeX data: {e}", f"Error parsing BibTeX data: {e}", None
+
+        # Extract DOIs
+        dois = [entry.get('doi') for entry in bib_database.entries if entry.get('doi')]
+        logger.info(f"Found {len(dois)} DOIs to download")
+
+        # Result lists
+        downloaded_files = []
+        failed_dois = []
+        downloaded_links = []
+
+        # Download PDFs
+        for doi in tqdm(dois, desc="Downloading papers"):
+            try:
+                # Try to download with multiple methods with retries
+                pdf_content = await self.download_with_retry_async(doi)
+
+                # Save PDF
+                if pdf_content:
+                    if doi is None:
+                        return None, "Error: DOI not provided", "Error: DOI not provided", None
+                    filename = f"{str(doi).replace('/', '_').replace('.', '_')}.pdf"
+                    filepath = os.path.join(self.output_dir, filename)
+
+                    with open(filepath, 'wb') as f:
+                        f.write(pdf_content)
+
                     downloaded_files.append(filepath)
                     downloaded_links.append(f'<a href="https://doi.org/{doi}">{doi}</a>')
                     logger.info(f"Successfully downloaded: {filename}")
@@ -338,23 +607,22 @@ def create_gradio_interface():
     """Create Gradio interface for Paper Downloader"""
     downloader = PaperDownloader()
 
-    def download_papers(bib_file, doi_input, dois_input):
+    async def download_papers(bib_file, doi_input, dois_input):
         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_path, downloaded_dois, failed_dois, _ = downloader.process_bibtex(bib_file)
+            zip_path, downloaded_dois, failed_dois, _ = await downloader.process_bibtex_async(bib_file)
             return zip_path, downloaded_dois, failed_dois, None
         elif doi_input:
             filepath, message, failed_doi = downloader.download_single_doi(doi_input)
             return None, message, failed_doi, filepath
         elif dois_input:
-           zip_path, downloaded_dois, failed_dois = downloader.download_multiple_dois(dois_input)
-           return zip_path, downloaded_dois, failed_dois, None
+            zip_path, downloaded_dois, failed_dois = downloader.download_multiple_dois(dois_input)
+            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
     interface = gr.Interface(
@@ -366,24 +634,21 @@ def create_gradio_interface():
         ],
         outputs=[
             gr.File(label="Download Papers (ZIP) or Single PDF"),
-             gr.HTML(label="""
-               <div style='padding-bottom: 5px; font-weight: bold;'>
-                        Enter Single DOI
-               </div>
-               <div style='border: 1px solid #ddd; padding: 5px; border-radius: 5px;'>
-                    <div style='padding-bottom: 5px; font-weight: bold;'>
-                        Downloaded DOIs
-                    </div>
+            gr.HTML(label="""
+                <div style='padding-bottom: 5px; font-weight: bold;'>
+                    Found DOIs
+                </div>
+                <div style='border: 1px solid #ddd; padding: 5px; border-radius: 5px;'>
                     <div id="downloaded-dois"></div>
-                 </div>
+                </div>
             """),
-           gr.HTML(label="""
+            gr.HTML(label="""
+                <div style='padding-bottom: 5px; font-weight: bold;'>
+                    Missed DOIs
+                </div>
                 <div style='border: 1px solid #ddd; padding: 5px; border-radius: 5px;'>
-                    <div style='padding-bottom: 5px; font-weight: bold;'>
-                        Failed DOIs
-                    </div>
                     <div id="failed-dois"></div>
-                 </div>
+                </div>
             """),
             gr.File(label="Downloaded Single PDF")
         ],
@@ -391,11 +656,11 @@ def create_gradio_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.",
         theme="Hev832/Applio",
         examples=[
-            ["example.bib", None, None], # Bibtex File
-            [None, "10.1038/nature12373", None], # Single DOI
-            [None, None, "10.1109/5.771073\n10.3390/horticulturae8080677"], # Multiple DOIs
-         ],
-         css="""
+            ["example.bib", None, None],  # Bibtex File
+            [None, "10.1038/nature12373", None],  # Single DOI
+            [None, None, "10.1109/5.771073\n10.3390/horticulturae8080677"],  # Multiple DOIs
+        ],
+        css="""
         .gradio-container {
             background-color: black;
         }
@@ -412,34 +677,33 @@ def create_gradio_interface():
                color: #007bff; /* Blue color for hyperlinks */
             }
         """,
-        cache_examples = False,
+        cache_examples=False,
     )
-    
+
     # Add Javascript to update HTML
     interface.load = """
         function(downloaded_dois, failed_dois){
-             let downloaded_html =  '<ul>';
+             let downloaded_html = '';
              downloaded_dois.split('\\n').filter(Boolean).forEach(doi => {
-                downloaded_html +=  '<li>' + doi + '</li>';
+                downloaded_html +=  '[' + doi + ']<br>';
             });
-            downloaded_html +=  '</ul>';
             document.querySelector("#downloaded-dois").innerHTML = downloaded_html;
 
-             let failed_html = '<ul>';
+             let failed_html = '';
              failed_dois.split('\\n').filter(Boolean).forEach(doi => {
-                failed_html += '<li>' + doi + '</li>';
+                failed_html += '[' + doi + ']<br>';
             });
-             failed_html += '</ul>';
             document.querySelector("#failed-dois").innerHTML = failed_html;
             return [downloaded_html, failed_html];
-
         }
     """
     return interface
 
+
 def main():
     interface = create_gradio_interface()
     interface.launch(share=True)
 
+
 if __name__ == "__main__":
-    main()
+    main()