pypdf_quickstart_extract_text_and_merge_pdfs.py

1from pypdf import PdfReader, PdfWriter
2
3# Part 1: Extracting text from a PDF
4reader = PdfReader("example.pdf")
5number_of_pages = len(reader.pages)
6page = reader.pages[0]
7text = page.extract_text()
8print(f"Extracted text from page 1: {text}")
9
10# Part 2: Merging PDFs
11merger = PdfWriter()
12
13for pdf in ["file1.pdf", "file2.pdf", "file3.pdf"]:
14    merger.append(pdf)
15
16merger.write("merged-pdf.pdf")
17merger.close()