113 lines
4.2 KiB
Python
113 lines
4.2 KiB
Python
import os
|
|
import re
|
|
from pptx import Presentation
|
|
from fpdf import FPDF
|
|
from fpdf.enums import XPos, YPos
|
|
|
|
# Define the PDF layout and styling
|
|
class NotesPDF(FPDF):
|
|
def header(self):
|
|
self.set_font("Helvetica", "B", 12)
|
|
self.set_text_color(100, 100, 100)
|
|
self.cell(0, 10, "Presentation Slides & Notes", align="C", new_x=XPos.LMARGIN, new_y=YPos.NEXT)
|
|
self.ln(5)
|
|
|
|
def footer(self):
|
|
self.set_y(-15)
|
|
self.set_font("Helvetica", "I", 8)
|
|
self.set_text_color(150, 150, 150)
|
|
self.cell(0, 10, f"Page {self.page_no()}", align="C")
|
|
|
|
def clean_text_for_fpdf(text):
|
|
"""Replaces unsupported Unicode characters with standard Latin-1 equivalents."""
|
|
if not text:
|
|
return ""
|
|
|
|
replacements = {
|
|
'\u2018': "'", '\u2019': "'", '\u201c': '"', '\u201d': '"',
|
|
'\u2013': "-", '\u2014': "--", '\u2022': "*", '\u2026': "...",
|
|
'\u00A0': " ", '\u2122': "TM", '\u00a9': "(c)", '\u00ae': "(R)"
|
|
}
|
|
for search, replace in replacements.items():
|
|
text = text.replace(search, replace)
|
|
|
|
return text.encode('latin-1', 'ignore').decode('latin-1')
|
|
|
|
def find_slide_image(images_folder, slide_num):
|
|
"""Smartly searches for an image file matching the slide number."""
|
|
if not os.path.exists(images_folder):
|
|
return None
|
|
|
|
for filename in os.listdir(images_folder):
|
|
# Check if it's an image file
|
|
if filename.lower().endswith(('.png', '.jpg', '.jpeg')):
|
|
# Extract all numbers from the filename
|
|
numbers = re.findall(r'\d+', filename)
|
|
# If the last number in the filename matches our slide number, we found it!
|
|
if numbers and int(numbers[-1]) == slide_num:
|
|
return os.path.join(images_folder, filename)
|
|
return None
|
|
|
|
def create_handout_pdf(pptx_path, images_folder, output_pdf):
|
|
print(f"Reading presentation: {pptx_path}...")
|
|
|
|
try:
|
|
prs = Presentation(pptx_path)
|
|
except Exception as e:
|
|
print(f"Error loading PPTX: {e}")
|
|
return
|
|
|
|
pdf = NotesPDF()
|
|
pdf.set_auto_page_break(auto=True, margin=15)
|
|
|
|
for i, slide in enumerate(prs.slides):
|
|
slide_num = i + 1
|
|
pdf.add_page()
|
|
|
|
# 1. Smartly find and place the Slide Image
|
|
img_path = find_slide_image(images_folder, slide_num)
|
|
|
|
if img_path:
|
|
# A4 width is ~210mm. 170mm width leaves 20mm margins on each side.
|
|
pdf.image(img_path, x=20, w=170)
|
|
pdf.ln(5)
|
|
else:
|
|
pdf.set_font("Helvetica", "B", 12)
|
|
pdf.set_text_color(255, 0, 0)
|
|
pdf.cell(0, 10, f"[Slide {slide_num} Image Missing - Check 'images' folder]", new_x=XPos.LMARGIN, new_y=YPos.NEXT)
|
|
pdf.ln(5)
|
|
|
|
# 2. Extract and Place the Notes
|
|
pdf.set_font("Helvetica", "B", 14)
|
|
pdf.set_text_color(0, 0, 0)
|
|
pdf.cell(0, 10, f"Notes - Slide {slide_num}:", new_x=XPos.LMARGIN, new_y=YPos.NEXT)
|
|
|
|
pdf.set_font("Helvetica", "", 11)
|
|
notes_text = ""
|
|
|
|
if slide.has_notes_slide and slide.notes_slide.notes_text_frame:
|
|
notes_text = slide.notes_slide.notes_text_frame.text
|
|
|
|
if not notes_text.strip():
|
|
notes_text = "(No notes provided for this slide)"
|
|
|
|
notes_text = clean_text_for_fpdf(notes_text)
|
|
pdf.multi_cell(0, 6, notes_text)
|
|
|
|
print(f"Compiling PDF...")
|
|
pdf.output(output_pdf)
|
|
print(f"✅ Success! Your file is ready: {output_pdf}")
|
|
|
|
if __name__ == "__main__":
|
|
PPTX_FILE = "/Users/guillemhernandezsola/Downloads/Assets/presentation.pptx"
|
|
# Make sure this folder exists in the same directory where you run the script!
|
|
IMAGES_DIR = "/Users/guillemhernandezsola/Downloads/Assets/images"
|
|
OUTPUT_FILE = "/Users/guillemhernandezsola/Downloads/Assets/Final_Presentation_Notes.pdf"
|
|
|
|
if not os.path.exists(IMAGES_DIR):
|
|
print(f"⚠️ ERROR: The folder '{IMAGES_DIR}' was not found.")
|
|
print("Please create it in: /Users/guillemhernandezsola/code/scripts/file-management/")
|
|
print("And make sure you exported your slide images from OnlyOffice into it!")
|
|
else:
|
|
create_handout_pdf(PPTX_FILE, IMAGES_DIR, OUTPUT_FILE)
|