Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -73,7 +73,7 @@ def parse_pdf(pdf_file, output_format, progress=gr.Progress()):
|
|
73 |
"tables": [table.to_dict(orient='records') for table in tables if not table.columns.duplicated().any()],
|
74 |
"images": images
|
75 |
}
|
76 |
-
json.dump(json_data, tmp, indent=4)
|
77 |
elif output_format == "Markdown":
|
78 |
markdown_text = f"# Extracted Text\n\n{text}\n\n# Tables\n"
|
79 |
for i, table in enumerate(tables):
|
@@ -84,7 +84,7 @@ def parse_pdf(pdf_file, output_format, progress=gr.Progress()):
|
|
84 |
for image in images:
|
85 |
image_path = os.path.join(os.getcwd(), image["filename"])
|
86 |
markdown_text += f'\n'
|
87 |
-
tmp.write(markdown_text.encode('utf-8'))
|
88 |
elif output_format == "HTML":
|
89 |
html_text = f"<p>{text}</p>\n\n<h2>Tables</h2>\n"
|
90 |
for i, table in enumerate(tables):
|
@@ -95,7 +95,7 @@ def parse_pdf(pdf_file, output_format, progress=gr.Progress()):
|
|
95 |
for image in images:
|
96 |
image_path = os.path.join(os.getcwd(), image["filename"])
|
97 |
html_text += f'<img src="{image_path}" alt="Image"><br>\n'
|
98 |
-
tmp.write(html_text.encode('utf-8'))
|
99 |
download_path = tmp.name
|
100 |
|
101 |
return text, download_path
|
@@ -117,4 +117,4 @@ iface = gr.Interface(
|
|
117 |
)
|
118 |
|
119 |
if __name__ == "__main__":
|
120 |
-
iface.launch() # Temporarily disable sharing
|
|
|
73 |
"tables": [table.to_dict(orient='records') for table in tables if not table.columns.duplicated().any()],
|
74 |
"images": images
|
75 |
}
|
76 |
+
json.dump(json_data, tmp, indent=4)
|
77 |
elif output_format == "Markdown":
|
78 |
markdown_text = f"# Extracted Text\n\n{text}\n\n# Tables\n"
|
79 |
for i, table in enumerate(tables):
|
|
|
84 |
for image in images:
|
85 |
image_path = os.path.join(os.getcwd(), image["filename"])
|
86 |
markdown_text += f'\n'
|
87 |
+
tmp.write(markdown_text.encode('utf-8'))
|
88 |
elif output_format == "HTML":
|
89 |
html_text = f"<p>{text}</p>\n\n<h2>Tables</h2>\n"
|
90 |
for i, table in enumerate(tables):
|
|
|
95 |
for image in images:
|
96 |
image_path = os.path.join(os.getcwd(), image["filename"])
|
97 |
html_text += f'<img src="{image_path}" alt="Image"><br>\n'
|
98 |
+
tmp.write(html_text.encode('utf-8'))
|
99 |
download_path = tmp.name
|
100 |
|
101 |
return text, download_path
|
|
|
117 |
)
|
118 |
|
119 |
if __name__ == "__main__":
|
120 |
+
iface.launch() # Temporarily disable sharing for debugging
|