dunkirk.sh
+42
.gitignore
+42
.gitignore
···
1
+
# Python
2
+
venv/
3
+
__pycache__/
4
+
*.pyc
5
+
*.pyo
6
+
*.pyd
7
+
.Python
8
+
*.egg-info/
9
+
dist/
10
+
build/
11
+
12
+
# Downloaded content
13
+
svg_layers/
14
+
webp_highres/
15
+
webp_layers/
16
+
merged_pages/
17
+
18
+
# Generated PDFs
19
+
*.pdf
20
+
21
+
# Temporary files
22
+
temp_*.html
23
+
test_*.png
24
+
test_*.webp
25
+
merged_page_*.png
26
+
27
+
# OS files
28
+
.DS_Store
29
+
.AppleDouble
30
+
.LSOverride
31
+
Thumbs.db
32
+
Desktop.ini
33
+
34
+
# IDE
35
+
.vscode/
36
+
.idea/
37
+
*.swp
38
+
*.swo
39
+
*~
40
+
41
+
# Crush
42
+
.crush/
+108
README.md
+108
README.md
···
1
+
# Cedarville Cybersecurity Textbook PDF Creator
2
+
3
+
Automated tool to download and convert the Cedarville "Invitation to Cybersecurity" textbook to PDF format.
4
+
5
+
## Features
6
+
7
+
- Downloads all 340 pages (SVG text layers + high-res WebP images)
8
+
- Composites layers with proper font rendering
9
+
- Creates high-quality PDF (1045x1350 pixels per page)
10
+
- Optional: Add searchable text with OCR
11
+
12
+
## Quick Start
13
+
14
+
```bash
15
+
./build.sh
16
+
```
17
+
18
+
That's it! The script will:
19
+
1. Create a Python virtual environment
20
+
2. Install dependencies
21
+
3. Download all page layers (~10-15 min)
22
+
4. Create the PDF (~8-10 min)
23
+
5. Optionally add OCR for selectable text (~30-60 min)
24
+
25
+
## Manual Steps
26
+
27
+
If you prefer to run steps individually:
28
+
29
+
### 1. Setup Environment
30
+
31
+
```bash
32
+
python3 -m venv venv
33
+
source venv/bin/activate
34
+
pip install -r requirements.txt
35
+
python -m playwright install chromium
36
+
```
37
+
38
+
### 2. Download Layers
39
+
40
+
```bash
41
+
python download_layers.py
42
+
```
43
+
44
+
Downloads 340 pages:
45
+
- SVG layers (text, vector graphics) → `svg_layers/`
46
+
- High-res WebP images (1045x1350) → `webp_highres/`
47
+
48
+
### 3. Create PDF
49
+
50
+
```bash
51
+
python create_pdf.py
52
+
```
53
+
54
+
Composites SVG + WebP and creates `Invitation_to_Cybersecurity.pdf`
55
+
56
+
### 4. Add OCR (Optional)
57
+
58
+
```bash
59
+
brew install ocrmypdf
60
+
ocrmypdf Invitation_to_Cybersecurity.pdf Invitation_to_Cybersecurity_OCR.pdf
61
+
```
62
+
63
+
Creates a version with selectable/searchable text.
