32 lines
1.1 KiB
Python
32 lines
1.1 KiB
Python
from sqlalchemy.ext.asyncio import AsyncSession
|
|
import os,logging,io
|
|
from fastapi import HTTPException
|
|
from pypdf import PdfReader
|
|
from sqlalchemy import select
|
|
from job.candidate.plugins import normalize_spaced_text
|
|
|
|
class FileRead:
|
|
def __init__(self,session:AsyncSession,filename=None,file=None):
|
|
self.session=session
|
|
self.filename=filename
|
|
self.file=file
|
|
|
|
async def read_file(self,file=None,filename=None):
|
|
try:
|
|
reader = PdfReader(io.BytesIO(self.file))
|
|
if reader.is_encrypted:
|
|
raise HTTPException(400, "PDF is password protected")
|
|
pages = [(page.extract_text() or "") for page in reader.pages]
|
|
return {
|
|
"filename": self.filename,
|
|
"num_pages": len(reader.pages),
|
|
"text": normalize_spaced_text("\n".join(pages)),
|
|
}
|
|
except HTTPException:
|
|
raise
|
|
except Exception as e:
|
|
raise HTTPException(400, str(e))
|
|
# async def get_intention(self,input):
|
|
# try:
|
|
# get_subject=Inbox_Messages.candidate_x_inbox(self.session,self.candidate_id)
|
|
# get_file= |