pip install PyPDF2

import PyPDF2

myfile=open ('filename.pdf',mode='rb')

pdf_reader= PyPDF2.PdfFileReader(myfile)

pdf_reader.numPages

page_one=pdf_reader.getPage(0)
print(page_one.extractText())

# create page object and extract text
pageObj = pdf_reader.getPage(0)
page1 = pageObj.extractText()
page1

# strip away page header
page1 = page1[25:]

# insert commas to separate variables and then remove excess strings
page1 = page1.replace('\n \n',', ').replace('\n','')

myfile.close()

pdf_writer=PyPDF2.PdfFileWriter()
pdf_writer.addPage(page_one)
pdf_output=open('New updated file.pdf',mode='wb')
pdf_writer.write(pdf_output)
page=pdf_writer.getPage(0).extractText()

print(pdf_reader.isEncrypted)

pip install tabula-py

import tabula
df = tabula.io.read_pdf(url, pages='all')

# ex
df[0]