Update app.py

app.py

@@ -10,6 +10,10 @@ from urllib.parse import quote, urlencode
 import gradio as gr
 from bs4 import BeautifulSoup
 import io
+from docx import Document
+from docx.shared import Inches
+from docx.enum.text import WD_ALIGN_PARAGRAPH
+
 
 # Configure logging
 logging.basicConfig(level=logging.INFO, 
@@ -215,241 +219,51 @@ class PaperDownloader:
     def download_single_doi(self, doi):
         """Downloads a single paper using a DOI"""
         if not doi:
-            return None, "Error: DOI not provided", "Error: DOI not provided"
+            return None, "Error: DOI not provided", "Error: DOI not provided", None, None
 
         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", "", None, 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)
                 logger.info(f"Successfully downloaded: {filename}")
-                return filepath, f'<a href="https://doi.org/{doi}">{doi}</a>', ""
+                return filepath, f'<a href="https://doi.org/{doi}">{doi}</a>', "", None
             else:
                 logger.warning(f"Could not download: {doi}")
-                return None, f"Could not download {doi}", f'<a href="https://doi.org/{doi}">{doi}</a>'
+                return None, f"Could not download {doi}", f'<a href="https://doi.org/{doi}">{doi}</a>', None, None
 
         except Exception as e:
             logger.error(f"Error processing {doi}: {e}")
-            return None, f"Error processing {doi}: {e}", f"Error processing {doi}: {e}"
+            return None, f"Error processing {doi}: {e}", f"Error processing {doi}: {e}", None, None
     
-    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"
-
-        downloaded_files = []
-        failed_dois = []
-        downloaded_links = []
-        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>')
-
-            else:
-                failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a>')
 
-        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 if downloaded_files else None, "\n".join(downloaded_links), "\n".join(failed_dois)
+# Create PaperDownloader instance
+downloader = PaperDownloader()
 
+def download_doi_callback(doi):
+    filepath, success_message, fail_message, _, _ = downloader.download_single_doi(doi)
+    if filepath:
+        return filepath, success_message, fail_message
+    else:
+        return None, fail_message, success_message
 
-    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()
-        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 = 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
-
-def create_gradio_interface():
-    """Create Gradio interface for Paper Downloader"""
-    downloader = PaperDownloader()
-
-    def download_papers(bib_file, doi_input, dois_input, theme_mode):
-        if theme_mode == "dark":
-            theme = gr.themes.Monochrome(
-                primary_hue="indigo",
-                secondary_hue="neutral",
-            )
-            
-        else:
-           theme = "gstaff/sketch"
-            
-        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)
-            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
-        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..."),
-             gr.Dropdown(choices=["light", "dark"], value="light", label="Theme mode"),
-        ],
-        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>
-                    <div id="downloaded-dois"></div>
-                 </div>
-            """),
-           gr.HTML(label="""
-                <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>
-            """),
-            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="gstaff/sketch",
-        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: #222222;
-        }
-        .gr-interface {
-            max-width: 800px;
-            margin: 0 auto;
-        }
-        .gr-box {
-            background-color: white;
-            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 =  '<ul>';
-             downloaded_dois.split('\\n').filter(Boolean).forEach(doi => {
-                downloaded_html +=  '<li>' + doi + '</li>';
-            });
-            downloaded_html +=  '</ul>';
-            document.querySelector("#downloaded-dois").innerHTML = downloaded_html;
-
-             let failed_html = '<ul>';
-             failed_dois.split('\\n').filter(Boolean).forEach(doi => {
-                failed_html += '<li>' + doi + '</li>';
-            });
-             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)
+# Test or connect to a Gradio interface
+iface = gr.Interface(
+    fn=download_doi_callback,
+    inputs=gr.Textbox(label="Enter DOI", placeholder="Enter DOI to download"),
+    outputs=[
+        gr.File(label="Download Paper"),
+        gr.HTML(label="Success Message"),
+        gr.HTML(label="Failure Message")
+    ],
+    live=True,
+)
 
-if __name__ == "__main__":
-    main()
+iface.launch()