Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -334,7 +334,6 @@ class PaperDownloader:
|
|
| 334 |
def _download_single_doi(self, doi, cancel_event): # removed async keyword
|
| 335 |
"""Descargar un 煤nico DOI con retroalimentaci贸n de progreso"""
|
| 336 |
if not doi:
|
| 337 |
-
|
| 338 |
return None, "Error: DOI no proporcionado", "Error: DOI no proporcionado"
|
| 339 |
logger.info(f"Starting download process for DOI: {doi}")
|
| 340 |
|
|
@@ -363,23 +362,22 @@ class PaperDownloader:
|
|
| 363 |
logger.warning(f"No se pudo descargar: {doi}")
|
| 364 |
return None, f"No se pudo descargar {doi}", f'<a href="https://doi.org/{doi}">{doi}</a>'
|
| 365 |
|
| 366 |
-
|
| 367 |
-
|
| 368 |
except CancelledError:
|
| 369 |
logger.info(f"Download Cancelled DOI: {doi}")
|
| 370 |
-
return None, f"Download cancelled {doi}","Download Cancelled"
|
| 371 |
|
| 372 |
except Exception as e:
|
| 373 |
logger.error(f"Error processing {doi}: {e}")
|
| 374 |
-
return None, f"Error processing {doi}: {e}", f"Error processing {doi}: {e}"
|
| 375 |
|
| 376 |
|
| 377 |
def download_multiple_dois(self, dois_text, cancel_event): #removed async here
|
| 378 |
"""Download multiple DOIs"""
|
| 379 |
# Validar entrada
|
| 380 |
if not dois_text:
|
| 381 |
-
|
| 382 |
-
return None, "Error: No DOIs provided", "Error: No DOIs provided",""
|
| 383 |
|
| 384 |
# Sanitizar y filtrar DOIs
|
| 385 |
# Eliminar l铆neas vac铆as, espacios en blanco, y DOIs duplicados
|
|
@@ -387,27 +385,25 @@ class PaperDownloader:
|
|
| 387 |
|
| 388 |
# Validar lista de DOIs
|
| 389 |
if not dois:
|
| 390 |
-
|
| 391 |
-
return None, "Error: No valid DOIs provided", "Error: No valid DOIs provided", ""
|
| 392 |
|
| 393 |
# Listas para rastrear resultados
|
| 394 |
downloaded_files = [] # Rutas de archivos descargados
|
| 395 |
failed_dois = [] # DOIs que no se pudieron descargar
|
| 396 |
downloaded_links = [] # Links de DOIs descargados
|
|
|
|
| 397 |
for doi in dois:
|
| 398 |
-
|
| 399 |
-
result = self._download_single_doi(doi,cancel_event)
|
| 400 |
|
| 401 |
if cancel_event.is_set():
|
| 402 |
-
|
| 403 |
logger.info("Downloads cancelled on multiple dois download")
|
| 404 |
-
return None,"Downloads cancelled","Downloads cancelled",""
|
| 405 |
-
|
| 406 |
-
if result is None:
|
| 407 |
-
|
| 408 |
-
|
| 409 |
if isinstance(result, Exception):
|
| 410 |
-
|
| 411 |
error_msg = f"Unexpected error: {str(result)}"
|
| 412 |
logger.error(f"Error downloading {doi}: {error_msg}")
|
| 413 |
failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a> - {error_msg}')
|
|
@@ -419,24 +415,24 @@ class PaperDownloader:
|
|
| 419 |
failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a> - {error_msg}')
|
| 420 |
|
| 421 |
else:
|
| 422 |
-
|
| 423 |
filepath = result[0]
|
| 424 |
|
| 425 |
-
|
| 426 |
filename = f"{str(doi).replace('/', '_').replace('.', '_')}.pdf"
|
| 427 |
filepath_unique = os.path.join(self.output_dir, filename)
|
| 428 |
-
|
| 429 |
try:
|
| 430 |
# Renombrar archivo
|
| 431 |
os.rename(filepath, filepath_unique)
|
| 432 |
-
|
| 433 |
-
|
| 434 |
downloaded_files.append(filepath_unique)
|
| 435 |
downloaded_links.append(f'<a href="https://doi.org/{doi}">{doi}</a>')
|
| 436 |
|
| 437 |
except Exception as rename_error:
|
| 438 |
-
|
| 439 |
-
|
| 440 |
|
| 441 |
|
| 442 |
# Crear archivo ZIP si hay archivos descargados
|
|
@@ -452,8 +448,7 @@ class PaperDownloader:
|
|
| 452 |
