Spaces:
Sleeping
Sleeping
File size: 1,302 Bytes
6fc3143 12fe8d7 6fc3143 12fe8d7 6fc3143 |
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 |
import logging
from pathlib import Path
from typing import Optional, Union
import PyPDF2
logger = logging.getLogger(__name__)
class PDFParser:
"""
Extracts text from PDF files.
"""
@staticmethod
def parse(file_path: Union[str, Path]) -> str:
"""
Extract text from a PDF file.
"""
path = Path(file_path)
if not path.exists():
raise FileNotFoundError(f"PDF file not found: {path}")
logger.info(f"Parsing PDF: {path}")
text_content = []
try:
with open(path, 'rb') as file:
reader = PyPDF2.PdfReader(file)
num_pages = len(reader.pages)
logger.info(f"PDF has {num_pages} pages")
for i, page in enumerate(reader.pages):
text = page.extract_text()
if text:
text_content.append(text)
full_text = "\n\n".join(text_content)
logger.info(f"Extracted {len(full_text)} characters from PDF")
return full_text
except Exception as e:
logger.error(f"Error parsing PDF: {e}")
raise RuntimeError(f"Failed to parse PDF: {e}")
|