Merge pull request #2 from 3c7/feature/from_banner

Implement HHHash from banner string

hhhash/__init__.py

@@ -1 +1 @@
-from hhhash.create import buildhash
+from hhhash.create import buildhash, hash_from_banner

hhhash/create.py

@@ -28,3 +28,42 @@ def buildhash(url=None, debug=False, method='GET', timeout=5):
     m.update(hhhash[1:].encode())
     digest = m.hexdigest()
     return f"hhh:1:{digest}"
+
+def hash_from_banner(banner, debug=False):
+    """Create a HHHash from an already fetched banner. Lines without colons will be skipped. 
+
+    Keyword arguments:
+    banner -- HTTP banner string
+    debug -- output the headers returned before hashing
+    
+    Example:
+        >>> hash_from_banner('''HTTP/1.1 200 OK
+        ... Content-Type: text/html; charset=ISO-8859-1
+        ... Content-Security-Policy-Report-Only: object-src 'none';base-uri 'self';script-src 'nonce-iV-j91UJEG2jNx4j6EeTug' 'strict-dynamic' 'report-sample' 'unsafe-eval' 'unsafe-inline' https: http:;report-uri https://csp.withgoogle.com/csp/gws/other-hp
+        ... P3P: CP="This is not a P3P policy! See g.co/p3phelp for more info."
+        ... Date: Wed, 12 Jul 2023 20:23:42 GMT
+        ... Server: gws
+        ... X-XSS-Protection: 0
+        ... X-Frame-Options: SAMEORIGIN
+        ... Transfer-Encoding: chunked
+        ... Expires: Wed, 12 Jul 2023 20:23:42 GMT
+        ... Cache-Control: private
+        ... Set-Cookie: <removed>
+        ... Set-Cookie: <removed>
+        ... Set-Cookie: <removed>
+        ... Alt-Svc: h3=":443"; ma=2592000,h3-29=":443"; ma=2592000''')
+        hhh:1:d9576f3e7a381562f7d18a514ab095fa8699e96891d346d0042f83e942373215
+    """
+    hhhash = ""
+    for line in banner.splitlines():
+        if ":" not in line:
+            continue
+
+        header, _ = line.split(":", maxsplit=1)
+        hhhash = f"{hhhash}:{header.strip()}"
+    if debug:
+        print(hhhash[1:])
+    m = hashlib.sha256()
+    m.update(hhhash[1:].encode())
+    digest = m.hexdigest()
+    return f"hhh:1:{digest}"