1# pip install tika
2from tika import parser
3
4raw = parser.from_file('yourfile.pdf')
5print(raw['content'])
6
1#!pip install tabula-py
2import tabula
3#read all table data
4df = tabula.read_pdf("sample.pdf",pages=[1,2])
5df[1]
6
7#tabula.convert_into("sample.pdf", "sample.csv", output_format="csv")