riteshcp commited on
Commit
522330d
·
verified ·
1 Parent(s): 506d115

Create app.py

Browse files
Files changed (1) hide show
  1. app.py +50 -0
app.py ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import streamlit as st
2
+ from PyPDF2 import PdfReader
3
+ from docx import Document
4
+ import pandas as pd
5
+
6
+ # Define functions for extracting text from different document types
7
+ def extract_text_from_pdf(pdf_file):
8
+ reader = PdfReader(pdf_file)
9
+ text = ''
10
+ for page in reader.pages:
11
+ text += page.extract_text()
12
+ return text
13
+
14
+ def extract_text_from_docx(docx_file):
15
+ doc = Document(docx_file)
16
+ text = ''
17
+ for para in doc.paragraphs:
18
+ text += para.text
19
+ return text
20
+
21
+ def extract_text_from_excel(excel_file):
22
+ df = pd.read_excel(excel_file)
23
+ return df.to_string()
24
+
25
+ # Streamlit UI elements
26
+ st.title("Document Text Extractor")
27
+
28
+ # Upload multiple files of specific types
29
+ uploaded_files = st.file_uploader("Upload your files", type=['pdf', 'docx', 'xlsx'], accept_multiple_files=True)
30
+
31
+ # If the 'Extract Text' button is clicked
32
+ if st.button("Extract Text"):
33
+ complete_text = ""
34
+ if uploaded_files is not None:
35
+ # Loop through all the uploaded files
36
+ for uploaded_file in uploaded_files:
37
+ # Identify the file type and extract text accordingly
38
+ if uploaded_file.name.endswith('.pdf'):
39
+ complete_text += extract_text_from_pdf(uploaded_file)
40
+ elif uploaded_file.name.endswith('.docx'):
41
+ complete_text += extract_text_from_docx(uploaded_file)
42
+ elif uploaded_file.name.endswith('.xlsx'):
43
+ complete_text += extract_text_from_excel(uploaded_file)
44
+
45
+ # Display the extracted text
46
+ st.text_area("Extracted Text", complete_text, height=300)
47
+ else:
48
+ st.write("Please upload at least one file to extract text.")
49
+
50
+