Update app.py
Browse files
app.py
CHANGED
|
@@ -4,6 +4,7 @@ from transformers import Trainer, AutoTokenizer, XLMRobertaForSequenceClassifica
|
|
| 4 |
import torch
|
| 5 |
import pickle
|
| 6 |
import re
|
|
|
|
| 7 |
|
| 8 |
def checker(content):
|
| 9 |
#if isinstance(content, bytes):#falls es ein Byte-String ist
|
|
@@ -36,7 +37,12 @@ def process_file(file):
|
|
| 36 |
|
| 37 |
# lese die Datei ein
|
| 38 |
def read_file(file):
|
| 39 |
-
if file:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
with open(file.name, 'r', encoding='utf-8') as f:
|
| 41 |
content = f.read()
|
| 42 |
#with open(file.name, 'rb') as f:
|
|
|
|
| 4 |
import torch
|
| 5 |
import pickle
|
| 6 |
import re
|
| 7 |
+
import PyPDF2
|
| 8 |
|
| 9 |
def checker(content):
|
| 10 |
#if isinstance(content, bytes):#falls es ein Byte-String ist
|
|
|
|
| 37 |
|
| 38 |
# lese die Datei ein
|
| 39 |
def read_file(file):
|
| 40 |
+
if ".pdf" in file.name:
|
| 41 |
+
# creating a pdf reader object
|
| 42 |
+
reader = PyPDF2.PdfReader(file.name)
|
| 43 |
+
# print the text of the first page
|
| 44 |
+
print(reader.pages[0].extract_text())
|
| 45 |
+
else:
|
| 46 |
with open(file.name, 'r', encoding='utf-8') as f:
|
| 47 |
content = f.read()
|
| 48 |
#with open(file.name, 'rb') as f:
|