Pdf

Split PDF

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)

Extract Metadata

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}")

Rotate Pages

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)

pdfplumber - Text and Table Extraction

Extract Text with Layout

import pdfplumber

with pdfplumber.open("document.pdf") as pdf:
    for page in pdf.pages:
        text = page.extract_text()
        print(text)

Extract Tables

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)

Advanced Table Extraction

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:  # Check if table is not empty
                df = pd.DataFrame(table[1:], columns=table[0])
                all_tables.append(df)

# Combine all tables
if all_tables:
    combined_df = pd.concat(all_tables, ignore_index=True)
    combined_df.to_excel("extracted_tables.xlsx", index=False)

reportlab - Create PDFs

Basic PDF Creation

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

c = canvas.Canvas("hello.pdf", pagesize=letter)
width, height = letter

# Add text
c.drawString(100, height - 100, "Hello World!")
c.drawString(100, height - 120, "This is a PDF created with reportlab")

# Add a line
c.line(100, height - 140, 400, height - 140)

# Save
c.save()

Create PDF with Multiple Pages

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 = []

# Add content
title = Paragraph("Report Title", styles['Title'])
story.append(title)
story.append(Spacer(1, 12))

body = Paragraph("This is the body of the report. " * 20, styles['Normal'])
story.append(body)
story.append(PageBreak())

# Page 2
story.append(Paragraph("Page 2", styles['Heading1']))
story.append(Paragraph("Content for page 2", styles['Normal']))

# Build PDF
doc.build(story)

Command-Line Tools

pdftotext (poppler-utils)

# Extract text
pdftotext input.pdf output.txt

# Extract text preserving layout
pdftotext -layout input.pdf output.txt

# Extract specific pages
pdftotext -f 1 -l 5 input.pdf output.txt  # Pages 1-5

qpdf

# Merge PDFs
qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf

# Split pages
qpdf input.pdf --pages . 1-5 -- pages1-5.pdf
qpdf input.pdf --pages . 6-10 -- pages6-10.pdf

# Rotate pages
qpdf input.pdf output.pdf --rotate=+90:1  # Rotate page 1 by 90 degrees

# Remove password
qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf

pdftk (if available)

# Merge
pdftk file1.pdf file2.pdf cat output merged.pdf

# Split
pdftk input.pdf burst

# Rotate
pdftk input.pdf rotate 1east output rotated.pdf

Common Tasks

Extract Text from Scanned PDFs

# Requires: pip install pytesseract pdf2image
import pytesseract
from pdf2image import convert_from_path

# Convert PDF to images
images = convert_from_path('scanned.pdf')

# OCR each page
text = ""
for i, image in enumerate(images):
    text += f"Page {i+1}:\n"
    text += pytesseract.image_to_string(image)
    text += "\n\n"

print(text)

Add Watermark

from pypdf import PdfReader, PdfWriter

# Create watermark (or load existing)
watermark = PdfReader("watermark.pdf").pages[0]

# Apply to all pages
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)

Extract Images

# Using pdfimages (poppler-utils)
pdfimages -j input.pdf output_prefix

# This extracts all images as output_prefix-000.jpg, output_prefix-001.jpg, etc.

Password Protection

from pypdf import PdfReader, PdfWriter

reader = PdfReader("input.pdf")
writer = PdfWriter()

for page in reader.pages:
    writer.add_page(page)

# Add password
writer.encrypt("userpassword", "ownerpassword")

with open("encrypted.pdf", "wb") as output:
    writer.write(output)

Quick Reference

Markdown ↔ PDF Conversion

Dependencies

pip install markdown weasyprint pdfplumber

MD → PDF (Markdown to PDF)

Convert Markdown files to beautifully styled PDF documents with full support for Chinese text, tables, code blocks, and more.

import markdown
from weasyprint import HTML

def md_to_pdf(md_file: str, pdf_file: str, css_style: str = None):
    """
    Convert Markdown file to PDF with styling.
    
    Args:
        md_file: Path to input Markdown file
        pdf_file: Path to output PDF file
        css_style: Optional custom CSS string
    """
    # Read Markdown content
    with open(md_file, 'r', encoding='utf-8') as f:
        md_content = f.read()
    
    # Convert to HTML with extensions
    html_content = markdown.markdown(
        md_content, 
        extensions=['tables', 'fenced_code', 'toc', 'nl2br']
    )
    
