how to convert pdf to text python code example
Example 1: 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")
Example 2: pdf to string python
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()