64
+
65
+
## Requirements
66
+
67
+
- Python 3.9+
68
+
- macOS (tested on Apple Silicon)
69
+
- Homebrew (for OCR step)
70
+
71
+
## Output
72
+
73
+
- **Invitation_to_Cybersecurity.pdf** - 340 pages, ~70-80 MB, high quality
74
+
- **Invitation_to_Cybersecurity_OCR.pdf** - Same as above + searchable text (optional)
75
+
76
+
## File Structure
77
+
78
+
```
79
+
cedrus/
80
+
├── build.sh # Main build script
81
+
├── requirements.txt # Python dependencies
82
+
├── download_layers.py # Download SVG + WebP
83
+
├── create_pdf.py # Composite and create PDF
84
+
├── svg_layers/ # Downloaded SVG files
85
+
├── webp_highres/ # Downloaded WebP files
86
+
├── merged_pages/ # Temporary composited PNGs
87
+
└── Invitation_to_Cybersecurity.pdf
88
+
```
89
+
90
+
## Troubleshooting
91
+
92
+
**"Command not found: python3"**
93
+
- Install Python 3: `brew install python3`
94
+
95
+
**"ocrmypdf not found"**
96
+
- OCR step is optional. Install with: `brew install ocrmypdf`
97
+
98
+
**Fonts look wrong**
99
+
- The script uses Playwright (Chromium) which properly renders embedded fonts
100
+
- If issues persist, check that Playwright browser installed: `python -m playwright install chromium`
101
+
102
+
## Notes
103
+
104
+
- Total time: ~20-30 minutes (without OCR)
105
+
- With OCR: ~50-90 minutes total
106
+
- Disk space needed: ~500 MB temporary files
107
+
- The script downloads from the official Cedarville publication server
108
+
- Be patient - high-quality rendering takes time!
+109
build.sh
+109
build.sh
···
1
+
#!/bin/bash
2
+
set -e
3
+
4
+
echo "================================================"
5
+
echo "Cedarville Cybersecurity Textbook PDF Creator"
6
+
echo "================================================"
7
+
echo ""
8
+
9
+
# Colors for output
10
+
GREEN='\033[0;32m'
11
+
BLUE='\033[0;34m'
12
+
NC='\033[0m' # No Color
13
+
14
+
# Get the directory where this script is located
15
+
SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
16
+
cd "$SCRIPT_DIR"
17
+
18
+
# Step 1: Setup virtual environment
19
+
echo -e "${BLUE}[Step 1/6] Setting up Python virtual environment...${NC}"
20
+
if [ ! -d "venv" ]; then
21
+
python3 -m venv venv
22
+
echo "✓ Virtual environment created"
23
+
else
24
+
echo "✓ Virtual environment already exists"
25
+
fi
26
+
27
+
source venv/bin/activate
28
+
29
+
# Step 2: Install Python dependencies
30
+
echo -e "${BLUE}[Step 2/6] Installing Python dependencies...${NC}"
31
+
pip install -q --upgrade pip
32
+
pip install -q -r requirements.txt
33
+
echo "✓ Python packages installed"
34
+
35
+
# Step 3: Install Playwright browsers
36
+
echo -e "${BLUE}[Step 3/6] Installing Playwright browsers...${NC}"
37
+
if [ ! -d "$HOME/.cache/ms-playwright" ]; then
38
+
python -m playwright install chromium
39
+
echo "✓ Playwright browser installed"
40
+
else
41
+
echo "✓ Playwright browser already installed"
42
+
fi
43
+
44
+
# Step 4: Download page layers (SVG + WebP)
45
+
echo -e "${BLUE}[Step 4/6] Downloading page layers...${NC}"
46
+
if [ ! -d "svg_layers" ] || [ ! -d "webp_highres" ]; then
47
+
echo "This will download 340 pages (SVG + high-res WebP)"
48
+
echo "Estimated time: 10-15 minutes"
49
+
echo ""
50
+
python download_layers.py
51
+
echo -e "${GREEN}✓ All page layers downloaded${NC}"
52
+
else
53
+
echo "✓ Page layers already downloaded"
54
+
fi
55
+
56
+
# Step 5: Create PDF
57
+
echo -e "${BLUE}[Step 5/6] Creating PDF from layers...${NC}"
58
+
if [ ! -f "Invitation_to_Cybersecurity.pdf" ]; then
59
+
echo "This will composite SVG + WebP and create the PDF"
60
+
echo "Estimated time: 8-10 minutes"
61
+
echo ""
62
+
python create_pdf.py
63
+
echo -e "${GREEN}✓ PDF created successfully${NC}"
64
+
else
65
+
echo "✓ PDF already exists"
66
+
read -p "Recreate PDF? (y/N): " recreate
67
+
if [[ $recreate =~ ^[Yy]$ ]]; then
68
+
rm Invitation_to_Cybersecurity.pdf
69
+
python create_pdf.py
70
+
echo -e "${GREEN}✓ PDF recreated${NC}"
71
+
fi
72
+
fi
73
+
74
+
# Step 6: Add OCR text layer (optional)
75
+
echo -e "${BLUE}[Step 6/6] Adding OCR text layer (optional)...${NC}"
76
+
if command -v ocrmypdf &> /dev/null; then
77
+
if [ ! -f "Invitation_to_Cybersecurity_OCR.pdf" ]; then
78
+
read -p "Add searchable text layer with OCR? This will take 30-60 minutes. (y/N): " add_ocr
79
+
if [[ $add_ocr =~ ^[Yy]$ ]]; then
80
+
echo "Running OCR (this will take a while)..."
