app.py

import os
import re
import time
import logging
import zipfile
import requests
import bibtexparser
from tqdm import tqdm
from urllib.parse import quote, urlencode
import gradio as gr
from bs4 import BeautifulSoup
import io
import asyncio
import aiohttp
from concurrent.futures import ThreadPoolExecutor


# Configure logging
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
        self.download_sources = [
            'https://sci-hub.ee/',
            'https://sci-hub.st/',
            'https://sci-hub.ru/',
            'https://sci-hub.ren/',
            'https://sci-hub.mksa.top/',
            'https://sci-hub.se/',
            'https://libgen.rs/scimag/'
        ]

        # 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-Language': 'en-US,en;q=0.9',
        }
        self.executor = ThreadPoolExecutor(max_workers=4)

    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, 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 fetch_pdf_content(self, session, url, max_redirects=5, max_retries=2, retry_delay=1):
        """Fetch content and validate if response is PDF, following up to max_redirects redirections with retries."""
        
        current_url = url
        redirect_count = 0
        retry_count = 0

        while redirect_count <= max_redirects:
            try:
                while retry_count <= max_retries:
                    try:
                        async with session.get(current_url, headers=self.headers, timeout=10, allow_redirects=False) as response:
                            if response.status in [301, 302, 307, 308]:
                                current_url = response.headers['Location']
                                redirect_count += 1
                                logger.debug(f"Following redirect from {url} to {current_url}")
                                break  # Break out of the retry loop for a redirect

                            response.raise_for_status()

                            if 'application/pdf' in response.headers.get('Content-Type', ''):
                                return await response.read()
                            else:
                                logger.debug(f"Content type not PDF for {current_url}: {response.headers.get('Content-Type', '')}")
                                return None
                    except Exception as e:
                         logger.debug(f"Error getting PDF, retrying ({retry_count}/{max_retries}) from {current_url}: {e}")
                         retry_count += 1
                         await asyncio.sleep(retry_delay)

                retry_count = 0  # Reset the retry count, in case there's a next redirect attempt

            except Exception as e:
                logger.debug(f"Error getting PDF from {current_url}: {e}")
                return None

        logger.debug(f"Too many redirects or retries {url}, not following this link further")
        return 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)}"
    
                # First, let's try to download the URL directly in case it is already the pdf.
                pdf_content = await self.fetch_pdf_content(session, doi_url)
                if pdf_content:
                    logger.debug(f"Direct DOI resolved to PDF from {doi_url}")
                    return pdf_content
    
                # If direct DOI link was not a pdf, fetch landing page and extract links
                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))
    
                # Attempt each pdf url and break when you find a PDF content.
                for pdf_url in pdf_urls:
                    pdf_content = await self.fetch_pdf_content(session, pdf_url)
                    if pdf_content:
                        logger.debug(f"Found PDF from: {pdf_url}")
                        return pdf_content
    
            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, but iterate over ALL
                for pdf_url in pdf_urls:
                    pdf_content = await self.fetch_pdf_content(session,pdf_url)
                    if pdf_content:
                        logger.debug(f"Found PDF from: {pdf_url}")
                        return pdf_content

            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_content = await self.fetch_pdf_content(session, pdf_url)
                if pdf_content:
                    logger.debug(f"Found PDF from: {pdf_url}")
                    return pdf_content
        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_content = await self.fetch_pdf_content(session,pdf_url)
                if pdf_content:
                  logger.debug(f"Found PDF from: {pdf_url}")
                  return pdf_content

        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_content = await self.fetch_pdf_content(session, pdf_url)
                                if pdf_content:
                                    logger.debug(f"Found PDF from: {pdf_url}")
                                    return pdf_content
            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):
        """
        Intenta descargar un paper con múltiples estrategias y un número limitado de reintentos.
        
        Args:
            doi (str): DOI del paper a descargar
            max_retries (int): Número máximo de reintentos
        
        Returns:
            bytes or None: Contenido del PDF o None si no se puede descargar
        """
        if not doi:
            logger.warning("DOI no proporcionado")
            return None
    
        # Estrategias de descarga en orden de preferencia
        download_strategies = [
            self.download_paper_direct_doi_async,
            self.download_paper_scihub_async,
            self.download_paper_libgen_async,
            self.download_paper_google_scholar_async,
            self.download_paper_crossref_async
        ]
    
        async with aiohttp.ClientSession() as session:
            for retry in range(max_retries):
                logger.info(f"Intento de descarga {retry + 1} para DOI: {doi}")
                
                # Probar cada estrategia de descarga
                for strategy in download_strategies:
                    try:
                        pdf_content = await strategy(session, doi)
                        if pdf_content:
                            logger.info(f"Descarga exitosa de {doi} usando {strategy.__name__}")
                            return pdf_content
                    except Exception as e:
                        logger.debug(f"Error en estrategia {strategy.__name__} para {doi}: {e}")
                
                # Si ninguna estrategia funcionó, esperar un poco antes de reintentar
                await asyncio.sleep(1)  # Pequeña pausa entre reintentos
    
            # Si se agotan todos los reintentos
            logger.warning(f"FALLO FINAL: No se pudo descargar DOI {doi} después de {max_retries} intentos")
            return None
    
    async def download_single_doi_async(self, doi, progress_callback):
        """Descargar un único DOI con retroalimentación de progreso"""
        if not doi:
            return None, "Error: DOI no proporcionado", "Error: DOI no proporcionado"
    
        try:
            pdf_content = await self.download_with_retry_async(doi)
    
            if pdf_content:
                filename = f"{str(doi).replace('/', '_').replace('.', '_')}.pdf"
                filepath = os.path.join(self.output_dir, filename)
    