    # Default CSS for beautiful output
    default_css = '''
        @import url('https://fonts.googleapis.com/css2?family=Noto+Sans+SC:wght@400;700&display=swap');
        body {
            font-family: "Noto Sans SC", "PingFang SC", "Microsoft YaHei", sans-serif;
            line-height: 1.8;
            max-width: 800px;
            margin: 0 auto;
            padding: 40px;
            color: #333;
        }
        h1 { color: #1a5f7a; border-bottom: 2px solid #1a5f7a; padding-bottom: 10px; }
        h2 { color: #2d7d9a; margin-top: 30px; }
        h3 { color: #3d9dba; }
        table {
            border-collapse: collapse;
            width: 100%;
            margin: 20px 0;
        }
        th, td {
            border: 1px solid #ddd;
            padding: 10px;
            text-align: left;
        }
        th { background-color: #1a5f7a; color: white; }
        tr:nth-child(even) { background-color: #f9f9f9; }
        blockquote {
            border-left: 4px solid #1a5f7a;
            margin: 20px 0;
            padding: 10px 20px;
            background-color: #f5f5f5;
        }
        code {
            background-color: #f4f4f4;
            padding: 2px 6px;
            border-radius: 3px;
            font-family: monospace;
        }
        pre {
            background-color: #2d2d2d;
            color: #f8f8f2;
            padding: 15px;
            border-radius: 5px;
            overflow-x: auto;
        }
        pre code { background: none; color: inherit; }
    '''
    
    css = css_style if css_style else default_css
    
    full_html = f'''
    <!DOCTYPE html>
    <html>
    <head>
        <meta charset="UTF-8">
        <style>{css}</style>
    </head>
    <body>{html_content}</body>
    </html>
    '''
    
    HTML(string=full_html).write_pdf(pdf_file)
    print(f"✅ PDF generated: {pdf_file}")

# Usage
md_to_pdf('document.md', 'document.pdf')

Quick One-Liner

import markdown
from weasyprint import HTML

md = open('doc.md', encoding='utf-8').read()
html = f'<meta charset="UTF-8"><style>body{{font-family:sans-serif}}</style>{markdown.markdown(md, extensions=["tables"])}'
HTML(string=html).write_pdf('doc.pdf')

MD → PDF with Mermaid Diagrams

Convert Markdown files containing Mermaid diagrams (flowcharts, sequence diagrams, architecture diagrams) to PDF with diagrams rendered as images.

Dependencies

pip install markdown weasyprint
npm install -g @mermaid-js/mermaid-cli  # or use npx (auto-installs)

Using the Script

# Basic usage
python scripts/convert_md_with_mermaid_to_pdf.py document.md

# Specify output file
python scripts/convert_md_with_mermaid_to_pdf.py document.md output.pdf

# Keep rendered diagram images
python scripts/convert_md_with_mermaid_to_pdf.py document.md --keep-images

Programmatic Usage

import markdown
from weasyprint import HTML
import subprocess
import tempfile
import base64
import re
import os

def render_mermaid_to_png(mermaid_code: str, output_path: str, width: int = 1200) -> bool:
    """Render Mermaid code to PNG using mermaid-cli"""
    with tempfile.NamedTemporaryFile(mode='w', suffix='.mmd', delete=False) as f:
        f.write(mermaid_code)
        mmd_file = f.name
    
    try:
        cmd = ['npx', '--yes', '@mermaid-js/mermaid-cli', 
               '-i', mmd_file, '-o', output_path, '-b', 'transparent', '-w', str(width)]
        result = subprocess.run(cmd, capture_output=True, timeout=120)
        return result.returncode == 0 and os.path.exists(output_path)
    finally:
        os.remove(mmd_file)

def process_mermaid_blocks(md_content: str, temp_dir: str) -> str:
    """Replace ```mermaid blocks with rendered PNG images (base64 embedded)"""
    pattern = r'```mermaid\n(.*?)```'
    matches = list(re.finditer(pattern, md_content, flags=re.DOTALL))
    
    for i, match in enumerate(reversed(matches)):
        idx = len(matches) - 1 - i
        mermaid_code = match.group(1).strip()
        png_path = os.path.join(temp_dir, f'mermaid_{idx}.png')
        
        if render_mermaid_to_png(mermaid_code, png_path):
            with open(png_path, 'rb') as f:
                b64 = base64.b64encode(f.read()).decode('utf-8')
            img_tag = f'<img src="data:image/png;base64,{b64}" style="max-width:100%">'
            md_content = md_content[:match.start()] + img_tag + md_content[match.end():]
    
    return md_content

def md_with_mermaid_to_pdf(md_file: str, pdf_file: str):
    """Convert Markdown with Mermaid diagrams to PDF"""
    with open(md_file, 'r', encoding='utf-8') as f:
        md_content = f.read()
    
