from pypdf import PdfReader, PdfWriter

# Read PDF
reader = PdfReader("input.pdf")
text = reader.pages[0].extract_text()

# Merge PDFs
writer = PdfWriter()
writer.append("file1.pdf")
writer.append("file2.pdf")
writer.write("merged.pdf")

# Split PDF
writer = PdfWriter()
writer.add_page(reader.pages[0])
writer.write("page1.pdf")

import pdfplumber

with pdfplumber.open("document.pdf") as pdf:
    page = pdf.pages[0]

    # Extract text with layout
    text = page.extract_text()

    # Extract tables
    tables = page.extract_tables()

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

c = canvas.Canvas("output.pdf", pagesize=letter)
c.drawString(100, 750, "Hello World")
c.save()

pdftotext document.pdf output.txt
pdftotext -layout document.pdf output.txt  # Preserve layout

qpdf input.pdf --pages . 1-5 -- output.pdf  # Extract pages
qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf

pdftk input.pdf output output.pdf user_pw password  # Add password
pdftk input.pdf cat 1-5 output first5.pdf  # Extract pages

import pytesseract
from pdf2image import convert_from_path

images = convert_from_path('scanned.pdf')
text = pytesseract.image_to_string(images[0])

import pandas as pd
import pdfplumber

with pdfplumber.open("document.pdf") as pdf:
    table = pdf.pages[0].extract_tables()[0]
    df = pd.DataFrame(table[1:], columns=table[0])
    df.to_excel("output.xlsx", index=False)