Cdm: Rework init_data param to expect PSSH object

A by product of this change is dropped support for providing a PSSH or init data directly in any form, that includes base64.

You must now provide it as a PSSH object, e.g., `cdm.get_license_challenge(session_id, PSSH("AAAAW3Bzc2...CSEQyAA=="))`

The idea behind this is to simplify the amount of places where parsing of PSSH and Init Data to a minimal amount. The codebase is getting quite annoying with the constant jumps and places where it needs to test for base64 strings, hex strings, bytes, and direct parsed PSSH boxes or WidevinePsshData. That's a ridiculous amount of code just to take in a pssh/init data, especially when the full pssh box will eventually be discarded/unused by the Cdm, as it just cares about the init data.

Client code should pass any PSSH value they get into a PSSH object appropriately, and then store it as such, instead of as a string or bytes. This makes it overall more powerful thanks to the ability to also access the underlying PSSH data more easily with this change.

It also helps to increase contrast between a compliant Widevine Cenc Header or PSSH Box, and arbitrary data (e.g., Netflix WidevineExchange's init data) because of how you initialize the PSSH.

It also allows the user to more accurately trace the underlying final parse of the PSSH value, instead of looking at it being pinged between multiple functions.

RemoteCdm now also sends the PSSH/init_data in full box form now, the serve API will be able to handle both scenarios but in edge cases providing the full box may be the difference between a working License Request and not.

pywidevine/cdm.py

@@ -235,7 +235,7 @@ class Cdm:
     def get_license_challenge(
         self,
         session_id: bytes,
-        init_data: Union[Container, bytes, str],
+        pssh: PSSH,
         type_: Union[int, str] = LicenseType.STREAMING,
         privacy_mode: bool = True
     ) -> bytes:
@@ -244,8 +244,7 @@ class Cdm:
 
         Parameters:
             session_id: Session identifier.
-            init_data: Widevine Cenc Header (Init Data) or a Protection System Specific
-                Header Box to take the init data from.
+            pssh: PSSH Object to get the init data from.
             type_: Type of License you wish to exchange, often `STREAMING`. The `OFFLINE`
                 Licenses are for Offline licensing of Downloaded content.
             privacy_mode: Encrypt the Client ID using the Privacy Certificate. If the
@@ -265,12 +264,10 @@ class Cdm:
         if not session:
             raise InvalidSession(f"Session identifier {session_id!r} is invalid.")
 
-        if not init_data:
-            raise InvalidInitData("The init_data must not be empty.")
-        try:
-            init_data = PSSH(init_data).init_data
-        except (ValueError, binascii.Error, DecodeError) as e:
-            raise InvalidInitData(str(e))
+        if not pssh:
+            raise InvalidInitData("A pssh must be provided.")
+        if not isinstance(pssh, PSSH):
+            raise InvalidInitData(f"Expected pssh to be a {PSSH}, not {pssh!r}")
 
         try:
             if isinstance(type_, int):
@@ -290,7 +287,9 @@ class Cdm:
         license_request.protocol_version = ProtocolVersion.Value("VERSION_2_1")
         license_request.key_control_nonce = random.randrange(1, 2 ** 31)
 
-        license_request.content_id.widevine_pssh_data.pssh_data.append(init_data)
+        # pssh_data may be either a WidevineCencHeader or custom data
+        # we have to assume the pssh.init_data value is valid, we cannot test
+        license_request.content_id.widevine_pssh_data.pssh_data.append(pssh.init_data)
         license_request.content_id.widevine_pssh_data.license_type = type_
         license_request.content_id.widevine_pssh_data.request_id = request_id
 

pywidevine/main.py

@@ -13,6 +13,7 @@ from pywidevine import __version__
 from pywidevine.cdm import Cdm
 from pywidevine.device import Device
 from pywidevine.license_protocol_pb2 import LicenseType, FileHashes
+from pywidevine.pssh import PSSH
 
 
 @click.group(invoke_without_command=True)
@@ -62,6 +63,9 @@ def license_(device: Path, pssh: str, server: str, type_: str, privacy: bool):
     """
     log = logging.getLogger("license")
 
+    # prepare pssh
+    pssh = PSSH(pssh)
+
     # load device
     device = Device.load(device)
     log.info(f"[+] Loaded Device ({device.system_id} L{device.security_level})")

pywidevine/remotecdm.py

@@ -153,7 +153,7 @@ class RemoteCdm(Cdm):
     def get_license_challenge(
         self,
         session_id: bytes,
-        init_data: Union[Container, bytes, str],
+        pssh: PSSH,
         type_: Union[int, str] = LicenseType.STREAMING,
         privacy_mode: bool = True
     ) -> bytes:
@@ -161,12 +161,10 @@ class RemoteCdm(Cdm):
         if not session:
             raise InvalidSession(f"Session identifier {session_id!r} is invalid.")
 
-        if not init_data:
-            raise InvalidInitData("The init_data must not be empty.")
-        try:
-            init_data = PSSH(init_data).init_data
-        except (ValueError, binascii.Error, DecodeError) as e:
-            raise InvalidInitData(str(e))
+        if not pssh:
+            raise InvalidInitData("A pssh must be provided.")
+        if not isinstance(pssh, PSSH):
+            raise InvalidInitData(f"Expected pssh to be a {PSSH}, not {pssh!r}")
 
         try:
             if isinstance(type_, int):
@@ -184,7 +182,7 @@ class RemoteCdm(Cdm):
             url=f"{self.host}/{self.device_name}/challenge/{type_}",
             json={
                 "session_id": session_id.hex(),
-                "init_data": base64.b64encode(init_data).decode()
+                "init_data": pssh.dumps()
             }
         )
         if r.status_code != 200:

pywidevine/serve.py

@@ -3,6 +3,8 @@ import sys
 from pathlib import Path
 from typing import Optional, Union
 
+from pywidevine.pssh import PSSH
+
 try:
     from aiohttp import web
 except ImportError:
@@ -210,10 +212,13 @@ async def challenge(request: web.Request) -> web.Response:
             "message": "No Service Certificate set but Privacy Mode is Enforced."
         }, status=403)
 
+    # get init data
+    init_data = PSSH(body["init_data"])
+
     # get challenge
     license_request = cdm.get_license_challenge(
         session_id=session_id,
-        init_data=body["init_data"],
+        pssh=init_data,
         type_=LicenseType.Value(request.match_info["license_type"]),
         privacy_mode=True
     )