For advanced features, JavaScript libraries, and detailed examples, see pdf/reference.md. For filling PDF forms, read pdf/forms.md and follow its instructions.
from pypdf import PdfReader, PdfWriter
reader = PdfReader("document.pdf")
print(f"Pages: {len(reader.pages)}")
text = ""
for page in reader.pages:
text += page.extract_text()from pypdf import PdfWriter, PdfReader
writer = PdfWriter()
for pdf_file in ["doc1.pdf", "doc2.pdf", "doc3.pdf"]:
reader = PdfReader(pdf_file)
for page in reader.pages:
writer.add_page(page)
with open("merged.pdf", "wb") as output:
writer.write(output)reader = PdfReader("input.pdf")
for i, page in enumerate(reader.pages):
writer = PdfWriter()
writer.add_page(page)
with open(f"page_{i+1}.pdf", "wb") as output:
writer.write(output)reader = PdfReader("document.pdf")
meta = reader.metadata
print(f"Title: {meta.title}")
print(f"Author: {meta.author}")
print(f"Subject: {meta.subject}")
print(f"Creator: {meta.creator}")reader = PdfReader("input.pdf")
writer = PdfWriter()
page = reader.pages[0]
page.rotate(90) # Rotate 90 degrees clockwise
writer.add_page(page)
with open("rotated.pdf", "wb") as output:
writer.write(output)import pdfplumber
with pdfplumber.open("document.pdf") as pdf:
for page in pdf.pages:
text = page.extract_text()
print(text)with pdfplumber.open("document.pdf") as pdf:
for i, page in enumerate(pdf.pages):
tables = page.extract_tables()
for j, table in enumerate(tables):
print(f"Table {j+1} on page {i+1}:")
for row in table:
print(row)import pandas as pd
with pdfplumber.open("document.pdf") as pdf:
all_tables = []
for page in pdf.pages:
tables = page.extract_tables()
for table in tables:
if table:
df = pd.DataFrame(table[1:], columns=table[0])
all_tables.append(df)
if all_tables:
combined_df = pd.concat(all_tables, ignore_index=True)
combined_df.to_excel("extracted_tables.xlsx", index=False)from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
c = canvas.Canvas("hello.pdf", pagesize=letter)
width, height = letter
c.drawString(100, height - 100, "Hello World!")
c.line(100, height - 140, 400, height - 140)
c.save()from reportlab.lib.pagesizes import letter
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak
from reportlab.lib.styles import getSampleStyleSheet
doc = SimpleDocTemplate("report.pdf", pagesize=letter)
styles = getSampleStyleSheet()
story = []
story.append(Paragraph("Report Title", styles['Title']))
story.append(Spacer(1, 12))
story.append(Paragraph("Body content.", styles['Normal']))
story.append(PageBreak())
story.append(Paragraph("Page 2", styles['Heading1']))
doc.build(story)IMPORTANT: Never use Unicode subscript/superscript characters (₀₁₂₃, ⁰¹²³) in ReportLab PDFs. Built-in fonts don't include these glyphs — they render as solid black boxes.
Use ReportLab's XML markup tags in Paragraph objects instead:
chemical = Paragraph("H<sub>2</sub>O", styles['Normal'])
squared = Paragraph("x<super>2</super> + y<super>2</super>", styles['Normal'])For canvas-drawn text (not Paragraph objects), manually adjust font size and position.
pdftotext input.pdf output.txt
pdftotext -layout input.pdf output.txt # preserve layout
pdftotext -f 1 -l 5 input.pdf output.txt # pages 1-5qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf
qpdf input.pdf --pages . 1-5 -- pages1-5.pdf
qpdf input.pdf --pages . 6-10 -- pages6-10.pdf
qpdf input.pdf output.pdf --rotate=+90:1 # rotate page 1
qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdfpdftk file1.pdf file2.pdf cat output merged.pdf
pdftk input.pdf burst
pdftk input.pdf rotate 1east output rotated.pdfimport pytesseract
from pdf2image import convert_from_path
images = convert_from_path('scanned.pdf')
text = ""
for i, image in enumerate(images):
text += f"Page {i+1}:\n"
text += pytesseract.image_to_string(image)
text += "\n\n"from pypdf import PdfReader, PdfWriter
watermark = PdfReader("watermark.pdf").pages[0]
reader = PdfReader("document.pdf")
writer = PdfWriter()
for page in reader.pages:
page.merge_page(watermark)
writer.add_page(page)
with open("watermarked.pdf", "wb") as output:
writer.write(output)pdfimages -j input.pdf output_prefix
# Creates output_prefix-000.jpg, output_prefix-001.jpg, etc.from pypdf import PdfReader, PdfWriter
reader = PdfReader("input.pdf")
writer = PdfWriter()
for page in reader.pages:
writer.add_page(page)
writer.encrypt("userpassword", "ownerpassword")
with open("encrypted.pdf", "wb") as output:
writer.write(output)| Task | Best Tool |
|---|---|
| Merge PDFs | pypdf |
| Split PDFs | pypdf |
| Extract text | pdfplumber |
| Extract tables | pdfplumber |
| Create PDFs | reportlab |
| Command line merge | qpdf |
| OCR scanned PDFs | pytesseract |
| Fill PDF forms | See pdf/forms.md |
Before delivering any created or modified PDF, render pages to PNG and inspect visually. This catches layout bugs that code-level checks miss.
# Install Poppler if needed: brew install poppler
pdftoppm -png input.pdf /tmp/pdf-preview/page
# Or render a specific page range
pdftoppm -png -f 1 -l 3 input.pdf /tmp/pdf-preview/pageThen inspect PNGs with the image tool. Do not deliver until:
- Text is readable, not clipped or overlapping
- Tables are aligned with consistent column widths
- Headers, footers, and page numbers render correctly
- Charts and images are sharp and properly placed
- Margins and spacing are consistent across pages
If pdftoppm is unavailable:
import subprocess
subprocess.run(["sips", "-s", "format", "png", "input.pdf", "--out", "/tmp/preview.png"])- For advanced pypdfium2 usage:
pdf/reference.md - For JavaScript libraries (pdf-lib):
pdf/reference.md - For form filling:
pdf/forms.md