Merge pull request #110 from realpython/creating-modifying-pdf

creating-modifying-pdfs

creating-and-modifying-pdfs/README.md

+# Creating and Modifying PDFs With Python
+
+This folder contains resources and materials for Real Python's [Creating and Modifying PDFs With Python](https://realpython.com/creating-modifying-pdf/) tutorial.
+
+There are two subfolders in this folder:
+
+1. **`practice_files/`:** Contains the sample PDFs used in the chapter
+2. **`source_code/`:** Contains source code from the chapter
+
+The source code files are organized by section of the article, and the start of each subsection is indicated with comments.
+
+The content of the companion tutorial was adapted from the "Creating and Modifying PDF Files" chapter of the book [*Python Basics: A Practical Introduction to Python 3*](https://realpython.com/products/python-basics-book/). If you enjoy this tutorial, check out the full book!

creating-and-modifying-pdfs/source_code/01-extracting-text-from-a-pdf.py

+# ---------------
+# Open a PDF File
+# ---------------
+
+from PyPDF2 import PdfFileReader
+
+# You might need to change this to match the path on your computer
+from pathlib import Path
+
+pdf_path = (
+    Path.home()
+    / "creating-and-modifying-pdfs"
+    / "practice_files"
+    / "Pride_and_Prejudice.pdf"
+)
+
+pdf = PdfFileReader(str(pdf_path))
+
+print(pdf.getNumPages())
+
+print(pdf.documentInfo)
+
+print(pdf.documentInfo.title)
+
+
+# ---------------------------
+# Extracting Text From a Page
+# ---------------------------
+
+first_page = pdf.getPage(0)
+
+print(type(first_page))
+
+print(first_page.extractText())
+
+for page in pdf.pages:
+    print(page.extractText())
+
+
+# -----------------------
+# Putting It All Together
+# -----------------------
+
+from pathlib import Path  # noqa
+from PyPDF2 import PdfFileReader  # noqa
+
+# Change the path below to the correct path for your computer.
+pdf_path = (
+    Path.home()
+    / "creating-and-modifying-pdfs"
+    / "practice-files"
+    / "Pride_and_Prejudice.pdf"
+)
+
+pdf_reader = PdfFileReader(str(pdf_path))
+output_file_path = Path.home() / "Pride_and_Prejudice.txt"
+
+with output_file_path.open(mode="w") as output_file:
+    title = pdf_reader.documentInfo.title
+    num_pages = pdf_reader.getNumPages()
+    output_file.write(f"{title}\\nNumber of pages: {num_pages}\\n\\n")
+
+    for page in pdf_reader.pages:
+        text = page.extractText()
+        output_file.write(text)

creating-and-modifying-pdfs/source_code/02-extracting-pages-from-a-pdf.py

+# -----------------------------
+# Using the PdfFileWriter Class
+# -----------------------------
+
+from PyPDF2 import PdfFileWriter
+
+pdf_writer = PdfFileWriter()
+
+page = pdf_writer.addBlankPage(width=72, height=72)
+
+print(type(page))
+
+from pathlib import Path  # noqa
+
+with Path("blank.pdf").open(mode="wb") as output_file:
+    pdf_writer.write(output_file)
+
+
+# -----------------------------------
+# Extracting a Single Page From a PDF
+# -----------------------------------
+
+from pathlib import Path  # noqa
+from PyPDF2 import PdfFileReader, PdfFileWriter  # noqa
+
+# Change the path to work on your computer if necessary
+pdf_path = (
+    Path.home()
+    / "creating-and-modifying-pdfs"
+    / "practice_files"
+    / "Pride_and_Prejudice.pdf"
+)
+input_pdf = PdfFileReader(str(pdf_path))
+
+first_page = input_pdf.getPage(0)
+
+pdf_writer = PdfFileWriter()
+pdf_writer.addPage(first_page)
+
+with Path("first_page.pdf").open(mode="wb") as output_file:
+    pdf_writer.write(output_file)
+
+
+# ------------------------------------
+# Extracting Multiple Pages From a PDF
+# ------------------------------------
+
+from PyPDF2 import PdfFileReader, PdfFileWriter  # noqa
+from pathlib import Path  # noqa
+
+pdf_path = (
+    Path.home()
+    / "creating-and-modifying-pdfs"
+    / "practice_files"
+    / "Pride_and_Prejudice.pdf"
+)
+input_pdf = PdfFileReader(str(pdf_path))
+
+pdf_writer = PdfFileWriter()
+for n in range(1, 4):
+    page = input_pdf.getPage(n)
+    pdf_writer.addPage(page)
+
+print(pdf_writer.getNumPages())
+
+pdf_writer = PdfFileWriter()
+
+for page in input_pdf.pages[1:4]:
+    pdf_writer.addPage(page)
+
+with Path("chapter1_slice.pdf").open(mode="wb") as output_file:
+    pdf_writer.write(output_file)