)
|
| 453 |
logger.info(f"ZIP file created: {zip_filename}")
|
| 454 |
|
| 455 |
-
return
|
| 456 |
-
|
| 457 |
|
| 458 |
def process_bibtex(self, bib_file, cancel_event):# removed async here
|
| 459 |
"""Process BibTeX file and download papers with multiple strategies and reports UI updates using a callback"""
|
|
@@ -480,16 +475,16 @@ class PaperDownloader:
|
|
| 480 |
downloaded_files = []
|
| 481 |
failed_dois = []
|
| 482 |
downloaded_links = []
|
| 483 |
-
|
| 484 |
for doi in dois:
|
| 485 |
-
|
| 486 |
-
|
| 487 |
-
|
| 488 |
-
|
| 489 |
-
|
| 490 |
-
|
| 491 |
-
|
| 492 |
-
|
| 493 |
|
| 494 |
if isinstance(result, Exception):
|
| 495 |
# Excepci贸n inesperada
|
|
@@ -499,29 +494,30 @@ class PaperDownloader:
|
|
| 499 |
|
| 500 |
elif result[0] is None:
|
| 501 |
# Descarga fallida (resultado de download_single_doi_async)
|
| 502 |
-
|
| 503 |
-
|
| 504 |
-
|
| 505 |
-
|
| 506 |
else:
|
| 507 |
-
|
| 508 |
-
|
| 509 |
|
| 510 |
-
|
| 511 |
-
|
| 512 |
-
|
| 513 |
-
|
| 514 |
-
|
| 515 |
-
|
| 516 |
-
|
|
|
|
| 517 |
if downloaded_files:
|
| 518 |
zip_filename = 'papers.zip'
|
| 519 |
loop = asyncio.get_running_loop()
|
| 520 |
loop.run_in_executor(self.executor, lambda: self.create_zip(zip_filename,downloaded_files))
|
| 521 |
logger.info(f"ZIP file created: {zip_filename}")
|
| 522 |
|
| 523 |
-
return
|
| 524 |
-
|
| 525 |
|
| 526 |
def create_zip(self, zip_filename, files):
|
| 527 |
"""Crea un archivo zip con los pdfs descargados"""
|
|
@@ -544,45 +540,48 @@ def create_gradio_interface():
|
|
| 544 |
|
| 545 |
|
| 546 |
def download_papers(bib_file, doi_input, dois_input, output_file, downloaded_dois_textbox,failed_dois_textbox,logs, single_file):
|
| 547 |
-
|
| 548 |
-
|
| 549 |
-
|
| 550 |
-
|
| 551 |
-
|
| 552 |
-
|
| 553 |
-
|
| 554 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 555 |
|
| 556 |
-
|
| 557 |
-
|
| 558 |
-
|
| 559 |
-
|
| 560 |
-
|
| 561 |
-
|
| 562 |
-
|
|
|
|
| 563 |
|
| 564 |
-
|
| 565 |
-
|
| 566 |
-
downloader.download_task = downloader.executor.submit( #changed async execution method
|
| 567 |
-
downloader._download_single_doi,
|
| 568 |
-
doi_input,
|
| 569 |
-
cancel_event
|
| 570 |
-
)
|
| 571 |
-
filepath, message, error= downloader.download_task.result()
|
| 572 |
-
|
| 573 |
-
return None, message, error, "", filepath
|
| 574 |
-
|
| 575 |
-
elif dois_input:
|
| 576 |
-
downloader.download_task = downloader.executor.submit( #changed async execution method
|
| 577 |
downloader.download_multiple_dois,
|
| 578 |
dois_input,
|
| 579 |
-
|
| 580 |
-
|
| 581 |
-
|
| 582 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 583 |
|
| 584 |
-
else:
|
| 585 |
-
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 # all parameters must have return data, to prevent gradio to crash on incomplete data for block
|
| 586 |
|
| 587 |
with gr.Blocks(theme="Hev832/Applio", css="""
|
| 588 |
.gradio-container {
|
|
@@ -641,17 +640,16 @@ def create_gradio_interface():
|
|
| 641 |
stop_button.click(lambda: downloader.cancel_download(), outputs=None) # added function in object downloader
|
| 642 |
|
| 643 |
submit_button.click(
|
| 644 |
-
|
| 645 |
-
|
| 646 |
-
outputs=[output_file, downloaded_dois_textbox, failed_dois_textbox,logs, single_file ]
|
| 647 |
-
|
| 648 |
-
|
| 649 |
-
|
| 650 |
interface.title="馃敩 Academic Paper Batch Downloader"
|
| 651 |
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."