81
+
ocrmypdf --force-ocr Invitation_to_Cybersecurity.pdf Invitation_to_Cybersecurity_OCR.pdf
82
+
echo -e "${GREEN}✓ OCR PDF created with selectable text${NC}"
83
+
else
84
+
echo "Skipped OCR step"
85
+
fi
86
+
else
87
+
echo "✓ OCR PDF already exists"
88
+
fi
89
+
else
90
+
echo "⚠ ocrmypdf not installed. To add selectable text, run:"
91
+
echo " brew install ocrmypdf"
92
+
echo " ocrmypdf Invitation_to_Cybersecurity.pdf Invitation_to_Cybersecurity_OCR.pdf"
93
+
fi
94
+
95
+
echo ""
96
+
echo -e "${GREEN}================================================${NC}"
97
+
echo -e "${GREEN}✓ Complete!${NC}"
98
+
echo -e "${GREEN}================================================${NC}"
99
+
echo ""
100
+
echo "Output files:"
101
+
if [ -f "Invitation_to_Cybersecurity.pdf" ]; then
102
+
SIZE=$(du -h "Invitation_to_Cybersecurity.pdf" | cut -f1)
103
+
echo " 📄 Invitation_to_Cybersecurity.pdf ($SIZE)"
104
+
fi
105
+
if [ -f "Invitation_to_Cybersecurity_OCR.pdf" ]; then
106
+
SIZE=$(du -h "Invitation_to_Cybersecurity_OCR.pdf" | cut -f1)
107
+
echo " 📄 Invitation_to_Cybersecurity_OCR.pdf ($SIZE) [with selectable text]"
108
+
fi
109
+
echo ""
+23
clean.sh
+23
clean.sh
···
1
+
#!/bin/bash
2
+
# Cleanup temporary files and start fresh
3
+
4
+
echo "Cleaning up temporary files..."
5
+
6
+
# Remove downloaded layers
7
+
rm -rf svg_layers webp_highres
8
+
echo "✓ Removed downloaded layers"
9
+
10
+
# Remove merged pages
11
+
rm -rf merged_pages
12
+
echo "✓ Removed merged pages"
13
+
14
+
# Remove generated PDFs
15
+
rm -f Invitation_to_Cybersecurity.pdf Invitation_to_Cybersecurity_OCR.pdf
16
+
echo "✓ Removed PDFs"
17
+
18
+
# Remove virtual environment
19
+
rm -rf venv
20
+
echo "✓ Removed virtual environment"
21
+
22
+
echo ""
23
+
echo "Cleanup complete! Run ./build.sh to start fresh."
+145
create_pdf.py
+145
create_pdf.py
···
1
+
#!/usr/bin/env python3
2
+
"""
3
+
Create PDF by compositing SVG + WebP layers using Playwright.
4
+
Ensures proper font rendering.
