1from pypdf import PdfReader, PdfWriter
 2
 3# Read a PDF
 4reader = PdfReader("document.pdf")
 5print(f"Pages: {len(reader.pages)}")
 6
 7# Extract text
 8text = ""
 9for page in reader.pages:
10    text += page.extract_text()

 1from pypdf import PdfWriter, PdfReader
 2
 3writer = PdfWriter()
 4for pdf_file in ["doc1.pdf", "doc2.pdf", "doc3.pdf"]:
 5    reader = PdfReader(pdf_file)
 6    for page in reader.pages:
 7        writer.add_page(page)
 8
 9with open("merged.pdf", "wb") as output:
10    writer.write(output)

1reader = PdfReader("input.pdf")
2for i, page in enumerate(reader.pages):
3    writer = PdfWriter()
4    writer.add_page(page)
5    with open(f"page_{i+1}.pdf", "wb") as output:
6        writer.write(output)

1reader = PdfReader("document.pdf")
2meta = reader.metadata
3print(f"Title: {meta.title}")
4print(f"Author: {meta.author}")
5print(f"Subject: {meta.subject}")
6print(f"Creator: {meta.creator}")

1reader = PdfReader("input.pdf")
2writer = PdfWriter()
3
4page = reader.pages[0]
5page.rotate(90)  # Rotate 90 degrees clockwise
6writer.add_page(page)
7
8with open("rotated.pdf", "wb") as output:
9    writer.write(output)

1import pdfplumber
2
3with pdfplumber.open("document.pdf") as pdf:
4    for page in pdf.pages:
5        text = page.extract_text()
6        print(text)

1with pdfplumber.open("document.pdf") as pdf:
2    for i, page in enumerate(pdf.pages):
3        tables = page.extract_tables()
4        for j, table in enumerate(tables):
5            print(f"Table {j+1} on page {i+1}:")
6            for row in table:
7                print(row)

 1import pandas as pd
 2
 3with pdfplumber.open("document.pdf") as pdf:
 4    all_tables = []
 5    for page in pdf.pages:
 6        tables = page.extract_tables()
 7        for table in tables:
 8            if table:  # Check if table is not empty
 9                df = pd.DataFrame(table[1:], columns=table[0])
10                all_tables.append(df)
11
12# Combine all tables
13if all_tables:
14    combined_df = pd.concat(all_tables, ignore_index=True)
15    combined_df.to_excel("extracted_tables.xlsx", index=False)

 1from reportlab.lib.pagesizes import letter
 2from reportlab.pdfgen import canvas
 3
 4c = canvas.Canvas("hello.pdf", pagesize=letter)
 5width, height = letter
 6
 7# Add text
 8c.drawString(100, height - 100, "Hello World!")
 9c.drawString(100, height - 120, "This is a PDF created with reportlab")
10
11# Add a line
12c.line(100, height - 140, 400, height - 140)
13
14# Save
15c.save()

 1from reportlab.lib.pagesizes import letter
 2from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak
 3from reportlab.lib.styles import getSampleStyleSheet
 4
 5doc = SimpleDocTemplate("report.pdf", pagesize=letter)
 6styles = getSampleStyleSheet()
 7story = []
 8
 9# Add content
10title = Paragraph("Report Title", styles['Title'])
11story.append(title)
12story.append(Spacer(1, 12))
13
14body = Paragraph("This is the body of the report. " * 20, styles['Normal'])
15story.append(body)
16story.append(PageBreak())
17
18# Page 2
19story.append(Paragraph("Page 2", styles['Heading1']))
20story.append(Paragraph("Content for page 2", styles['Normal']))
21
22# Build PDF
23doc.build(story)

1# Extract text
2pdftotext input.pdf output.txt
3
4# Extract text preserving layout
5pdftotext -layout input.pdf output.txt
6
7# Extract specific pages
8pdftotext -f 1 -l 5 input.pdf output.txt  # Pages 1-5

 1# Merge PDFs
 2qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf
 3
 4# Split pages
 5qpdf input.pdf --pages . 1-5 -- pages1-5.pdf
 6qpdf input.pdf --pages . 6-10 -- pages6-10.pdf
 7
 8# Rotate pages
 9qpdf input.pdf output.pdf --rotate=+90:1  # Rotate page 1 by 90 degrees
10
11# Remove password
12qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf

1# Merge
2pdftk file1.pdf file2.pdf cat output merged.pdf
3
4# Split
5pdftk input.pdf burst
6
7# Rotate
8pdftk input.pdf rotate 1east output rotated.pdf

 1# Requires: pip install pytesseract pdf2image
 2import pytesseract
 3from pdf2image import convert_from_path
 4
 5# Convert PDF to images
 6images = convert_from_path('scanned.pdf')
 7
 8# OCR each page
 9text = ""
10for i, image in enumerate(images):
11    text += f"Page {i+1}:\n"
12    text += pytesseract.image_to_string(image)
13    text += "\n\n"
14
15print(text)

 1from pypdf import PdfReader, PdfWriter
 2
 3# Create watermark (or load existing)
 4watermark = PdfReader("watermark.pdf").pages[0]
 5
 6# Apply to all pages
 7reader = PdfReader("document.pdf")
 8writer = PdfWriter()
 9
10for page in reader.pages:
11    page.merge_page(watermark)
12    writer.add_page(page)
13
14with open("watermarked.pdf", "wb") as output:
15    writer.write(output)

1# Using pdfimages (poppler-utils)
2pdfimages -j input.pdf output_prefix
3
4# This extracts all images as output_prefix-000.jpg, output_prefix-001.jpg, etc.

 1from pypdf import PdfReader, PdfWriter
 2
 3reader = PdfReader("input.pdf")
 4writer = PdfWriter()
 5
 6for page in reader.pages:
 7    writer.add_page(page)
 8
 9# Add password
10writer.encrypt("userpassword", "ownerpassword")
11
12with open("encrypted.pdf", "wb") as output:
13    writer.write(output)