Spaces:
Sleeping
Sleeping
ajout ppt
Browse files
main.py
CHANGED
@@ -779,14 +779,20 @@ async def convert_file_to_txt(
|
|
779 |
raise HTTPException(status_code=500, detail="Erreur lors du nettoyage du fichier HTML.")
|
780 |
input_filename = cleaned_input_filename
|
781 |
|
782 |
-
# Conversion en HTML via
|
783 |
if ext == '.pdf':
|
784 |
html_content = pdf_to_html(input_filename)
|
785 |
elif ext == '.pptx':
|
786 |
html_content = convert_pptx_to_html(input_filename)
|
787 |
-
elif ext
|
788 |
-
|
789 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
790 |
elif ext == '.doc':
|
791 |
text = convert_doc_to_text(input_filename)
|
792 |
html_content = text_to_html(text)
|
|
|
779 |
raise HTTPException(status_code=500, detail="Erreur lors du nettoyage du fichier HTML.")
|
780 |
input_filename = cleaned_input_filename
|
781 |
|
782 |
+
# Conversion en HTML via appropriate methods
|
783 |
if ext == '.pdf':
|
784 |
html_content = pdf_to_html(input_filename)
|
785 |
elif ext == '.pptx':
|
786 |
html_content = convert_pptx_to_html(input_filename)
|
787 |
+
elif ext == '.ppt':
|
788 |
+
try:
|
789 |
+
text = convert_doc_to_text(input_filename) # Reuse convert_doc_to_text which uses textract
|
790 |
+
html_content = text_to_html(text)
|
791 |
+
except HTTPException as e:
|
792 |
+
raise e
|
793 |
+
except Exception as e:
|
794 |
+
logging.error(f"Erreur lors de la conversion de .ppt avec textract: {e}")
|
795 |
+
raise HTTPException(status_code=500, detail=f"Erreur lors de la conversion du fichier .ppt: {e}")
|
796 |
elif ext == '.doc':
|
797 |
text = convert_doc_to_text(input_filename)
|
798 |
html_content = text_to_html(text)
|