Still deciding on output

binhop.py

@@ -1,10 +1,33 @@
+#!/usr/bin/env python3
+
 import asyncio
 import hashlib
-import math
 import time
+import tempfile
+import binwalk
+import os
+
 
 from aiohttp import web
 
+async def scan_file(filename, base_dir):
+    try:
+        scan = binwalk.scan(filename, signature=True, quiet=True, extract=True, matryoshka=True, remove_after_execute=False, directory=base_dir)
+        return scan
+    except binwalk.ModuleException as e:
+        print("Critical failure: ", e)
+
+async def build_listing(path):
+    result = {}
+    for item in os.listdir(path):
+        item_path = os.path.join(path, item)
+        if os.path.isdir(item_path):
+            result[item] = await build_listing(item_path)
+        else:
+            result[item] = {"s": os.path.getsize(item_path)}
+            print(item)
+    return result
+
 async def upload_file(request):
     reader = await request.multipart()
     field = await reader.next()
@@ -16,28 +39,53 @@ async def upload_file(request):
     sha1_hash = hashlib.sha1()
     md5_hash = hashlib.md5()
 
+
+    temp_file = tempfile.NamedTemporaryFile(mode='ab', delete=False)
+
     while True:
         chunk = await field.read_chunk()
         if not chunk:
             break
+        temp_file.write(chunk)
         file_size += len(chunk)
         sha1_hash.update(chunk)
         md5_hash.update(chunk)
+    
+    try:
+        working_dir = tempfile.TemporaryDirectory(ignore_cleanup_errors=True)
+        scan = await scan_file(temp_file.name, working_dir.name)
+        sigs = scan[0]
+        extractor = sigs.extractor.output
+    finally:
+        os.unlink(temp_file.name)
 
-    size_suffixes = ['B', 'KB', 'MB', 'GB', 'TB']
-    size_suffix_index = math.floor(math.log(file_size, 1024))
-    human_readable_size = f'{file_size / (1024 ** size_suffix_index):.2f} {size_suffixes[size_suffix_index]}'
-
-    # await asyncio.sleep(2)
+    carved = []
+    for sig in sigs.results:
+        tmp_path = sig.file.path
+        if tmp_path in extractor:
+            if sig.offset in extractor[tmp_path].carved:
+                end_offset = sig.offset + os.path.getsize(extractor[tmp_path].carved[sig.offset])
+                print("Carved data from offsets 0x%X-0x%X to %s" % (sig.offset, end_offset, extractor[tmp_path].carved[sig.offset]))
+                carved.append({"start": sig.offset, "end": end_offset, "d": sig.description})
+            if sig.offset in extractor[tmp_path].extracted:
+                extracted_files = [x for x in extractor[tmp_path].extracted[sig.offset].files if os.path.isfile(x)]
+                extracted_dirs = [x for x in extractor[tmp_path].extracted[sig.offset].files if os.path.isdir(x)]
+                print("Extracted %d files and %d directories from offset 0x%X to '%s' using '%s'" % (len(extracted_files), len(extracted_dirs), sig.offset, extractor[tmp_path].extracted[sig.offset].files[0], sigs.extractor.output[tmp_path].extracted[sig.offset].command))
+                for i in extractor[tmp_path].extracted[sig.offset].files:
+                    print(f"  File: {i}")
+    # listing = await build_listing(working_dir.name)
+    # print(listing)
+    working_dir.cleanup()
 
     response_data = {
         'meta': {
             'name': filename,
             'sizeb': file_size,
-            'sizeh': human_readable_size,
             'sha1': sha1_hash.hexdigest(),
-            'md5': md5_hash.hexdigest()
-        }
+            'md5': md5_hash.hexdigest(),
+            'sig_quant': len(sigs.magic.signatures)
+        },
+        'offsets': carved
     }
 
     processing_time = time.time() - start_time

static/binhop.js

@@ -1,3 +1,42 @@
+function draw_bytes(data) {
+    const canvas = document.getElementById("blob");
+    const ctx = canvas.getContext("2d");
+
+    // canvas.width = canvas.parentNode.width;
+    // canvas.height = canvas.parentNode.height;
+
+    const blockSize = 2;
+    const blockPadding = 1;
+
+    ctx.fillStyle = "#ddd";
+
+    const numBlocks = Math.ceil(data.meta.sizeb / (blockSize + blockPadding));
+    for (let i = 0; i < numBlocks; i++) {
+        const x = i * (blockSize + blockPadding);
+        ctx.fillRect(x, 0, blockSize, canvas.height);
+    }
+
+    ctx.fillStyle = "blue";
+    data.offsets.forEach((offset) => {
+        const start = Math.floor(offset.start / (blockSize + blockPadding));
+        const end = Math.ceil(offset.end / (blockSize + blockPadding));
+        for (let i = start; i < end; i++) {
+            const x = i * (blockSize + blockPadding);
+            ctx.fillRect(x, 0, blockSize, canvas.height);
+        }
+    });
+}
+
+function bytes_to_human(bytes) {
+	const units = ["B", "KB", "MB", "GB", "TB", "PB", "EB", "ZB", "YB"];
+	let i =0;
+	while (bytes >= 1024 && i < units.length - 1) {
+		bytes /= 1024;
+		i++;
+	}
+	return bytes.toFixed(2) + " " + units[i];
+}
+
 async function process_upload(file) {
     const formData = new FormData();
     formData.append('file', file);
@@ -39,7 +78,7 @@ async function process_upload(file) {
             </tr>
             <tr>
                 <th><strong>size:</strong></th>
-                <td>${data.meta.sizeb} (${data.meta.sizeh})</td>
+                <td>${data.meta["sizeb"]} (${bytes_to_human(data.meta.sizeb)})</td>
             </tr>
             <tr>
                 <th><strong>sha1:</strong></th>
@@ -66,6 +105,7 @@ async function process_upload(file) {
 </small>
 </div>
 </div>`;
+    draw_bytes(data);
     } else {
       console.error('error uploading file');
     }
@@ -79,4 +119,4 @@ async function process_upload(file) {
       process_upload(file);
     });
     fileInput.click();
-  }
+  }