5
+
"""
6
+
7
+
import asyncio
8
+
from pathlib import Path
9
+
from PIL import Image
10
+
from playwright.async_api import async_playwright
11
+
import sys
12
+
13
+
async def merge_page(page, page_num, svg_dir, webp_dir, output_file):
14
+
"""Merge SVG and WebP using browser rendering."""
15
+
svg_file = svg_dir / f"page_{page_num:04d}.svg"
16
+
webp_file = webp_dir / f"page_{page_num:04d}_3.webp"
17
+
18
+
if not webp_file.exists() and not svg_file.exists():
19
+
return False
20
+
21
+
# Get dimensions from WebP
22
+
if webp_file.exists():
23
+
img = Image.open(webp_file)
24
+
width, height = img.size
25
+
else:
26
+
width, height = 1045, 1350
27
+
28
+
# Create HTML
29
+
html_content = f"""
30
+
<!DOCTYPE html>
31
+
<html>
32
+
<head>
33
+
<style>
34
+
body {{ margin: 0; padding: 0; }}
35
+
.container {{
36
+
position: relative;
37
+
width: {width}px;
38
+
height: {height}px;
39
+
}}
40
+
.layer {{
41
+
position: absolute;
42
+
top: 0;
43
+
left: 0;
44
+
width: 100%;
45
+
height: 100%;
46
+
}}
47
+
</style>
48
+
</head>
49
+
<body>
50
+
<div class="container">
51
+
"""
52
+
53
+
if webp_file.exists():
54
+
html_content += f'<img class="layer" src="file://{webp_file.absolute()}" />'
55
+
56
+
if svg_file.exists():
57
+
html_content += f'<img class="layer" src="file://{svg_file.absolute()}" />'
58
+
59
+
html_content += """
60
+
</div>
61
+
</body>
62
+
</html>
63
+
"""
64
+
65
+
temp_html = output_file.parent / "temp_render.html"
66
+
with open(temp_html, 'w') as f:
67
+
f.write(html_content)
68
+
69
+
try:
70
+
await page.goto(f"file://{temp_html.absolute()}")
71
+
await page.wait_for_load_state('networkidle', timeout=10000)
72
+
73
+
container = await page.query_selector('.container')
74
+
screenshot_bytes = await container.screenshot()
75
+
76
+
with open(output_file, 'wb') as f:
77
+
f.write(screenshot_bytes)
78
+
79
+
temp_html.unlink()
80
+
return True
81
+
except Exception as e:
82
+
print(f" Error page {page_num}: {e}")
83
+
if temp_html.exists():
84
+
temp_html.unlink()
85
+
return False
86
+
87
+
async def main():
88
+
script_dir = Path(__file__).parent
89
+
svg_dir = script_dir / "svg_layers"
90
+
webp_dir = script_dir / "webp_highres"
91
+
merged_dir = script_dir / "merged_pages"
92
+
merged_dir.mkdir(exist_ok=True)
93
+
94
+
print("Creating PDF with Playwright (proper font rendering)...")
95
+
print("Estimated time: 8-10 minutes")
96
+
print()
97
+
98
+
async with async_playwright() as p:
99
+
browser = await p.chromium.launch(headless=True)
100
+
page = await browser.new_page()
101
+
102
+
# Merge all pages
103
+
for page_num in range(1, 341):
104
+
if page_num % 10 == 0:
105
+
print(f" Rendering: {page_num}/340 pages...")
106
+
sys.stdout.flush()
107
+
108
+
output_file = merged_dir / f"page_{page_num:04d}.png"
109
+
await merge_page(page, page_num, svg_dir, webp_dir, output_file)
110
+
111
+
await browser.close()
112
+
113
+
print()
114
+
print("All pages rendered! Creating PDF...")
115
+
116
+
# Convert to PDF
117
+
image_files = sorted(merged_dir.glob("page_*.png"))
118
+
119
+
images = []
120
+
for i, img_file in enumerate(image_files, 1):
121
+
if i % 50 == 0:
122
+
print(f" Adding to PDF: {i}/{len(image_files)}...")
