Spaces:
Sleeping
Sleeping
File size: 2,796 Bytes
164d23a | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 | """
Module for extracting text from different file formats.
Supports: TXT, PDF, DOCX
"""
import os
import logging
from typing import Optional
try:
import PyPDF2
except ImportError:
PyPDF2 = None
try:
from docx import Document
except ImportError:
Document = None
# Configurazione logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
def extract_text(file_path: str) -> Optional[str]:
"""
Extract text from a supported file.
Args:
file_path (str): Path to file to process
Returns:
Optional[str]: Extracted text or None if error
"""
if not os.path.exists(file_path):
logger.error(f"File not found: {file_path}")
return None
file_extension = os.path.splitext(file_path)[1].lower()
try:
if file_extension == '.txt':
return _extract_from_txt(file_path)
elif file_extension == '.pdf':
return _extract_from_pdf(file_path)
elif file_extension == '.docx':
return _extract_from_docx(file_path)
else:
logger.error(f"Unsupported file format: {file_extension}")
return None
except Exception as e:
logger.error(f"Error extracting text from {file_path}: {str(e)}")
return None
def _extract_from_txt(file_path: str) -> str:
"""Extract text from TXT file."""
encodings = ['utf-8', 'latin-1', 'cp1252']
for encoding in encodings:
try:
with open(file_path, 'r', encoding=encoding) as file:
return file.read()
except UnicodeDecodeError:
continue
# If all encodings fail, try with error handling
with open(file_path, 'r', encoding='utf-8', errors='replace') as file:
return file.read()
def _extract_from_pdf(file_path: str) -> str:
"""Extract text from PDF file."""
if PyPDF2 is None:
raise ImportError("PyPDF2 not installed. Install with: pip install pypdf2")
text = ""
with open(file_path, 'rb') as file:
pdf_reader = PyPDF2.PdfReader(file)
for page_num in range(len(pdf_reader.pages)):
page = pdf_reader.pages[page_num]
text += page.extract_text() + "\n"
return text.strip()
def _extract_from_docx(file_path: str) -> str:
"""Extract text from DOCX file."""
if Document is None:
raise ImportError("python-docx not installed. Install with: pip install python-docx")
doc = Document(file_path)
text = ""
for paragraph in doc.paragraphs:
text += paragraph.text + "\n"
return text.strip()
def get_supported_extensions() -> list:
"""Return supported file extensions."""
return ['.txt', '.pdf', '.docx']
|