PYTHON

how to read pdf in python

# importing required modules
import PyPDF2
 
# creating a pdf file object
pdfFileObj = open('example.pdf', 'rb')
 
# creating a pdf reader object
pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
 
# printing number of pages in pdf file
print(pdfReader.numPages)
 
# creating a page object
pageObj = pdfReader.getPage(0)
 
# extracting text from page
print(pageObj.extractText())
 
# closing the pdf file object
pdfFileObj.close()

read pdf py

import textract
text = textract.process('path/to/pdf/file', method='pdfminer')

python read pdf

from PyPDF2 import PDFFileReader
temp = open('document_path.PDF', 'rb')
PDF_read = PDFFileReader(temp)
first_page = PDF_read.getPage(0)
print(first_page.extractText())

python read pdf

from PDFminer.high_level import extract_text
PDF_read = extract_text('document_path.PDF')

python read pdf

import PDFplumber
with PDFplumber.open("document_path.PDF") as temp:
  first_page = temp.pages[0]
  print(first_page.extract_text())

python read pdf

import textract
PDF_read = textract.process('document_path.PDF', method='PDFminer')