|
| 652 |
-
|
| 653 |
return interface
|
| 654 |
-
|
| 655 |
|
| 656 |
def main():
|
| 657 |
interface = create_gradio_interface()
|
|
|
|
| 334 |
def _download_single_doi(self, doi, cancel_event): # removed async keyword
|
| 335 |
"""Descargar un 煤nico DOI con retroalimentaci贸n de progreso"""
|
| 336 |
if not doi:
|
|
|
|
| 337 |
return None, "Error: DOI no proporcionado", "Error: DOI no proporcionado"
|
| 338 |
logger.info(f"Starting download process for DOI: {doi}")
|
| 339 |
|
|
|
|
| 362 |
logger.warning(f"No se pudo descargar: {doi}")
|
| 363 |
return None, f"No se pudo descargar {doi}", f'<a href="https://doi.org/{doi}">{doi}</a>'
|
| 364 |
|
| 365 |
+
return asyncio.run(call_async()) #added the loop event here
|
| 366 |
+
|
| 367 |
except CancelledError:
|
| 368 |
logger.info(f"Download Cancelled DOI: {doi}")
|
| 369 |
+
return None, f"Download cancelled {doi}","Download Cancelled"
|
| 370 |
|
| 371 |
except Exception as e:
|
| 372 |
logger.error(f"Error processing {doi}: {e}")
|
| 373 |
+
return None, f"Error processing {doi}: {e}", f"Error processing {doi}: {e}"
|
| 374 |
|
| 375 |
|
| 376 |
def download_multiple_dois(self, dois_text, cancel_event): #removed async here
|
| 377 |
"""Download multiple DOIs"""
|
| 378 |
# Validar entrada
|
| 379 |
if not dois_text:
|
| 380 |
+
return None, "Error: No DOIs provided", "Error: No DOIs provided", ""
|
|
|
|
| 381 |
|
| 382 |
# Sanitizar y filtrar DOIs
|
| 383 |
# Eliminar l铆neas vac铆as, espacios en blanco, y DOIs duplicados
|
|
|
|
| 385 |
|
| 386 |
# Validar lista de DOIs
|
| 387 |
if not dois:
|
| 388 |
+
return None, "Error: No valid DOIs provided", "Error: No valid DOIs provided", ""
|
|
|
|
| 389 |
|
| 390 |
# Listas para rastrear resultados
|
| 391 |
downloaded_files = [] # Rutas de archivos descargados
|
| 392 |
failed_dois = [] # DOIs que no se pudieron descargar
|
| 393 |
downloaded_links = [] # Links de DOIs descargados
|
| 394 |
+
|
| 395 |
for doi in dois:
|
| 396 |
+
result = self._download_single_doi(doi,cancel_event) # now single methods directly
|
|
|
|
| 397 |
|
| 398 |
if cancel_event.is_set():
|
|
|
|
| 399 |
logger.info("Downloads cancelled on multiple dois download")
|
| 400 |
+
return None,"Downloads cancelled","Downloads cancelled", ""# early return on cancelled
|
| 401 |
+
|
| 402 |
+
if result is None:
|
| 403 |
+
continue
|
| 404 |
+
|
| 405 |
if isinstance(result, Exception):
|
| 406 |
+
# Excepci贸n inesperada
|
| 407 |
error_msg = f"Unexpected error: {str(result)}"
|
| 408 |
logger.error(f"Error downloading {doi}: {error_msg}")
|
| 409 |
failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a> - {error_msg}')
|
|
|
|
| 415 |
failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a> - {error_msg}')
|
| 416 |
|
| 417 |
else:
|
| 418 |
+
# Descarga exitosa
|
| 419 |
filepath = result[0]
|
| 420 |
|
| 421 |
+
# Generar nombre de archivo 煤nico
|
| 422 |
filename = f"{str(doi).replace('/', '_').replace('.', '_')}.pdf"
|
| 423 |
