revise: PPT script reader

app.py

@@ -6,6 +6,7 @@ import time
 import numpy as np
 import pandas as pd
 import PyPDF2
+from pptx import Presentation
 import openai
 import subprocess
 
@@ -117,16 +118,31 @@ def text2ppt(token_key, input_prompt, input_theme):
 def ppt2script(token_key, input_file, input_type):
     openai.api_key = token_key
 
-    with open(input_file, 'rb') as pdf_file:
-        pdf_reader = PyPDF2.PdfReader(pdf_file)
-        num_pages = len(pdf_reader.pages)
+    if input_type=="PDF":
+        with open(input_file, 'rb') as pdf_file:
+            pdf_reader = PyPDF2.PdfReader(pdf_file)
+            num_pages = len(pdf_reader.pages)
+    
+            # 각 페이지의 내용을 문자열로 변환합니다.
+            text = ""
+            for page_num in range(num_pages):
+                page = pdf_reader.pages[page_num]
+                text += "[PAGE_NUM " + str(page_num + 1) + "]"
+                text += page.extract_text()
+    else:
+        prs = Presentation(path_to_presentation)
 
-        # 각 페이지의 내용을 문자열로 변환합니다.
         text = ""
-        for page_num in range(num_pages):
-            page = pdf_reader.pages[page_num]
+        page_num = 0
+        for slide in prs.slides:
             text += "[PAGE_NUM " + str(page_num + 1) + "]"
-            text += page.extract_text()
+            page_num += 1
+            for shape in slide.shapes:
+                if not shape.has_text_frame:
+                    continue
+                for paragraph in shape.text_frame.paragraphs:
+                    for run in paragraph.runs:
+                        text += run.text
 
     header = """
     너는는 PPT 발표에 도움을 주는 조력자야.