import pdfplumber
with pdfplumber.open("doc.pdf") as pdf:
    text = "\n".join(p.extract_text() for p in pdf.pages)

import openpyxl
wb = openpyxl.load_workbook("data.xlsx")
ws = wb.active
data = [[cell.value for cell in row] for row in ws.iter_rows()]

from docx import Document
doc = Document("report.docx")
text = "\n".join(p.text for p in doc.paragraphs)

import pandas as pd
df = pd.read_excel("data.xlsx")
df.to_csv("data.csv", index=False)

with pdfplumber.open("doc.pdf") as pdf:
    tables = pdf.pages[0].extract_tables()