123
+
sys.stdout.flush()
124
+
img = Image.open(img_file).convert('RGB')
125
+
images.append(img)
126
+
127
+
if images:
128
+
output_pdf = script_dir / "Invitation_to_Cybersecurity.pdf"
129
+
images[0].save(
130
+
output_pdf,
131
+
"PDF",
132
+
resolution=100.0,
133
+
save_all=True,
134
+
append_images=images[1:]
135
+
)
136
+
137
+
file_size = output_pdf.stat().st_size / 1024 / 1024
138
+
print()
139
+
print(f"✓ PDF created successfully!")
140
+
print(f" Location: {output_pdf}")
141
+
print(f" Pages: {len(images)}")
142
+
print(f" Size: {file_size:.1f} MB")
143
+
144
+
if __name__ == "__main__":
145
+
asyncio.run(main())
+81
download_layers.py
+81
download_layers.py
···
1
+
#!/usr/bin/env python3
2
+
"""
3
+
Download all page layers (SVG + high-res WebP) from Cedarville textbook.
4
+
"""
5
+
6
+
import requests
7
+
from pathlib import Path
8
+
import time
9
+
import sys
10
+
11
+
GUID = "abc80436024deb05cedb27129b7ae6b0"
12
+
BASE_URL = "https://publications.cedarville.edu/cedrus_press/invitation_to_cybersecurity/files/assets"
13
+
14
+
def download_svg(page_num, output_dir):
15
+
"""Download SVG text layer."""
16
+
url = f"{BASE_URL}/common/page-vectorlayers/{page_num:04d}.svg?uni={GUID}"
17
+
output_file = output_dir / f"page_{page_num:04d}.svg"
18
+
19
+
try:
20
+
response = requests.get(url, timeout=30)
21
+
if response.status_code == 200:
22
+
with open(output_file, 'wb') as f:
23
+
f.write(response.content)
24
+
return True
25
+
except:
26
+
pass
27
+
return False
28
+
29
+
def download_webp(page_num, output_dir):
30
+
"""Download high-res WebP background."""
31
+
url = f"{BASE_URL}/common/page-html5-substrates/page{page_num:04d}_3.webp?uni={GUID}"
32
+
output_file = output_dir / f"page_{page_num:04d}_3.webp"
33
+
34
+
try:
35
+
response = requests.get(url, timeout=30)
36
+
if response.status_code == 200:
37
+
with open(output_file, 'wb') as f:
38
+
f.write(response.content)
39
+
return True
40
+
except:
41
+
pass
42
+
return False
43
+
44
+
def main():
45
+
script_dir = Path(__file__).parent
46
+
svg_dir = script_dir / "svg_layers"
47
+
webp_dir = script_dir / "webp_highres"
48
+
49
+
svg_dir.mkdir(exist_ok=True)
50
+
webp_dir.mkdir(exist_ok=True)
51
+
52
+
print("Downloading 340 pages (SVG + high-res WebP)...")
53
+
print(f" SVG layers → {svg_dir}")
54
+
print(f" WebP layers → {webp_dir}")
55
+
print()
56
+
57
+
svg_count = 0
58
+
webp_count = 0
59
+
60
+
for page_num in range(1, 341):
61
+
# Download both layers
62
+
if download_svg(page_num, svg_dir):
63
+
svg_count += 1
64
+
if download_webp(page_num, webp_dir):
65
+
webp_count += 1
66
+
67
+
# Progress update
68
+
if page_num % 20 == 0:
69
+
print(f" Progress: {page_num}/340 (SVG: {svg_count}, WebP: {webp_count})")
70
+
sys.stdout.flush()
71
+
72
+
# Be polite to server
73
+
time.sleep(0.3)
74
+
75
+
print()
76
+
print(f"Download complete!")
77
+
print(f" SVG layers: {svg_count}/340")
78
+
print(f" WebP layers: {webp_count}/340")
79
+
80
+
if __name__ == "__main__":
81
+
main()