CANVAS = (512, 512) BGCOLOR = 255 # white FGCOLOR = 0 # black

— SVG -> raster —

def rasterize_svg_path(path_d: str, canvas=CANVAS) -> Image.Image:

Build a minimal SVG document; rely on CAIRO for correct path handling

svg = f’‘’‘’’ png_bytes = cairosvg.svg2png(bytestring=svg.encode(‘utf-8’)) img = Image.open(io.BytesIO(png_bytes)).convert(‘L’) return img

— Perceptual hash —

def phash_img(img: Image.Image) -> str:

Normalize to grayscale and fixed size

img = ImageOps.grayscale(img).resize((128, 128), Image.LANCZOS) return str(imagehash.phash(img))

— Reference atlas from TTF —

def render_char(candidate: str, ttf_path: str, canvas=CANVAS, size=420) -> Image.Image:

Render centered text on same canvas to approximate glyph shapes

font = ImageFont.truetype(ttf_path, size=size) img = Image.new(‘L’, canvas, color=BGCOLOR) draw = ImageDraw.Draw(img) w, h = draw.textbbox((0,0), candidate, font=font)[2:] dx = (canvas[0]-w)//2 dy = (canvas[1]-h)//2 draw.text((dx, dy), candidate, fill=FGCOLOR, font=font) return img

— Build atlases for variants —

FONT_VARIANTS = { ‘normal’: ‘/path/to/Bookerly-Regular.ttf’, ‘italic’: ‘/path/to/Bookerly-Italic.ttf’, ‘bold’: ‘/path/to/Bookerly-Bold.ttf’, ‘bolditalic’:‘/path/to/Bookerly-BoldItalic.ttf’, } CANDIDATES = [ *[chr(c) for c in range(0x20, 0x7F)], # basic ASCII ‘–’, ‘—’, ‘“’, ‘”’, ‘‘’, ‘’’, ‘•’, # common punctuation ‘ff’,‘fi’,‘fl’,‘ffi’,‘ffl’ # ligatures ]

def build_atlases(): atlases = {} # variant -> list[(char, img)] for variant, ttf in FONT_VARIANTS.items(): out = [] for ch in CANDIDATES: img = render_char(ch, ttf) out.append((ch, img)) atlases[variant] = out return atlases

— SSIM match —

def best_match(img: Image.Image, atlases) -> tuple[str, float, str]:

Returns (char, score, variant)

img_n = ImageOps.grayscale(img).resize((128,128), Image.LANCZOS) img_n = ImageOps.autocontrast(img_n) best = (‘’, -1.0, ‘’) import numpy as np candA = np.array(img_n) for variant, entries in atlases.items(): for ch, ref in entries: ref_n = ImageOps.grayscale(ref).resize((128,128), Image.LANCZOS) ref_n = ImageOps.autocontrast(ref_n) candB = np.array(ref_n) score = ssim(candA, candB) if score > best[1]: best = (ch, score, variant) return best

— Putting it together for one TAR batch —

def process_tar(tar_path: str, cache: dict, atlases) -> list[dict]:

cache: perceptual-hash -> mapping

out_runs = [] with tarfile.open(tar_path, ‘r:*’) as tf: glyphs = json.load(tf.extractfile(‘glyphs.json’))

page_data_0_4.json may differ in name; list members to find it

pd_name = next(m.name for m in tf.getmembers() if m.name.startswith(‘page_data_’)) page_data = json.load(tf.extractfile(pd_name))

1. Rasterize + hash all glyphs for this batch

id2hash = {} for gid, meta in glyphs.items(): img = rasterize_svg_path(meta[‘path’]) h = phash_img(img) id2hash[int(gid)] = (h, img)

2. Ensure all hashes are resolved to characters in cache

for h, img in {v[0]: v[1] for v in id2hash.values()}.items(): if h not in cache: ch, score, variant = best_match(img, atlases) cache[h] = { ‘char’: ch, ‘score’: float(score), ‘variant’: variant }

3. Decode text runs

for run in page_data: if run.get(‘type’) != ‘TextRun’: continue decoded = [] for gid in run[‘glyphs’]: h, _ = id2hash[gid] decoded.append(cache[h][‘char’]) run_out = { ‘text’: ‘’.join(decoded), ‘rect’: run.get(‘rect’), ‘fontStyle’: run.get(‘fontStyle’), ‘fontWeight’: run.get(‘fontWeight’), ‘fontSize’: run.get(‘fontSize’), } out_runs.append(run_out) return out_runs