filepath_unique = os.path.join(self.output_dir, filename)
|
| 424 |
+
|
| 425 |
try:
|
| 426 |
# Renombrar archivo
|
| 427 |
os.rename(filepath, filepath_unique)
|
| 428 |
+
|
| 429 |
+
# A帽adir a lista de archivos descargados
|
| 430 |
downloaded_files.append(filepath_unique)
|
| 431 |
downloaded_links.append(f'<a href="https://doi.org/{doi}">{doi}</a>')
|
| 432 |
|
| 433 |
except Exception as rename_error:
|
| 434 |
+
logger.error(f"Error renaming file for {doi}: {rename_error}")
|
| 435 |
+
failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a> - Error saving file')
|
| 436 |
|
| 437 |
|
| 438 |
# Crear archivo ZIP si hay archivos descargados
|
|
|
|
| 448 |
)
|
| 449 |
logger.info(f"ZIP file created: {zip_filename}")
|
| 450 |
|
| 451 |
+
return zip_filename if downloaded_files else None, "\n".join(downloaded_links),"\n".join(failed_dois), ""
|
|
|
|
| 452 |
|
| 453 |
def process_bibtex(self, bib_file, cancel_event):# removed async here
|
| 454 |
"""Process BibTeX file and download papers with multiple strategies and reports UI updates using a callback"""
|
|
|
|
| 475 |
downloaded_files = []
|
| 476 |
failed_dois = []
|
| 477 |
downloaded_links = []
|
| 478 |
+
|
| 479 |
for doi in dois:
|
| 480 |
+
result= self._download_single_doi(doi,cancel_event) # calls function
|
| 481 |
+
|
| 482 |
+
if cancel_event.is_set():
|
| 483 |
+
logger.info("Download Cancelled in bibtex mode")
|
| 484 |
+
return None, "Download Cancelled", "Download Cancelled", ""#cancel if requested
|
| 485 |
+
|
| 486 |
+
if result is None: #skips nulls to perform continue on a multi processing with threads.
|
| 487 |
+
continue;
|
| 488 |
|
| 489 |
if isinstance(result, Exception):
|
| 490 |
# Excepci贸n inesperada
|
|
|
|
| 494 |
|
| 495 |
elif result[0] is None:
|
| 496 |
# Descarga fallida (resultado de download_single_doi_async)
|
| 497 |
+
error_msg = result[1]
|
| 498 |
+
logger.warning(f"Failed to download {doi}: {error_msg}")
|
| 499 |
+
failed_dois.append(f'<a href="https://doi.org/{doi}">{doi}</a> - {error_msg}')
|
| 500 |
+
|
| 501 |
else:
|
| 502 |
+
# Descarga exitosa
|
| 503 |
+
filepath = result[0]
|
| 504 |
|
| 505 |
+
# Unique filename for zip
|
| 506 |
+
filename = f"{str(doi).replace('/', '_').replace('.', '_')}_{i}.pdf"
|
| 507 |
+
filepath_unique = os.path.join(self.output_dir, filename)
|
| 508 |
+
os.rename(filepath, filepath_unique)
|
| 509 |
+
downloaded_files.append(filepath_unique)
|
| 510 |
+
downloaded_links.append(f'<a href="https://doi.org/{doi}">{doi}</a>')
|
| 511 |
+
|
| 512 |
+
|
| 513 |
if downloaded_files:
|
| 514 |
zip_filename = 'papers.zip'
|
| 515 |
loop = asyncio.get_running_loop()
|
| 516 |
loop.run_in_executor(self.executor, lambda: self.create_zip(zip_filename,downloaded_files))
|
| 517 |
logger.info(f"ZIP file created: {zip_filename}")
|
| 518 |
|
| 519 |
+
return zip_filename, "\n".join(downloaded_links), "\n".join(failed_dois), ""# all callbacks done, sending empty logs so no value breaks on UI.
