PDF_Merger / app.py
Ze101's picture
Update app.py
12f7318 verified
Raw
History Blame Contribute Delete
6.02 kB
import os
from fpdf import FPDF
from PyPDF2 import PdfMerger
from PIL import Image
import gradio as gr
#import aspose.words as aw
import pypandoc
def docx_to_pdf(docx_file, pdf_file):
try:
pypandoc.convert_file(
docx_file, 'pdf', outputfile=pdf_file, extra_args=['--pdf-engine=pdflatex']
)
except OSError:
# Download pandoc programmatically if it's not found
print("Pandoc not found. Downloading pandoc...")
pypandoc.download_pandoc()
pypandoc.convert_file(
docx_file, 'pdf', outputfile=pdf_file, extra_args=['--pdf-engine=pdflatex']
)
# Function to add a single text input as a new page in an FPDF object
def add_text_as_page(pdf, text):
pdf.add_page()
pdf.set_auto_page_break(auto=True, margin=15)
pdf.set_font("Arial", size=12)
pdf.multi_cell(0, 10, text)
# Function to convert an image to a standalone PDF
def image_to_pdf(image_file):
img = Image.open(image_file)
pdf_path = image_file + ".pdf"
img.convert('RGB').save(pdf_path)
return pdf_path
# Function to merge multiple PDFs
def merge_pdfs(pdfs):
merger = PdfMerger()
for pdf in pdfs:
merger.append(pdf)
output_path = "merged_output.pdf"
merger.write(output_path)
merger.close()
return output_path
# Convert DOCX to PDF
#def docx_to_pdf(docx_file, pdf_file):
# doc = aw.Document(docx_file)
# doc.save(pdf_file)
# Main function to process uploaded files and manual text inputs
def process_files_and_text(files, manual_texts, file_order):
pdfs = []
manual_text_pdf = "manual_texts.pdf"
pdf = FPDF()
# Process uploaded files according to file_order
for file_name in file_order:
file = next(f for f in files if f.name == file_name)
file_name, file_extension = os.path.splitext(file.name)
if file_extension.lower() == ".pdf":
pdfs.append(file.name)
elif file_extension.lower() == ".txt":
text = file.read().decode("utf-8")
add_text_as_page(pdf, text)
elif file_extension.lower() == ".docx":
docx_to_pdf(file.name, file_name + ".pdf")
#pdf_file = file_name + ".pdf"
#docx_to_pdf(file.name, pdf_file)
pdfs.append(file_name + ".pdf")
elif file_extension.lower() in [".png", ".jpg", ".jpeg"]:
pdf_output = image_to_pdf(file.name)
pdfs.append(pdf_output)
# Add manual text inputs, with each input becoming a new page
for text in manual_texts:
if text.strip(): # Add only non-empty text
add_text_as_page(pdf, text)
# Save manual text inputs to PDF if any pages were added
if len(pdf.pages) > 0:
pdf.output(manual_text_pdf)
pdfs.append(manual_text_pdf)
# Merge all PDFs into one
merged_pdf = merge_pdfs(pdfs)
return merged_pdf
# Function to move items up or down in the list
def reorder_files(file_list, direction, index):
if direction == "up" and index > 0:
file_list[index], file_list[index - 1] = file_list[index - 1], file_list[index]
elif direction == "down" and index < len(file_list) - 1:
file_list[index], file_list[index + 1] = file_list[index + 1], file_list[index]
return file_list
# Gradio interface function
def file_merger(files, texts, file_order):
merged_pdf = process_files_and_text(files, texts, file_order)
return merged_pdf
# Define Gradio interface
with gr.Blocks() as iface:
gr.Markdown("### File Merger: Merge PDF, TXT, DOCX, Image files, and manual text inputs into a single PDF.")
with gr.Row():
file_input = gr.File(file_count="multiple", label="Upload Files")
manual_text_inputs = gr.Textbox(
lines=5,
placeholder="Enter text here...",
label="Manual Text Inputs",
elem_id="manual_text_inputs",
interactive=True
)
file_list_state = gr.State([])
file_display = gr.Textbox(
label="Uploaded Files (Reorder Below)",
interactive=False,
lines=10
)
file_index = gr.Number(label="File Index to Move (Starting from 0)", value=0, interactive=True)
with gr.Row():
move_up_button = gr.Button("Move Up")
move_down_button = gr.Button("Move Down")
add_more_button = gr.Button("Add More Text")
merge_button = gr.Button("Merge Files and Text")
output = gr.File(label="Download Merged PDF")
# Maintain a dynamic list for manual inputs
manual_texts_state = gr.State(value=[])
def add_text_to_state(current_text, state_texts):
state_texts.append(current_text)
return "", state_texts # Clear the input box and update the state
def update_file_list(files):
file_names = [file.name for file in files]
return file_names, "\n".join(file_names)
def handle_reorder(file_list, direction, index):
if 0 <= index < len(file_list):
reordered_list = reorder_files(file_list, direction, index)
return reordered_list, "\n".join(reordered_list)
return file_list, "\n".join(file_list) # No change if index is out of range
# Add functionality to add more text
add_more_button.click(add_text_to_state, inputs=[manual_text_inputs, manual_texts_state], outputs=[manual_text_inputs, manual_texts_state])
# Update file list when files are uploaded
file_input.change(update_file_list, inputs=[file_input], outputs=[file_list_state, file_display])
# Move files up or down
move_up_button.click(handle_reorder, inputs=[file_list_state, gr.Text("up"), file_index], outputs=[file_list_state, file_display])
move_down_button.click(handle_reorder, inputs=[file_list_state, gr.Text("down"), file_index], outputs=[file_list_state, file_display])
# Merge files and text
merge_button.click(file_merger, inputs=[file_input, manual_texts_state, file_list_state], outputs=output)
iface.launch(share=True)