update pptx
Browse files
app.py
CHANGED
|
@@ -247,13 +247,13 @@ def extract_text_from_ppt(file_path):
|
|
| 247 |
return "Error extracting text from PPT file"
|
| 248 |
|
| 249 |
|
| 250 |
-
def extract_text_from_ppt_or_pptx(file_path):
|
| 251 |
-
|
| 252 |
-
|
| 253 |
-
|
| 254 |
-
|
| 255 |
-
|
| 256 |
-
|
| 257 |
|
| 258 |
|
| 259 |
def convert_pdf_to_image(file):
|
|
@@ -412,12 +412,12 @@ doc_or_docx_to_text = gr.Interface(
|
|
| 412 |
api_name="doc_or_docx_to_text",
|
| 413 |
)
|
| 414 |
|
| 415 |
-
pptx_or_ppt_to_text = gr.Interface(
|
| 416 |
-
|
| 417 |
-
|
| 418 |
-
|
| 419 |
-
|
| 420 |
-
)
|
| 421 |
|
| 422 |
ppt_to_text = gr.Interface(
|
| 423 |
extract_text_from_ppt,
|
|
@@ -426,6 +426,12 @@ ppt_to_text = gr.Interface(
|
|
| 426 |
api_name="ppt_to_text",
|
| 427 |
)
|
| 428 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 429 |
str_to_json = gr.Interface(
|
| 430 |
sanitize_list_of_lists,
|
| 431 |
gr.Text(),
|
|
@@ -452,13 +458,13 @@ url_parser = gr.Interface(
|
|
| 452 |
api_name="url_to_text",
|
| 453 |
)
|
| 454 |
demo = gr.TabbedInterface(
|
| 455 |
-
[pdf_to_img, pdf_to_text, doc_or_docx_to_text,
|
| 456 |
[
|
| 457 |
"PDF to Image",
|
| 458 |
"Extract PDF Text",
|
| 459 |
"Extract DOC/DOCX Text",
|
| 460 |
-
"Extract PPTX/PPT Text",
|
| 461 |
"Extract PPT Text",
|
|
|
|
| 462 |
"Extract text from URL",
|
| 463 |
"Extract Json",
|
| 464 |
],
|
|
|
|
| 247 |
return "Error extracting text from PPT file"
|
| 248 |
|
| 249 |
|
| 250 |
+
# def extract_text_from_ppt_or_pptx(file_path):
|
| 251 |
+
# if file_path.endswith(".pptx"):
|
| 252 |
+
# return extract_text_from_pptx(file_path)
|
| 253 |
+
# elif file_path.endswith(".ppt"):
|
| 254 |
+
# return extract_text_from_ppt(file_path)
|
| 255 |
+
# else:
|
| 256 |
+
# return "Unsupported file type. Please provide a .ppt or .pptx file."
|
| 257 |
|
| 258 |
|
| 259 |
def convert_pdf_to_image(file):
|
|
|
|
| 412 |
api_name="doc_or_docx_to_text",
|
| 413 |
)
|
| 414 |
|
| 415 |
+
# pptx_or_ppt_to_text = gr.Interface(
|
| 416 |
+
# extract_text_from_ppt_or_pptx,
|
| 417 |
+
# gr.File(),
|
| 418 |
+
# gr.Textbox(placeholder="Extracted text from PPTX will appear here"),
|
| 419 |
+
# api_name="pptx_or_ppt_to_text",
|
| 420 |
+
# )
|
| 421 |
|
| 422 |
ppt_to_text = gr.Interface(
|
| 423 |
extract_text_from_ppt,
|
|
|
|
| 426 |
api_name="ppt_to_text",
|
| 427 |
)
|
| 428 |
|
| 429 |
+
pptx_to_text = gr.Interface(
|
| 430 |
+
extract_text_from_pptx,
|
| 431 |
+
gr.File(),
|
| 432 |
+
gr.Textbox(),
|
| 433 |
+
api_name="pptx_to_text",
|
| 434 |
+
)
|
| 435 |
str_to_json = gr.Interface(
|
| 436 |
sanitize_list_of_lists,
|
| 437 |
gr.Text(),
|
|
|
|
| 458 |
api_name="url_to_text",
|
| 459 |
)
|
| 460 |
demo = gr.TabbedInterface(
|
| 461 |
+
[pdf_to_img, pdf_to_text, doc_or_docx_to_text, ppt_to_text, pptx_to_text, url_parser, str_to_json],
|
| 462 |
[
|
| 463 |
"PDF to Image",
|
| 464 |
"Extract PDF Text",
|
| 465 |
"Extract DOC/DOCX Text",
|
|
|
|
| 466 |
"Extract PPT Text",
|
| 467 |
+
"Extract PPTX Text",
|
| 468 |
"Extract text from URL",
|
| 469 |
"Extract Json",
|
| 470 |
],
|