Answers for "python pdf text"

read text from a pdffile 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()

pdf to text python

#!pip install tabula-py
import tabula
#read all table data
df = tabula.read_pdf("sample.pdf",pages=[1,2])
df[1]

#tabula.convert_into("sample.pdf", "sample.csv", output_format="csv")