Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -9,6 +9,25 @@ def process_pdf(file):
|
|
| 9 |
for page in pdf_reader.pages:
|
| 10 |
text += page.extract_text()
|
| 11 |
return text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
with gr.Blocks() as demo:
|
| 14 |
gr.Markdown("### File upload", elem_classes="tab-header")
|
|
@@ -18,6 +37,6 @@ with gr.Blocks() as demo:
|
|
| 18 |
file_input = gr.File(label="Wähle eine PDF-Datei aus", type="filepath")
|
| 19 |
with gr.Row():
|
| 20 |
submit_button = gr.Button("upload")
|
| 21 |
-
submit_button.click(
|
| 22 |
|
| 23 |
demo.launch()
|
|
|
|
| 9 |
for page in pdf_reader.pages:
|
| 10 |
text += page.extract_text()
|
| 11 |
return text
|
| 12 |
+
|
| 13 |
+
def process_file(file):
|
| 14 |
+
file_extension = file.name.split(".")[-1].lower()
|
| 15 |
+
|
| 16 |
+
if file_extension == 'pdf':
|
| 17 |
+
ocr_text = process_pdf(file)
|
| 18 |
+
return ocr_text
|
| 19 |
+
|
| 20 |
+
elif file_extension == 'docx':
|
| 21 |
+
docx_document = DocxDocument(file.name)
|
| 22 |
+
text = ""
|
| 23 |
+
for paragraph in docx_document.paragraphs:
|
| 24 |
+
text += paragraph.text + "\n"
|
| 25 |
+
|
| 26 |
+
return text
|
| 27 |
+
#return [Document(text=text)]
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|
| 31 |
|
| 32 |
with gr.Blocks() as demo:
|
| 33 |
gr.Markdown("### File upload", elem_classes="tab-header")
|
|
|
|
| 37 |
file_input = gr.File(label="Wähle eine PDF-Datei aus", type="filepath")
|
| 38 |
with gr.Row():
|
| 39 |
submit_button = gr.Button("upload")
|
| 40 |
+
submit_button.click(process_file, inputs=file_input, outputs=text_output)
|
| 41 |
|
| 42 |
demo.launch()
|