creating-and-modifying-pdfs/source_code/03-concatenating-and-merging-pdfs.py

+# -----------------------------
+# Using the PdfFileMerger Class
+# -----------------------------
+
+from PyPDF2 import PdfFileMerger
+
+pdf_merger = PdfFileMerger()
+
+# ---------------------------------
+# Concatenating PDFs With .append()
+# ---------------------------------
+
+from pathlib import Path  # noqa
+
+reports_dir = (
+    Path.home()
+    / "creating-and-modifying-pdfs"
+    / "practice_files"
+    / "expense_reports"
+)
+
+for path in reports_dir.glob("*.pdf"):
+    print(path.name)
+
+expense_reports = list(reports_dir.glob("*.pdf"))
+expense_reports.sort()
+
+for path in expense_reports:
+    print(path.name)
+
+for path in expense_reports:
+    pdf_merger.append(str(path))
+
+with Path("expense_reports.pdf").open(mode="wb") as output_file:
+    pdf_merger.write(output_file)
+
+
+# --------------------------
+# Merging PDFs With .merge()
+# --------------------------
+
+from pathlib import Path  # noqa
+from PyPDF2 import PdfFileMerger  # noqa
+
+report_dir = (
+    Path.home()
+    / "creating-and-modifying-pdfs"
+    / "practice_files"
+    / "quarterly_report"
+)
+
+report_path = report_dir / "report.pdf"
+toc_path = report_dir / "toc.pdf"
+
+pdf_merger = PdfFileMerger()
+pdf_merger.append(str(report_path))
+
+pdf_merger.merge(1, str(toc_path))
+
+with Path("full_report.pdf").open(mode="wb") as output_file:
+    pdf_merger.write(output_file)

creating-and-modifying-pdfs/source_code/04-rotating-and-cropping-PDF-pages.py

+# --------------
+# Rotating Pages
+# --------------
+
+from pathlib import Path
+from PyPDF2 import PdfFileReader, PdfFileWriter
+
+pdf_path = (
+    Path.home() / "creating-and-modifying-pdfs" / "practice_files" / "ugly.pdf"
+)
+
+pdf_reader = PdfFileReader(str(pdf_path))
+pdf_writer = PdfFileWriter()
+
+for n in range(pdf_reader.getNumPages()):
+    page = pdf_reader.getPage(n)
+    if n % 2 == 0:
+        page.rotateClockwise(90)
+    pdf_writer.addPage(page)
+
+with Path("ugly_rotated.pdf").open(mode="wb") as output_file:
+    pdf_writer.write(output_file)
+
+pdf_reader = PdfFileReader(str(pdf_path))
+
+print(pdf_reader.getPage(0))
+
+page = pdf_reader.getPage(0)
+print(page["/Rotate"])
+
+page = pdf_reader.getPage(1)
+print(page["/Rotate"])
+
+page = pdf_reader.getPage(0)
+print(page["/Rotate"])
+
+page.rotateClockwise(90)
+print(page["/Rotate"])
+
+pdf_reader = PdfFileReader(str(pdf_path))
+pdf_writer = PdfFileWriter()
+
+for page in pdf_reader.pages:
+    if page["/Rotate"] == -90:
+        page.rotateClockwise(90)
+    pdf_writer.addPage(page)
+
+with Path("ugly_rotated2.pdf").open(mode="wb") as output_file:
+    pdf_writer.write(output_file)
+
+
+# --------------
+# Cropping Pages
+# --------------
+
+from pathlib import Path  # noqa
+from PyPDF2 import PdfFileReader, PdfFileWriter  # noqa
+
+pdf_path = (
+    Path.home()
+    / "creating-and-modifying-pdfs"
+    / "practice_files"
+    / "half_and_half.pdf"
+)
+
+pdf_reader = PdfFileReader(str(pdf_path))
+first_page = pdf_reader.getPage(0)
+
+print(first_page.mediaBox)
+print(first_page.mediaBox.lowerLeft)
+print(first_page.mediaBox.lowerRight)
+print(first_page.mediaBox.upperLeft)
+print(first_page.mediaBox.upperRight)
+print(first_page.mediaBox.upperRight[0])
+print(first_page.mediaBox.upperRight[1])
+
+first_page.mediaBox.upperLeft = (0, 480)
+print(first_page.mediaBox.upperLeft)
+print(first_page.mediaBox.upperRight)
+
+pdf_writer = PdfFileWriter()
+pdf_writer.addPage(first_page)
+with Path("cropped_page.pdf").open(mode="wb") as output_file:
+    pdf_writer.write(output_file)
+
+pdf_reader = PdfFileReader(str(pdf_path))
+pdf_writer = PdfFileWriter()
+
+first_page = pdf_reader.getPage(0)
+
+import copy  # noqa
+
+left_side = copy.deepcopy(first_page)
+current_coords = left_side.mediaBox.upperRight
+new_coords = (current_coords[0] / 2, current_coords[1])
+left_side.mediaBox.upperRight = new_coords
+
+right_side = copy.deepcopy(first_page)
+right_side.mediaBox.upperLeft = new_coords
+
+pdf_writer.addPage(left_side)
+pdf_writer.addPage(right_side)
+with Path("cropped_pages.pdf").open(mode="wb") as output_file:
+    pdf_writer.write(output_file)

