Update sample code for the PDF article (#389)

* Update sample code for the PDF article

* TR updates, first round

* Language edit

* README LE

* Final QA

---------

Co-authored-by: KateFinegan <[email protected]>
Co-authored-by: gahjelle <[email protected]>

Author: 3 people

creating-and-modifying-pdfs/README.md

@@ -4,9 +4,9 @@ This folder contains resources and materials for Real Python's [Creating and Mod
 
 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
+1. **`practice_files/`:** Contains the sample PDFs used in the tutorial
+2. **`source_code/`:** Contains source code from the tutorial
 
-The source code files are organized by section of the article, and the start of each subsection is indicated with comments.
+The source code files are organized by section of the tutorial, 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

@@ -1,65 +1,66 @@
 # ---------------
-# Open a PDF File
+# Opening a PDF File
 # ---------------
 
-from PyPDF2 import PdfFileReader
-
-# You might need to change this to match the path on your computer
 from pathlib import Path
 
+from pypdf import PdfReader
+
 pdf_path = (
     Path.home()
     / "creating-and-modifying-pdfs"
     / "practice_files"
     / "Pride_and_Prejudice.pdf"
 )
 
-pdf = PdfFileReader(str(pdf_path))
+pdf_reader = PdfReader(pdf_path)
 
-print(pdf.getNumPages())
+print(len(pdf_reader.pages))
 
-print(pdf.documentInfo)
+print(pdf_reader.metadata)
 
-print(pdf.documentInfo.title)
+print(pdf_reader.metadata.title)
 
 
 # ---------------------------
 # Extracting Text From a Page
 # ---------------------------
 
-first_page = pdf.getPage(0)
+first_page = pdf_reader.pages[0]
 
 print(type(first_page))
 
-print(first_page.extractText())
+print(first_page.extract_text())
 
-for page in pdf.pages:
-    print(page.extractText())
+for page in pdf_reader.pages:
+    print(page.extract_text())
 
 
 # -----------------------
 # Putting It All Together
 # -----------------------
 
 from pathlib import Path  # noqa
-from PyPDF2 import PdfFileReader  # noqa
+
+from pypdf import PdfReader  # noqa
 
 # Change the path below to the correct path for your computer.
 pdf_path = (
     Path.home()
     / "creating-and-modifying-pdfs"
-    / "practice-files"
+    / "practice_files"
     / "Pride_and_Prejudice.pdf"
 )
 
-pdf_reader = PdfFileReader(str(pdf_path))
-output_file_path = Path.home() / "Pride_and_Prejudice.txt"
+pdf_reader = PdfReader(pdf_path)
+txt_file = Path.home() / "Pride_and_Prejudice.txt"
+
+content = [
+    f"{pdf_reader.metadata.title}",
+    f"Number of pages: {len(pdf_reader.pages)}",
+]
 
-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:
+    content.append(page.extract_text())
 
-    for page in pdf_reader.pages:
-        text = page.extractText()
-        output_file.write(text)
+txt_file.write_text("\n".join(content))

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

@@ -1,27 +1,26 @@
 # -----------------------------
-# Using the PdfFileWriter Class
+# Using the PdfWriter Class
 # -----------------------------
 
-from PyPDF2 import PdfFileWriter
+from pypdf import PdfWriter
 
-pdf_writer = PdfFileWriter()
+output_pdf = PdfWriter()
 
-page = pdf_writer.addBlankPage(width=72, height=72)
+page = output_pdf.add_blank_page(width=8.27 * 72, height=11.7 * 72)
 
 print(type(page))
 
 from pathlib import Path  # noqa
 
-with Path("blank.pdf").open(mode="wb") as output_file:
-    pdf_writer.write(output_file)
-
+output_pdf.write("blank.pdf")
 
 # -----------------------------------
 # Extracting a Single Page From a PDF
 # -----------------------------------
 
 from pathlib import Path  # noqa
-from PyPDF2 import PdfFileReader, PdfFileWriter  # noqa
+
+from pypdf import PdfReader, PdfWriter  # noqa
 
 # Change the path to work on your computer if necessary
 pdf_path = (
@@ -30,43 +29,37 @@
     / "practice_files"
     / "Pride_and_Prejudice.pdf"
 )
-input_pdf = PdfFileReader(str(pdf_path))
+input_pdf = PdfReader(pdf_path)
 
-first_page = input_pdf.getPage(0)
+first_page = input_pdf.pages[0]
 
-pdf_writer = PdfFileWriter()
-pdf_writer.addPage(first_page)
+output_pdf = PdfWriter()
+output_pdf.add_page(first_page)
 
-with Path("first_page.pdf").open(mode="wb") as output_file:
-    pdf_writer.write(output_file)
+output_pdf.write("first_page.pdf")
 
 
 # ------------------------------------
 # Extracting Multiple Pages From a PDF
 # ------------------------------------
 
-from PyPDF2 import PdfFileReader, PdfFileWriter  # noqa
 from pathlib import Path  # noqa
 
+from pypdf import PdfReader, PdfWriter  # noqa
+
 pdf_path = (
     Path.home()
     / "creating-and-modifying-pdfs"
     / "practice_files"
     / "Pride_and_Prejudice.pdf"
 )
-input_pdf = PdfFileReader(str(pdf_path))
+input_pdf = PdfReader(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()
+output_pdf = PdfWriter()
 
 for page in input_pdf.pages[1:4]:
-    pdf_writer.addPage(page)
+    output_pdf.add_page(page)
+
+print(len(output_pdf.pages))
 
-with Path("chapter1_slice.pdf").open(mode="wb") as output_file:
-    pdf_writer.write(output_file)
+output_pdf.write("chapter1.pdf")

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

@@ -2,9 +2,9 @@
 # Using the PdfFileMerger Class
 # -----------------------------
 
-from PyPDF2 import PdfFileMerger
+from pypdf import PdfMerger
 
-pdf_merger = PdfFileMerger()
+pdf_merger = PdfMerger()
 
 # ---------------------------------
 # Concatenating PDFs With .append()
@@ -22,25 +22,26 @@
 for path in reports_dir.glob("*.pdf"):
     print(path.name)
 
-expense_reports = list(reports_dir.glob("*.pdf"))
-expense_reports.sort()
+expense_reports = sorted(reports_dir.glob("*.pdf"))
 
 for path in expense_reports:
     print(path.name)
 
+pdf_merger = PdfMerger()
+
 for path in expense_reports:
-    pdf_merger.append(str(path))
+    pdf_merger.append(path)
 
-with Path("expense_reports.pdf").open(mode="wb") as output_file:
-    pdf_merger.write(output_file)
+pdf_merger.write("expense_reports.pdf")
 
 
 # --------------------------
 # Merging PDFs With .merge()
 # --------------------------
 
 from pathlib import Path  # noqa
-from PyPDF2 import PdfFileMerger  # noqa
+
+from pypdf import PdfMerger  # noqa
 
 report_dir = (
     Path.home()
@@ -52,10 +53,9 @@
 report_path = report_dir / "report.pdf"
 toc_path = report_dir / "toc.pdf"
 
-pdf_merger = PdfFileMerger()
-pdf_merger.append(str(report_path))
+pdf_merger = PdfMerger()
+pdf_merger.append(report_path)
 
-pdf_merger.merge(1, str(toc_path))
+pdf_merger.merge(1, toc_path)
 
-with Path("full_report.pdf").open(mode="wb") as output_file:
-    pdf_merger.write(output_file)
+pdf_merger.write("full_report.pdf")