[Python] CV extraction problem with double-column format

I wrote code to extract PDF resumes using PyMuPDF. It works for single-column resumes, but for double-column resumes like those from Canva, the extraction is messy and disorganized. I need help to properly extract the resume with the correct information.

Here is an example of a resume: example image

I made two files: an extract file and a main file.

Here is my extraction file for resumes (extract.py):

import fitz # PyMuPDF
import re
import sys
from pathlib import Path

def extract_text_from_pdf(pdf_path: str) -> str:
doc = fitz.open(pdf_path)
text = ""
for page in doc:
blocks = page.get_text("blocks") # Retrieve the text blocks
# Sorting by vertical position to maintain the order
blocks.sort(key=lambda b: b[1])
for b in blocks:
text += b[4].strip() + "\n" # b[4] Contains the text of the block
text += "\n" # Page separator
return text



def clean_text(text: str) -> str:
# Remove multiple spaces but keep line breaks
text = re.sub(r"[ \t]+", " ", text) # Multiple spaces → single space
text = re.sub(r"\n{2,}", "\n\n", text) # 2+ empty lines → 2 lines
text = text.strip()
return text

def save_text_to_file(text: str, output_path: str):
with open(output_path, "w", encoding="utf-8") as f:
f.write(text)


main.py:

import sys
from pathlib import Path

from extract import extract_text_from_pdf, clean_text, save_text_to_file



def main(pdf_path: str):
raw_text = extract_text_from_pdf(pdf_path)
cleaned_text = clean_text(raw_text)

output_path = Path(pdf_path).with_suffix(".txt")
save_text_to_file(cleaned_text, output_path)

print(f"[OK] Extracted and cleaned text → {output_path}")

if __name__ == "__main__":
if len(sys.argv) < 2:
print("Usage: python extract.py path/to/file.pdf")
else:
main(sys.argv[1])

Continue reading...