creating-and-modifying-pdfs/source_code/05-encrypting-and-decrypting-pdfs.py

+# ---------------
+# Encrypting PDFs
+# ---------------
+
+from pathlib import Path
+from PyPDF2 import PdfFileReader, PdfFileWriter
+
+pdf_path = (
+    Path.home()
+    / "creating-and-modifying-pdfs"
+    / "practice_files"
+    / "newsletter.pdf"
+)
+
+pdf_reader = PdfFileReader(str(pdf_path))
+
+pdf_writer = PdfFileWriter()
+pdf_writer.appendPagesFromReader(pdf_reader)
+
+pdf_writer.encrypt(user_pwd="SuperSecret")
+
+output_path = Path.home() / "newsletter_protected.pdf"
+with output_path.open(mode="wb") as output_file:
+    pdf_writer.write(output_file)
+
+user_pwd = "SuperSecret"
+owner_pwd = "ReallySuperSecret"
+pdf_writer.encrypt(user_pwd=user_pwd, owner_pwd=owner_pwd)
+
+
+# ---------------
+# Decrypting PDFs
+# ---------------
+
+from pathlib import Path  # noqa
+from PyPDF2 import PdfFileReader, PdfFileWriter  # noqa
+
+pdf_path = Path.home() / "newsletter_protected.pdf"
+
+pdf_reader = PdfFileReader(str(pdf_path))
+
+print(pdf_reader.getPage(0))  # Raises PdfReadError
+
+print(pdf_reader.decrypt(password="SuperSecret"))
+
+print(pdf_reader.getPage(0))

creating-and-modifying-pdfs/source_code/06-creating-a-pdf-file-from-scratch.py

+# ----------------------
+# Using the Canvas Class
+# ----------------------
+
+from reportlab.pdfgen.canvas import Canvas
+
+canvas = Canvas("hello.pdf")
+canvas.drawString(72, 72, "Hello, World")
+canvas.save()
+
+
+# ---------------------
+# Setting the Page Size
+# ---------------------
+
+from reportlab.lib.units import inch, cm  # noqa
+
+print(cm)
+print(inch)
+
+canvas = Canvas("hello.pdf", pagesize=(8.5 * inch, 11 * inch))
+
+from reportlab.lib.pagesizes import LETTER  # noqa
+
+canvas = Canvas("hello.pdf", pagesize=LETTER)
+print(LETTER)
+
+
+# -----------------------
+# Setting Font Properties
+# -----------------------
+
+canvas = Canvas("font-example.pdf", pagesize=LETTER)
+canvas.setFont("Times-Roman", 18)
+canvas.drawString(1 * inch, 10 * inch, "Times New Roman (18 pt)")
+canvas.save()
+
+# The code below creates a PDF with blue text
+from reportlab.lib.colors import blue  # noqa
+from reportlab.lib.pagesizes import LETTER  # noqa
+from reportlab.lib.units import inch  # noqa
+from reportlab.pdfgen.canvas import Canvas  # noqa
+
+canvas = Canvas("font-colors.pdf", pagesize=LETTER)
+
+# Set font to Times New Roman with 12-point size
+canvas.setFont("Times-Roman", 12)
+
+# Draw blue text one inch from the left and ten
+# inches from the bottom
+canvas.setFillColor(blue)
+canvas.drawString(1 * inch, 10 * inch, "Blue text")
+
+# Save the PDF file
+canvas.save()