    # Process Mermaid blocks
    temp_dir = tempfile.mkdtemp()
    md_content = process_mermaid_blocks(md_content, temp_dir)
    
    # Convert to HTML and PDF
    html_content = markdown.markdown(md_content, extensions=['tables', 'fenced_code'])
    
    css = '''
        body { font-family: "PingFang SC", sans-serif; line-height: 1.8; }
        h1 { color: #1a5f7a; border-bottom: 2px solid #1a5f7a; }
        table { border-collapse: collapse; width: 100%; }
        th, td { border: 1px solid #ddd; padding: 8px; }
        th { background-color: #1a5f7a; color: white; }
        pre { background: #2d2d2d; color: #f8f8f2; padding: 15px; }
        img { max-width: 100%; display: block; margin: 15px auto; }
    '''
    
    full_html = f'''
    <!DOCTYPE html>
    <html>
    <head><meta charset="UTF-8"><style>{css}</style></head>
    <body>{html_content}</body>
    </html>
    '''
    
    HTML(string=full_html).write_pdf(pdf_file)
    print(f"✅ PDF generated: {pdf_file}")

# Usage
md_with_mermaid_to_pdf('document.md', 'document.pdf')

Supported Mermaid Diagram Types

• sequenceDiagram: Sequence/timing diagrams
• flowchart / graph: Flowcharts and process diagrams
• stateDiagram: State machine diagrams
• classDiagram: Class diagrams
• gantt: Gantt charts

Example Markdown with Mermaid

# API Flow

```mermaid
sequenceDiagram
    participant Client
    participant Server
    participant DB
    
    Client->>Server: Request
    Server->>DB: Query
    DB-->>Server: Result
    Server-->>Client: Response
```

PDF → MD (PDF to Markdown)

Extract content from PDF and convert to Markdown format, preserving structure like headings, lists, and tables.

import pdfplumber
import re

def pdf_to_md(pdf_file: str, md_file: str):
    """
    Convert PDF to Markdown format.
    
    Args:
        pdf_file: Path to input PDF file
        md_file: Path to output Markdown file
    """
    md_content = []
    
    with pdfplumber.open(pdf_file) as pdf:
        for i, page in enumerate(pdf.pages):
            # Extract text
            text = page.extract_text() or ""
            
            # Extract tables
            tables = page.extract_tables()
            
            if text:
                # Basic formatting: detect potential headers (ALL CAPS or short lines)
                lines = text.split('\n')
                for line in lines:
                    line = line.strip()
                    if not line:
                        md_content.append('')
                        continue
                    
                    # Detect headers (heuristic: short lines, possibly uppercase)
                    if len(line) < 60 and line.isupper():
                        md_content.append(f'## {line.title()}')
                    elif len(line) < 40 and not line.endswith('.'):
                        md_content.append(f'### {line}')
                    else:
                        md_content.append(line)
            
            # Convert tables to Markdown format
            for table in tables:
                if table and len(table) > 0:
                    md_content.append('')
                    # Header row
                    headers = table[0]
                    md_content.append('| ' + ' | '.join(str(h) if h else '' for h in headers) + ' |')
                    md_content.append('|' + '|'.join(['---'] * len(headers)) + '|')
                    # Data rows
                    for row in table[1:]:
                        md_content.append('| ' + ' | '.join(str(c) if c else '' for c in row) + ' |')
                    md_content.append('')
            
            # Page separator
            if i < len(pdf.pages) - 1:
                md_content.append('\n---\n')
    
    # Write to file
    with open(md_file, 'w', encoding='utf-8') as f:
        f.write('\n'.join(md_content))
    
    print(f"✅ Markdown generated: {md_file}")

# Usage
pdf_to_md('document.pdf', 'document.md')

Extract Tables Only

import pdfplumber
import pandas as pd

def extract_tables_to_md(pdf_file: str) -> str:
    """Extract all tables from PDF as Markdown."""
    md_tables = []
    
    with pdfplumber.open(pdf_file) as pdf:
        for page in pdf.pages:
            for table in page.extract_tables():
                if table:
                    df = pd.DataFrame(table[1:], columns=table[0])
                    md_tables.append(df.to_markdown(index=False))
    
    return '\n\n'.join(md_tables)

Quick Reference - MD ↔ PDF

Tips

1. Chinese Support: Use fonts like "Noto Sans SC", "PingFang SC", or "Microsoft YaHei"
2. Tables: Enable extensions=['tables'] in markdown.markdown()
3. Code Blocks: Enable extensions=['fenced_code'] for syntax highlighting
4. Large PDFs: Process page by page to manage memory

Next Steps

• For advanced pypdfium2 usage, see reference.md
• For JavaScript libraries (pdf-lib), see reference.md
• If you need to fill out a PDF form, follow the instructions in forms.md
• For troubleshooting guides, see reference.md