Neurolingua
commited on
Commit
•
9a1ecae
1
Parent(s):
2b88356
Update teacher_function.py
Browse files- teacher_function.py +6 -1
teacher_function.py
CHANGED
@@ -4,8 +4,13 @@ from pdf2image import convert_from_path
|
|
4 |
import cv2
|
5 |
import numpy as np
|
6 |
import pytesseract
|
|
|
|
|
7 |
AI71_API_KEY = "api71-api-652e5c6c-8edf-41d0-9c34-28522b07bef9"
|
8 |
|
|
|
|
|
|
|
9 |
def extract_text_from_pdf(pdf_file):
|
10 |
text = ""
|
11 |
reader = PdfReader(pdf_file)
|
@@ -33,7 +38,7 @@ def generate_questions_from_text(text, no_of_questions, marks_per_part, no_parts
|
|
33 |
return "".join(questions)
|
34 |
|
35 |
def extract_text_from_image(image_path):
|
36 |
-
img =
|
37 |
text = pytesseract.image_to_string(img)
|
38 |
return text
|
39 |
|
|
|
4 |
import cv2
|
5 |
import numpy as np
|
6 |
import pytesseract
|
7 |
+
import subprocess
|
8 |
+
from PIL import Image
|
9 |
AI71_API_KEY = "api71-api-652e5c6c-8edf-41d0-9c34-28522b07bef9"
|
10 |
|
11 |
+
subprocess.run(['apt-get','update'])
|
12 |
+
subprocess.run(['apt-get','install','-y','tesseract-ocr'])
|
13 |
+
|
14 |
def extract_text_from_pdf(pdf_file):
|
15 |
text = ""
|
16 |
reader = PdfReader(pdf_file)
|
|
|
38 |
return "".join(questions)
|
39 |
|
40 |
def extract_text_from_image(image_path):
|
41 |
+
img = Image.open(image_path)
|
42 |
text = pytesseract.image_to_string(img)
|
43 |
return text
|
44 |
|