amir / document_processor.py
amirmadjour's picture
translation working pdf
b584aa5
Raw History Blame Contribute Delete
1.73 kB
from pathlib import Path
import PyPDF2
from docx import Document
import pptx
import pandas as pd
import tempfile
def supported_formats():
return ['.pdf', '.docx', '.pptx', '.txt', '.xlsx']
def process_document(file_path: str) -> str:
"""Extract text from various document formats"""
file_ext = Path(file_path).suffix.lower()
try:
if file_ext == '.pdf':
return _extract_pdf_text(file_path)
elif file_ext == '.docx':
return _extract_docx_text(file_path)
elif file_ext == '.pptx':
return _extract_pptx_text(file_path)
elif file_ext == '.txt':
with open(file_path, 'r', encoding='utf-8') as f:
return f.read()
elif file_ext == '.xlsx':
return _extract_excel_text(file_path)
else:
raise ValueError(f"Unsupported file format: {file_ext}")
except Exception as e:
raise ValueError(f"Error processing document: {str(e)}")
def _extract_pdf_text(file_path: str) -> str:
text = ""
with open(file_path, 'rb') as f:
reader = PyPDF2.PdfReader(f)
for page in reader.pages:
text += page.extract_text() + "\n"
return text
def _extract_docx_text(file_path: str) -> str:
doc = Document(file_path)
return "\n".join([para.text for para in doc.paragraphs])
def _extract_pptx_text(file_path: str) -> str:
prs = pptx.Presentation(file_path)
text = []
for slide in prs.slides:
for shape in slide.shapes:
if hasattr(shape, "text"):
text.append(shape.text)
return "\n".join(text)
def _extract_excel_text(file_path: str) -> str:
df = pd.read_excel(file_path)
return df.to_string()