renato97/cbcren2026
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Restore full pipeline: 3-step summarization, formatting, PDF/DOCX generation

Browse Source
This commit is contained in:
renato97
2026-01-09 17:01:22 -03:00
parent b017504c52
commit e6a01d08d4
20 changed files with 260 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

90
main.py
View File

@@ -276,7 +276,95 @@ def run_main_loop() -> None:
for file_path in audio_files:
if any(file_path.lower().endswith(ext) for ext in settings.AUDIO_EXTENSIONS):
if not processed_registry.is_processed(file_path):
audio_processor.process(file_path)
from pathlib import Path
from urllib.parse import unquote
from document.generators import DocumentGenerator
from services.telegram_service import telegram_service
local_filename = unquote(Path(file_path).name)
base_name = Path(local_filename).stem
local_path = settings.LOCAL_DOWNLOADS_PATH / local_filename
settings.LOCAL_DOWNLOADS_PATH.mkdir(parents=True, exist_ok=True)
# Step 1: Notify and download
telegram_service.send_message(
f"🎵 Nuevo audio detectado: {local_filename}\n"
f"⬇️ Descargando..."
)
logger.info(f"Downloading audio: {file_path} -> {local_path}")
webdav_service.download(file_path, local_path)
# Step 2: Transcribe
telegram_service.send_message(f"📝 Transcribiendo audio con Whisper...")
result = audio_processor.process(str(local_path))
if result.get("success") and result.get("transcription_path"):
transcription_file = Path(result["transcription_path"])
transcription_text = result.get("text", "")
# Step 3: Generate AI summary and documents
telegram_service.send_message(f"🤖 Generando resumen con IA...")
doc_generator = DocumentGenerator()
success, summary, output_files = doc_generator.generate_summary(
transcription_text, base_name
)
# Step 4: Upload all files to Nextcloud
if success and output_files:
# Create folders
for folder in [settings.RESUMENES_FOLDER, settings.DOCX_FOLDER]:
try:
webdav_service.makedirs(folder)
except Exception:
pass
# Upload transcription TXT
if transcription_file.exists():
remote_txt = f"{settings.RESUMENES_FOLDER}/{transcription_file.name}"
webdav_service.upload(transcription_file, remote_txt)
logger.info(f"Uploaded: {remote_txt}")
# Upload DOCX
docx_path = Path(output_files.get('docx_path', ''))
if docx_path.exists():
remote_docx = f"{settings.DOCX_FOLDER}/{docx_path.name}"
webdav_service.upload(docx_path, remote_docx)
logger.info(f"Uploaded: {remote_docx}")
# Upload PDF
pdf_path = Path(output_files.get('pdf_path', ''))
if pdf_path.exists():
remote_pdf = f"{settings.DOCX_FOLDER}/{pdf_path.name}"
webdav_service.upload(pdf_path, remote_pdf)
logger.info(f"Uploaded: {remote_pdf}")
# Upload Markdown
md_path = Path(output_files.get('markdown_path', ''))
if md_path.exists():
remote_md = f"{settings.RESUMENES_FOLDER}/{md_path.name}"
webdav_service.upload(md_path, remote_md)
logger.info(f"Uploaded: {remote_md}")
# Final notification
telegram_service.send_message(
f"✅ Audio procesado: {local_filename}\n"
f"📄 DOCX: {docx_path.name if docx_path.exists() else 'N/A'}\n"
f"📑 PDF: {pdf_path.name if pdf_path.exists() else 'N/A'}\n"
f"☁️ Subido a Nextcloud"
)
else:
# Just upload transcription if summary failed
if transcription_file.exists():
try:
webdav_service.makedirs(settings.RESUMENES_FOLDER)
except Exception:
pass
remote_txt = f"{settings.RESUMENES_FOLDER}/{transcription_file.name}"
webdav_service.upload(transcription_file, remote_txt)
telegram_service.send_message(
f"⚠️ Resumen fallido, solo transcripción subida:\n{transcription_file.name}"
)
processed_registry.save(file_path)
except Exception as e:
logger.exception(f"Error processing audio: {e}")