@@ -9,12 +9,12 @@ def convert_pdf_to_text(pdf_path, text_path):
99 :param text_path: Path to save the output text file
1010 """
1111 try :
12- doc = fitz .open (pdf_path )
12+ doc = fitz .open (pdf_path )# Open the PDF document
1313 text = ""
1414 for page in doc :
15- text += page .get_text ("text" )
15+ text += page .get_text ("text" )# Extract text from each page
1616 with open (text_path , "w" , encoding = "utf-8" ) as txt_file :
17- txt_file .write (text )
17+ txt_file .write (text )# Save extracted text to a text file
1818 print (f"Text extracted and saved to { text_path } )
1919 except Exception as e :
2020 print (f"Error converting PDF to text: { e } )
@@ -26,13 +26,13 @@ def convert_pdf_to_images(pdf_path, images_folder):
2626 :param images_folder: Folder to save the output images
2727 """
2828 try :
29- doc = fitz .open (pdf_path )
30- os .makedirs (images_folder , exist_ok = True )
29+ doc = fitz .open (pdf_path )# Open the PDF document
30+ os .makedirs (images_folder , exist_ok = True )# Create the output folder if it doesn't exist
3131 for page_num , page in enumerate (doc ):
3232 image_path = os .path .join (images_folder , f"page_{ page_num + 1 } )
3333 pix = page .get_pixmap (matrix = fitz .Matrix (2 , 2 )) # Increase resolution for better quality
3434 img = Image .frombytes ("RGB" , (pix .width , pix .height ), pix .samples )
35- img .save (image_path , format = "PNG" )
35+ img .save (image_path , format = "PNG" )# Save each page as a PNG image
3636 print (f"Images saved to { images_folder } )
3737 except Exception as e :
3838 print (f"Error converting PDF to images: { e } )
0 commit comments