Update app.py

app.py

@@ -10,6 +10,8 @@ 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, 
@@ -35,15 +37,186 @@ 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 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) 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_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_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:
@@ -299,7 +472,7 @@ class PaperDownloader:
         downloaded_links = []
 
         # Download PDFs
-        for doi in tqdm(dois, desc="Downloading papers"):
+        for doi in tqdm(dois, desc="Downloading papers")):
             try:
                 # Try to download with multiple methods with retries
                 pdf_content = self.download_with_retry(doi)
@@ -334,17 +507,79 @@ class PaperDownloader:
 
         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}")
+                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
+
 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)
@@ -436,4 +671,4 @@ def main():
     interface.launch(share=True)
 
 if __name__ == "__main__":
-    main()
+    main()