Merge pull request #1297 from alexa-infra/fix-stores-decryption

Fix stores decrypt

yfinance/data.py

@@ -46,13 +46,33 @@ def wrapped(*args, **kwargs):
     return wrapped
 
 
-def decrypt_cryptojs_aes(data):
+def decrypt_cryptojs_aes_stores(data):
     encrypted_stores = data['context']['dispatcher']['stores']
-    _cs = data["_cs"]
-    _cr = data["_cr"]
 
-    _cr = b"".join(int.to_bytes(i, length=4, byteorder="big", signed=True) for i in json.loads(_cr)["words"])
-    password = hashlib.pbkdf2_hmac("sha1", _cs.encode("utf8"), _cr, 1, dklen=32).hex()
+    if "_cs" in data and "_cr" in data:
+        _cs = data["_cs"]
+        _cr = data["_cr"]
+        _cr = b"".join(int.to_bytes(i, length=4, byteorder="big", signed=True) for i in json.loads(_cr)["words"])
+        password = hashlib.pbkdf2_hmac("sha1", _cs.encode("utf8"), _cr, 1, dklen=32).hex()
+    else:
+        # Currently assume one extra key in dict, which is password. Print error if 
+        # more extra keys detected.
+        new_keys = [k for k in data.keys() if k not in ["context", "plugins"]]
+        l = len(new_keys)
+        if l == 0:
+            return None
+        elif l == 1 and isinstance(data[new_keys[0]], str):
+            password_key = new_keys[0]
+        else:
+            msg = "Yahoo has again changed data format, yfinance now unsure which key(s) is for decryption:"
+            k = new_keys[0]
+            k_str = k if len(k) < 32 else k[:32-3]+"..."
+            msg += f" '{k_str}'->{type(data[k])}"
+            for i in range(1, len(new_keys)):
+                msg += f" , '{k_str}'->{type(data[k])}"
+            raise Exception(msg)
+        password_key = new_keys[0]
+        password = data[password_key]
 
     encrypted_stores = b64decode(encrypted_stores)
     assert encrypted_stores[0:8] == b"Salted__"
@@ -98,7 +118,10 @@ def EVPKDF(password, salt, keySize=32, ivSize=16, iterations=1, hashAlgorithm="m
         key, iv = key_iv[:keySize], key_iv[keySize:final_length]
         return key, iv
 
-    key, iv = EVPKDF(password, salt, keySize=32, ivSize=16, iterations=1, hashAlgorithm="md5")
+    try:
+        key, iv = EVPKDF(password, salt, keySize=32, ivSize=16, iterations=1, hashAlgorithm="md5")
+    except:
+        raise Exception("yfinance failed to decrypt Yahoo data response")
 
     if usePycryptodome:
         cipher = AES.new(key, AES.MODE_CBC, iv=iv)
@@ -176,15 +199,16 @@ def get_json_data_stores(self, sub_page: str = None, proxy=None) -> dict:
 
         data = json.loads(json_str)
 
-        if "_cs" in data and "_cr" in data:
-            data = decrypt_cryptojs_aes(data)
-
-        if "context" in data and "dispatcher" in data["context"]:
-            # Keep old code, just in case
-            data = data['context']['dispatcher']['stores']
+        stores = decrypt_cryptojs_aes_stores(data)
+        if stores is None:
+            # Maybe Yahoo returned old format, not encrypted
+            if "context" in data and "dispatcher" in data["context"]:
+                stores = data['context']['dispatcher']['stores']
+        if stores is None:
+            raise Exception(f"{self.ticker}: Failed to extract data stores from web request")
 
         # return data
-        new_data = json.dumps(data).replace('{}', 'null')
+        new_data = json.dumps(stores).replace('{}', 'null')
         new_data = re.sub(
             r'{[\'|\"]raw[\'|\"]:(.*?),(.*?)}', r'\1', new_data)