|
| 520 |
+
|
| 521 |
|
| 522 |
def create_zip(self, zip_filename, files):
|
| 523 |
"""Crea un archivo zip con los pdfs descargados"""
|
|
|
|
| 540 |
|
| 541 |
|
| 542 |
def download_papers(bib_file, doi_input, dois_input, output_file, downloaded_dois_textbox,failed_dois_textbox,logs, single_file):
|
| 543 |
+
|
| 544 |
+
|
| 545 |
+
cancel_event = asyncio.Event() # Create cancellation event for every submission.
|
| 546 |
+
downloader.cancel_event = cancel_event # store the event so that it is available to stop the process
|
| 547 |
+
if bib_file:
|
| 548 |
+
# Check file type
|
| 549 |
+
if not bib_file.name.lower().endswith('.bib'):
|
| 550 |
+
return None, "Error: Please upload a .bib file", "Error: Please upload a .bib file","", None
|
| 551 |
+
|
| 552 |
+
downloader.download_task = downloader.executor.submit(
|
| 553 |
+
downloader.process_bibtex,
|
| 554 |
+
bib_file,
|
| 555 |
+
cancel_event # Added cancelllation event.
|
| 556 |
+
)
|
| 557 |
+
zip_file, downloaded_dois, failed_dois, logs_text= downloader.download_task.result() #gets the values returned.
|
| 558 |
+
|
| 559 |
+
return zip_file, downloaded_dois, failed_dois, logs_text, None # simple return
|
| 560 |
+
|
| 561 |
+
elif doi_input:
|
| 562 |
|
| 563 |
+
downloader.download_task = downloader.executor.submit( #changed async execution method
|
| 564 |
+
downloader._download_single_doi,
|
| 565 |
+
doi_input,
|
| 566 |
+
cancel_event
|
| 567 |
+
)
|
| 568 |
+
|
| 569 |
+
filepath, message, error = downloader.download_task.result()#gets results, nothing more
|
| 570 |
+
return None, message, error, "", filepath
|
| 571 |
|
| 572 |
+
elif dois_input:
|
| 573 |
+
downloader.download_task = downloader.executor.submit( #changed async execution method
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 574 |
downloader.download_multiple_dois,
|
| 575 |
dois_input,
|
| 576 |
+
cancel_event #Add cancellation event.
|
| 577 |
+
)
|
| 578 |
+
zip_file, downloaded_dois, failed_dois, logs_text= downloader.download_task.result()
|
| 579 |
+
return zip_file, downloaded_dois, failed_dois, logs_text, None
|
| 580 |
+
|
| 581 |
+
else:
|
| 582 |
+
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#all params provided
|
| 583 |
+
|
| 584 |
|
|
|
|
|
|
|
| 585 |
|
| 586 |
with gr.Blocks(theme="Hev832/Applio", css="""
|
| 587 |
.gradio-container {
|
|
|
|
| 640 |
stop_button.click(lambda: downloader.cancel_download(), outputs=None) # added function in object downloader
|
| 641 |
|
| 642 |
submit_button.click(
|
| 643 |
+
download_papers,
|
| 644 |
+
inputs=[bib_file, doi_input, dois_input],
|
| 645 |
+
outputs=[output_file, downloaded_dois_textbox, failed_dois_textbox,logs, single_file ] # the new output should be a tuple and we output logs too for debugging.
|
| 646 |
+
)
|
| 647 |
+
|
| 648 |
+
|
| 649 |
interface.title="馃敩 Academic Paper Batch Downloader"
|
| 650 |
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."
|
| 651 |
+
|
| 652 |
return interface
|
|
|
|
| 653 |
|
| 654 |
def main():
|
| 655 |
interface = create_gradio_interface()
|