Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,31 +1,38 @@
|
|
|
|
|
| 1 |
from docx import Document
|
|
|
|
| 2 |
|
| 3 |
-
def extract_text_from_docx(
|
| 4 |
-
"""Extracts all text from
|
| 5 |
try:
|
| 6 |
-
# Open the .docx file
|
| 7 |
-
doc = Document(
|
| 8 |
|
| 9 |
# Extract text from each paragraph in the document
|
| 10 |
text = ""
|
| 11 |
for paragraph in doc.paragraphs:
|
| 12 |
text += paragraph.text + '\n'
|
| 13 |
-
|
| 14 |
return text
|
| 15 |
|
| 16 |
except Exception as e:
|
| 17 |
-
|
| 18 |
return None
|
| 19 |
|
| 20 |
def main():
|
| 21 |
-
|
| 22 |
-
text = extract_text_from_docx(file_path)
|
| 23 |
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
|
| 30 |
if __name__ == "__main__":
|
| 31 |
main()
|
|
|
|
| 1 |
+
import streamlit as st
|
| 2 |
from docx import Document
|
| 3 |
+
import io
|
| 4 |
|
| 5 |
+
def extract_text_from_docx(file):
|
| 6 |
+
"""Extracts all text from an uploaded .docx file"""
|
| 7 |
try:
|
| 8 |
+
# Open the uploaded .docx file
|
| 9 |
+
doc = Document(io.BytesIO(file.read()))
|
| 10 |
|
| 11 |
# Extract text from each paragraph in the document
|
| 12 |
text = ""
|
| 13 |
for paragraph in doc.paragraphs:
|
| 14 |
text += paragraph.text + '\n'
|
| 15 |
+
|
| 16 |
return text
|
| 17 |
|
| 18 |
except Exception as e:
|
| 19 |
+
st.error(f"Error processing the document: {e}")
|
| 20 |
return None
|
| 21 |
|
| 22 |
def main():
|
| 23 |
+
st.title("Extract Text from DOCX")
|
|
|
|
| 24 |
|
| 25 |
+
# File upload
|
| 26 |
+
uploaded_file = st.file_uploader("Choose a DOCX file", type=["docx"])
|
| 27 |
+
|
| 28 |
+
if uploaded_file is not None:
|
| 29 |
+
text = extract_text_from_docx(uploaded_file)
|
| 30 |
+
|
| 31 |
+
if text:
|
| 32 |
+
st.subheader("Extracted Text")
|
| 33 |
+
st.text(text)
|
| 34 |
+
else:
|
| 35 |
+
st.error("Failed to extract text.")
|
| 36 |
|
| 37 |
if __name__ == "__main__":
|
| 38 |
main()
|