import PyPDF2
pdfFileObject = open(r"F:pdf.pdf", 'rb')
pdfReader = PyPDF2.PdfFileReader(pdfFileObject)
print(" No. Of Pages :", pdfReader.numPages)
pageObject = pdfReader.getPage(0)
print(pageObject.extractText())
pdfFileObject.close()
#!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")
pip install PyPDF2
import PyPDF2
pdfFileObject=open(r"F:fileName.pdf",'rb')
pdfReader = PyPDF2.PdfFileReader(pdfFileObject) //Creating reader obj
print(" No. Of Pages :", pdfReader.numPages)//To know no.of pages
from PyPDF2 import PdfReader
reader = PdfReader("example.pdf")
text = ""
for page in reader.pages:
text += page.extract_text() + "
"