Soumen commited on
Commit
f0ec4df
·
1 Parent(s): bb3614e

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +3 -3
app.py CHANGED
@@ -64,14 +64,14 @@ from PIL import Image
64
  # all_page_text += text + " " #page.extractText()
65
  # return all_page_text
66
  def read_pdf_with_pdfplumber(file):
67
- all_page_text=""
68
  with pdfplumber.open(file) as pdf:
69
  page = pdf.pages[0]
70
  #return page.extract_text()
71
  # get co-ordinates to cr
72
  #img = Image.open(im)
73
- img = page.save("img.png")
74
- image_name = cv2.imread("img.png")
75
  ## get co-ordinates to cr
76
  text = pytesseract.image_to_string(image_name, lang="ben") if st.checkbox("Mark to see Bangla Image's Text") else pytesseract.image_to_string(image_name)
77
  all_page_text += text + " " #page.extractText()
 
64
  # all_page_text += text + " " #page.extractText()
65
  # return all_page_text
66
  def read_pdf_with_pdfplumber(file):
67
+ all_page_text=" "
68
  with pdfplumber.open(file) as pdf:
69
  page = pdf.pages[0]
70
  #return page.extract_text()
71
  # get co-ordinates to cr
72
  #img = Image.open(im)
73
+ img = page.save("img.png")
74
+ image_name = cv2.imread("img.png")
75
  ## get co-ordinates to cr
76
  text = pytesseract.image_to_string(image_name, lang="ben") if st.checkbox("Mark to see Bangla Image's Text") else pytesseract.image_to_string(image_name)
77
  all_page_text += text + " " #page.extractText()