FD900 commited on
Commit
269c8c2
·
verified ·
1 Parent(s): fd607c0

Create tools/file_loader.py

Browse files
Files changed (1) hide show
  1. tools/file_loader.py +14 -0
tools/file_loader.py ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import io
2
+ import pandas as pd
3
+ from PyPDF2 import PdfReader
4
+
5
+ def read_pdf(file_bytes):
6
+ reader = PdfReader(io.BytesIO(file_bytes))
7
+ return "\n".join(page.extract_text() for page in reader.pages if page.extract_text())
8
+
9
+ def read_csv(file_bytes):
10
+ df = pd.read_csv(io.BytesIO(file_bytes))
11
+ return df.to_string()
12
+
13
+ def read_txt(file_bytes):
14
+ return file_bytes.decode("utf-8")