File size: 358 Bytes
e675bdb
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
import io
from pathlib import Path
from pypdf import PdfReader


def load_text(filename: str, content: bytes) -> str:
    ext = Path(filename).suffix.lower()
    if ext == ".pdf":
        reader = PdfReader(io.BytesIO(content))
        return "\n".join(page.extract_text() or "" for page in reader.pages)
    return content.decode("utf-8", errors="replace")