Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
from PIL import Image
|
3 |
+
import pytesseract # For basic text extraction (optional)
|
4 |
+
import pdfkit # For PDF generation
|
5 |
+
import os # For temporary file handling
|
6 |
+
|
7 |
+
# Function to process a single image with user-provided sequence number
|
8 |
+
def process_image(image_file, sequence_number):
|
9 |
+
image = Image.open(image_file)
|
10 |
+
|
11 |
+
# Optionally extract text using Tesseract (if needed for layout)
|
12 |
+
# text = pytesseract.image_to_string(image) # May require Tesseract installation
|
13 |
+
|
14 |
+
# Consider techniques for layout analysis and image manipulation (if complex)
|
15 |
+
|
16 |
+
return image, sequence_number # Return the image and its sequence number
|
17 |
+
|
18 |
+
# Function to generate the PDF
|
19 |
+
def generate_pdf(images_with_sequence):
|
20 |
+
pdf_name = "output.pdf"
|
21 |
+
|
22 |
+
# Create a temporary directory to store intermediate images (if needed)
|
23 |
+
# temp_dir = os.path.join(os.getcwd(), "temp_images")
|
24 |
+
# os.makedirs(temp_dir, exist_ok=True)
|
25 |
+
|
26 |
+
# Sort images by sequence number
|
27 |
+
images_with_sequence.sort(key=lambda x: x[1])
|
28 |
+
|
29 |
+
pdf_options = {
|
30 |
+
"margin-top": "0.5in",
|
31 |
+
"margin-right": "0.5in",
|
32 |
+
"margin-bottom": "0.5in",
|
33 |
+
"margin-left": "0.5in",
|
34 |
+
"encoding": "UTF-8",
|
35 |
+
"dpi": 300, # Adjust as needed
|
36 |
+
}
|
37 |
+
|
38 |
+
# Generate PDF content (consider layout strategies if necessary)
|
39 |
+
pdfkit.from_file(
|
40 |
+
[image[0] for image in images_with_sequence],
|
41 |
+
pdf_name,
|
42 |
+
options=pdf_options,
|
43 |
+
)
|
44 |
+
|
45 |
+
# Clean up temporary files (if used)
|
46 |
+
# for filename in os.listdir(temp_dir):
|
47 |
+
# os.remove(os.path.join(temp_dir, filename))
|
48 |
+
|
49 |
+
return pdf_name
|
50 |
+
|
51 |
+
st.title("Image to PDF Converter (Multiple Images)")
|
52 |
+
|
53 |
+
uploaded_images = st.file_uploader("Upload Images", type=["jpg", "jpeg", "png"], accept_multiple=True)
|
54 |
+
|
55 |
+
if uploaded_images:
|
56 |
+
images_with_sequence = []
|
57 |
+
|
58 |
+
for image_file in uploaded_images:
|
59 |
+
st.image(image_file, width=250) # Display uploaded images
|
60 |
+
|
61 |
+
sequence_options = [str(i) for i in range(1, len(uploaded_images) + 1)]
|
62 |
+
sequence_number = st.selectbox("Sequence Number", sequence_options)
|
63 |
+
|
64 |
+
processed_image, processed_sequence = process_image(image_file, int(sequence_number))
|
65 |
+
images_with_sequence.append((processed_image, processed_sequence))
|
66 |
+
|
67 |
+
if st.button("Generate PDF"):
|
68 |
+
pdf_name = generate_pdf(images_with_sequence)
|
69 |
+
st.success(f"PDF generated! Download: {pdf_name}")
|
70 |
+
|
71 |
+
with open(pdf_name, "rb") as pdf_file:
|
72 |
+
st.download_button("Download PDF", pdf_file, file_name=pdf_name)
|
73 |
+
|
74 |
+
# Delete the generated PDF after download (optional)
|
75 |
+
# os.remove(pdf_name)
|