                # Escribir contenido del PDF
                loop = asyncio.get_running_loop()
                await loop.run_in_executor(
                    self.executor, 
                    lambda: open(filepath, 'wb').write(pdf_content)
                )
                
                logger.info(f"Descarga exitosa: {filename}")
                progress_callback(f"Descargado exitosamente: <a href='https://doi.org/{doi}'>{doi}</a>")
                return filepath, f'<a href="https://doi.org/{doi}">{doi}</a>', ""
            else:
                logger.warning(f"No se pudo descargar: {doi}")
                progress_callback(f"No se pudo descargar: <a href='https://doi.org/{doi}'>{doi}</a>")
                return None, f"No se pudo descargar {doi}", f'<a href="https://doi.org/{doi}">{doi}</a>'
    
        except Exception as e:
            logger.error(f"Error procesando {doi}: {e}")
            progress_callback(f"Error procesando {doi}: <a href='https://doi.org/{doi}'>{doi}</a> {e}")
            return None, f"Error procesando {doi}: {e}", f"Error procesando {doi}: {e}"
    
    async def download_multiple_dois_async(self, dois_text, progress_callback):
        # Validar entrada
        if not dois_text:
            return None, "Error: No DOIs provided", "Error: No DOIs provided"
    
        # Sanitizar y filtrar DOIs
        # Eliminar líneas vacías, espacios en blanco, y DOIs duplicados
        dois = list(set([doi.strip() for doi in dois_text.split('\n') if doi.strip()]))
        
        # Validar lista de DOIs
        if not dois:
            return None, "Error: No valid DOIs provided", "Error: No valid DOIs provided"
    
        # Listas para rastrear resultados
        downloaded_files = []      # Rutas de archivos descargados
        failed_dois = []           # DOIs que no se pudieron descargar
        downloaded_links = []      # Links de DOIs descargados
    
        # Generar tareas de descarga concurrentes
        download_tasks = []
        for doi in dois:
            task = self.download_single_doi_async(doi, progress_callback)
            download_tasks.append(task)
        
        # Ejecutar todas las descargas concurrentemente
        results = await asyncio.gather(*download_tasks, return_exceptions=True)
        
        # Procesar resultados de cada DOI
        for i, result in enumerate(results):
            doi = dois[i]
            
            # Manejar diferentes tipos de resultados
            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}')
            
            else:
                # Descarga exitosa
                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
                    os.rename(filepath, filepath_unique)
                    
                    # 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')
    
        # Crear archivo ZIP si hay archivos descargados
        zip_filename = None
        if downloaded_files:
            zip_filename = 'papers.zip'
            loop = asyncio.get_running_loop()
            
            # Ejecutar creación de ZIP en un executor para no bloquear
            await loop.run_in_executor(
                self.executor, 
                lambda: self.create_zip(zip_filename, downloaded_files)
            )
            logger.info(f"ZIP file created: {zip_filename}")
    
        # Devolver resultados
        return (
            zip_filename if downloaded_files else None,  # Archivo ZIP o None
            "\n".join(downloaded_links),                # DOIs descargados 
            "\n".join(failed_dois)                      # DOIs fallidos
        )

    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
            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}"
    
            # 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}"
    
            # 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 = []
    
            tasks = [self.download_single_doi_async(doi, progress_callback) for doi in dois]
            results = await asyncio.gather(*tasks)

            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}")
    
            return zip_filename, "\n".join(downloaded_links), "\n".join(failed_dois)

def create_gradio_interface():
    """Create Gradio interface for Paper Downloader"""
    downloader = PaperDownloader()

    async def download_papers(bib_file, doi_input, dois_input, progress=gr.Progress()):
            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 = 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
            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


    # Gradio Interface
    interface = gr.Interface(
        fn=download_papers,
        inputs=[
            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"),
            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>
            """),
            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 id="failed-dois"></div>
                </div>
            """),
           gr.File(label="Downloaded Single PDF")
        ],
        title="🔬 Academic Paper Batch Downloader",
        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="""
        .gradio-container {
            background-color: black;
        }
        .gr-interface {
            max-width: 800px;
            margin: 0 auto;
        }
        .gr-box {
            background-color: black;
            border-radius: 10px;
            box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1);
        }
           .output-text a {
               color: #007bff; /* Blue color for hyperlinks */
            }
        """,
        cache_examples=False,
    )

    # Add Javascript to update HTML
    interface.load = """
        function(downloaded_dois, failed_dois){
             let downloaded_html = '';
             downloaded_dois.split('\\n').filter(Boolean).forEach(doi => {
                downloaded_html +=  '[' + doi + ']<br>';
            });
            document.querySelector("#downloaded-dois").innerHTML = downloaded_html;

             let failed_html = '';
             failed_dois.split('\\n').filter(Boolean).forEach(doi => {
                failed_html += '[' + doi + ']<br>';
            });
            document.querySelector("#failed-dois").innerHTML = failed_html;
            return [downloaded_html, failed_html];
        }
    """
    return interface


def main():
    interface = create_gradio_interface()
    interface.launch()

if __name__ == "__main__":
    main()