Usage sketch:

atlases = build_atlases()

cache =

for tar in sorted(glob(‘batches/*.tar’)):

runs = process_tar(tar, cache, atlases)

# accumulate runs for layout reconstruction → EPUB/HTML

</details>

## Heuristiques de reconstruction de la mise en page/EPUB

- Paragraph breaks: If the next run’s top Y exceeds the previous line’s baseline by a threshold (relative to font size), start a new paragraph.
- Alignment: Group by similar left X for left-aligned paragraphs; detect centered lines by symmetric margins; detect right-aligned by right edges.
- Styling: Preserve italic/bold via `fontStyle`/`fontWeight`; vary CSS classes by `fontSize` buckets to approximate headings vs body.
- Links: If runs include link metadata (e.g., `positionId`), emit anchors and internal hrefs.

## Mitigating SVG anti-scraping path tricks

- Use filled paths with `fill-rule: nonzero` and a proper renderer (CairoSVG, resvg). Do not rely on path token normalization.
- Avoid stroke rendering; focus on filled solids to sidestep hairline artifacts caused by micro relative moves.
- Keep a stable viewBox per render so that identical shapes rasterize consistently across batches.

## Notes de performance

- En pratique, les livres convergent vers quelques centaines de glyphes uniques (p.ex., ~361 incluant les ligatures). Cachez les résultats SSIM par hachage perceptuel.
- After initial discovery, future batches predominantly re-use known hashes; decoding becomes I/O-bound.
- Average SSIM ≈0.95 is a strong signal; consider flagging low-scoring matches for manual review.

## Généralisation à d'autres visualiseurs

Tout système qui :
- Retourne des runs de glyphes positionnés avec des IDs numériques limités à la requête
- Fournit des glyphes vectoriels par requête (SVG paths or subset fonts)
- Caps pages per request to prevent bulk export

…peuvent être traités avec la même normalisation :
- Rasteriser les formes par requête → hachage perceptuel → ID de forme
- Atlas des glyphes/ligatures candidats par variante de police
- SSIM (ou métrique perceptuelle similaire) pour assigner des caractères
- Reconstruire la mise en page à partir des rectangles/styles des runs

## Exemple d'acquisition minimal (esquisse)

Use your browser’s DevTools to capture the exact headers, cookies and tokens used by the reader when requesting `/renderer/render`. Then replicate those from a script or curl. Example outline:
```bash
curl 'https://read.amazon.com/renderer/render' \
-H 'Cookie: session-id=...; at-main=...; sess-at-main=...' \
-H 'x-adp-session: <ADP_SESSION_TOKEN>' \
-H 'authorization: Bearer <RENDERING_TOKEN_FROM_startReading>' \
-H 'User-Agent: <copy from browser>' \
-H 'Accept: application/x-tar' \
--compressed --output batch_000.tar

Ajustez la paramétrisation (ASIN du livre, fenêtre de pages, viewport) pour correspondre aux demandes du lecteur. Prévoyez une limite de 5 pages par requête.

Résultats réalisables

• Regrouper plus de 100 alphabets aléatoires en un seul espace de glyphes via perceptual hashing
• Cartographie à 100% des glyphes uniques avec un SSIM moyen ~0.95 lorsque les atlas incluent des ligatures et des variantes
• EPUB/HTML reconstruit visuellement indiscernable de l’original

Références

• Kindle Web DRM: Breaking Randomized SVG Glyph Obfuscation with Raster Hashing + SSIM (Pixelmelt blog)
• CairoSVG – SVG to PNG renderer
• imagehash – Perceptual image hashing (pHash)
• scikit-image – Structural Similarity Index (SSIM)

Tip

Apprenez et pratiquez le hacking AWS :HackTricks Training AWS Red Team Expert (ARTE)
Apprenez et pratiquez le hacking GCP : HackTricks Training GCP Red Team Expert (GRTE) Apprenez et pratiquez le hacking Azure : HackTricks Training Azure Red Team Expert (AzRTE)

Soutenir HackTricks

• Vérifiez les plans d’abonnement !
• Rejoignez le 💬 groupe Discord ou le groupe telegram ou suivez-nous sur Twitter 🐦 @hacktricks_live.
• Partagez des astuces de hacking en soumettant des PR au HackTricks et HackTricks Cloud dépôts github.