Как подключить PySark к ElasticSearch на AWS?

Question

Я настроил кластер ES-7.1 на AWS. Из экземпляра EC2 я пытаюсь запросить этот ES благодаря PySpark и classi c ES api.

С API Classi c все в порядке:

from elasticsearch import Elasticsearch
es = Elasticsearch([{"host": ES_HOST, "port": ES_PORT}])

Но когда я пытаюсь подключиться к spark, я получаю следующую ошибку:

es_reader = (
    spark.read.format("org.elasticsearch.spark.sql")
    .option("es.nodes", ES_HOST)
    .option("inferSchema", True)
    .option("es.nodes.wan.only", True)
    .option("es.port", ES_PORT)
    .option("es.net.http.auth.user", "")
    .option("es.net.http.auth.pass", "")
    .option("es.resource", ES_INDEX)
)

my_index = es_reader.load("my_index")
my_index.registerTempTable("my_index")

# error :

---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
<ipython-input-12-aaa39c59af9b> in <module>
     36 
     37 # Requeter ES
---> 38 my_index = es_reader.load("my_index")
     39 my_index.registerTempTable("my_index")

~/.pyenv/versions/3.7.1/lib/python3.7/site-packages/pyspark/sql/readwriter.py in load(self, path, format, schema, **options)
    164         self.options(**options)
    165         if isinstance(path, basestring):
--> 166             return self._df(self._jreader.load(path))
    167         elif path is not None:
    168             if type(path) != list:

~/.pyenv/versions/3.7.1/lib/python3.7/site-packages/py4j/java_gateway.py in __call__(self, *args)
   1255         answer = self.gateway_client.send_command(command)
   1256         return_value = get_return_value(
-> 1257             answer, self.gateway_client, self.target_id, self.name)
   1258 
   1259         for temp_arg in temp_args:

~/.pyenv/versions/3.7.1/lib/python3.7/site-packages/pyspark/sql/utils.py in deco(*a, **kw)
     61     def deco(*a, **kw):
     62         try:
---> 63             return f(*a, **kw)
     64         except py4j.protocol.Py4JJavaError as e:
     65             s = e.java_exception.toString()

~/.pyenv/versions/3.7.1/lib/python3.7/site-packages/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
    326                 raise Py4JJavaError(
    327                     "An error occurred while calling {0}{1}{2}.\n".
--> 328                     format(target_id, ".", name), value)
    329             else:
    330                 raise Py4JError(

Py4JJavaError: An error occurred while calling o297.load.
: org.elasticsearch.hadoop.EsHadoopIllegalArgumentException: Cannot detect ES version - typically this happens if the network/Elasticsearch cluster is not accessible or when targeting a WAN/Cloud instance without the proper setting 'es.nodes.wan.only'
    at org.elasticsearch.hadoop.rest.InitializationUtils.discoverClusterInfo(InitializationUtils.java:344)
    at org.elasticsearch.spark.sql.ElasticsearchRelation.cfg$lzycompute(DefaultSource.scala:225)
    at org.elasticsearch.spark.sql.ElasticsearchRelation.cfg(DefaultSource.scala:223)
    at org.elasticsearch.spark.sql.ElasticsearchRelation.lazySchema$lzycompute(DefaultSource.scala:229)
    at org.elasticsearch.spark.sql.ElasticsearchRelation.lazySchema(DefaultSource.scala:229)
    at org.elasticsearch.spark.sql.ElasticsearchRelation$$anonfun$schema$1.apply(DefaultSource.scala:233)
    at org.elasticsearch.spark.sql.ElasticsearchRelation$$anonfun$schema$1.apply(DefaultSource.scala:233)
    at scala.Option.getOrElse(Option.scala:121)
    at org.elasticsearch.spark.sql.ElasticsearchRelation.schema(DefaultSource.scala:233)
    at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:403)
    at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:223)
    at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:211)
    at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:178)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
    at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
    at py4j.Gateway.invoke(Gateway.java:282)
    at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
    at py4j.commands.CallCommand.execute(CallCommand.java:79)
    at py4j.GatewayConnection.run(GatewayConnection.java:238)
    at java.lang.Thread.run(Thread.java:748)
Caused by: org.elasticsearch.hadoop.rest.EsHadoopInvalidRequest: [GET] on [] failed; server[15.188.6.224:443] returned [400|Bad Request:]
    at org.elasticsearch.hadoop.rest.RestClient.checkResponse(RestClient.java:448)
    at org.elasticsearch.hadoop.rest.RestClient.execute(RestClient.java:405)
    at org.elasticsearch.hadoop.rest.RestClient.execute(RestClient.java:367)
    at org.elasticsearch.hadoop.rest.RestClient.execute(RestClient.java:371)
    at org.elasticsearch.hadoop.rest.RestClient.get(RestClient.java:166)
    at org.elasticsearch.hadoop.rest.RestClient.mainInfo(RestClient.java:692)
    at org.elasticsearch.hadoop.rest.InitializationUtils.discoverClusterInfo(InitializationUtils.java:334)
    ... 23 more

Мой ip включен в белый список для этого кластера ES, и я уже пытался поиграть с аргументом .option ("es. node.wan.only ", True) от True до False, как было предложено в этом этом выпуске