我正在尝试使用AvroProducer.s将csv文件推送到Kafka主题。我正在读取csv文件并在Kafka主题中逐行循环。 csv文件有10列，它们与value_schema_str变量中定义的相同。但是我遇到了错误。使用Python 3.7，avro-python3 1.8.2，confluent_kafka
运行Producer.py时出现此错误
Traceback (most recent call last):
File "/anaconda3/lib/python3.7/site-packages/urllib3/connectionpool.py", line 600, in urlopen
chunked=chunked)
File "/anaconda3/lib/python3.7/site-packages/urllib3/connectionpool.py", line 384, in _make_request
six.raise_from(e, None)
File "<string>", line 2, in raise_from
File "/anaconda3/lib/python3.7/site-packages/urllib3/connectionpool.py", line 380, in _make_request
httplib_response = conn.getresponse()
File "/anaconda3/lib/python3.7/http/client.py", line 1321, in getresponse
response.begin()
File "/anaconda3/lib/python3.7/http/client.py", line 296, in begin
version, status, reason = self._read_status()
File "/anaconda3/lib/python3.7/http/client.py", line 278, in _read_status
raise BadStatusLine(line)
http.client.BadStatusLine: P
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/anaconda3/lib/python3.7/site-packages/requests/adapters.py", line 449, in send
timeout=timeout
File "/anaconda3/lib/python3.7/site-packages/urllib3/connectionpool.py", line 638, in urlopen
_stacktrace=sys.exc_info()[2])
File "/anaconda3/lib/python3.7/site-packages/urllib3/util/retry.py", line 367, in increment
raise six.reraise(type(error), error, _stacktrace)
File "/anaconda3/lib/python3.7/site-packages/urllib3/packages/six.py", line 685, in reraise
raise value.with_traceback(tb)
File "/anaconda3/lib/python3.7/site-packages/urllib3/connectionpool.py", line 600, in urlopen
chunked=chunked)
File "/anaconda3/lib/python3.7/site-packages/urllib3/connectionpool.py", line 384, in _make_request
six.raise_from(e, None)
File "<string>", line 2, in raise_from
File "/anaconda3/lib/python3.7/site-packages/urllib3/connectionpool.py", line 380, in _make_request
httplib_response = conn.getresponse()
File "/anaconda3/lib/python3.7/http/client.py", line 1321, in getresponse
response.begin()
File "/anaconda3/lib/python3.7/http/client.py", line 296, in begin
version, status, reason = self._read_status()
File "/anaconda3/lib/python3.7/http/client.py", line 278, in _read_status
raise BadStatusLine(line)
urllib3.exceptions.ProtocolError: ('Connection aborted.', BadStatusLine('\x15\x03\x03\x00\x02\x02P'))
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "producer.py", line 97, in <module>
avroProducer.produce(topic='UserActivity', value=row)
File "/anaconda3/lib/python3.7/site-packages/confluent_kafka/avro/__init__.py", line 80, in produce
value = self._serializer.encode_record_with_schema(topic, value_schema, value)
File "/anaconda3/lib/python3.7/site-packages/confluent_kafka/avro/serializer/message_serializer.py", line 105, in encode_record_with_schema
schema_id = self.registry_client.register(subject, schema)
File "/anaconda3/lib/python3.7/site-packages/confluent_kafka/avro/cached_schema_registry_client.py", line 215, in register
result, code = self._send_request(url, method='POST', body=body)
File "/anaconda3/lib/python3.7/site-packages/confluent_kafka/avro/cached_schema_registry_client.py", line 164, in _send_request
response = self._session.request(method, url, headers=_headers, json=body)
File "/anaconda3/lib/python3.7/site-packages/requests/sessions.py", line 533, in request
resp = self.send(prep, **send_kwargs)
File "/anaconda3/lib/python3.7/site-packages/requests/sessions.py", line 646, in send
r = adapter.send(request, **kwargs)
File "/anaconda3/lib/python3.7/site-packages/requests/adapters.py", line 498, in send
raise ConnectionError(err, request=request)
requests.exceptions.ConnectionError: ('Connection aborted.', BadStatusLine('\x15\x03\x03\x00\x02\x02P'))
Producer.py
from confluent_kafka import Producer
from avro import schema
import avro
from confluent_kafka.avro import AvroProducer
import csv
AvroProducerConf= {
'bootstrap.servers':'confluent-cp-kafka-external.confluent-----',
'schema.registry.url':'https://confluent-cp-schema-registry-----',
'security.protocol':'SSL',
'ssl.ca.location':'rootca',
'ssl.certificate.location':'server_qa.crt',
'ssl.key.location':'server_qa.key',
#'ssl.key.password':'123456',
'debug':'msg,topic,broker'
#'group.id': 'testing_group',
}
value_schema_str = """
{
"namespace": "my.test",
"name": "value",
"type": "record",
"fields" : [
{"name" : "id", "type" : "long"},
{"name" : "activity_id", "type" : "string"},
{"name" : "user_activity_id", "type" : "long"},
{"name" : "activity_name", "type" : "string"},
{"name" : "num_points", "type" : "long"},
{"name" : "notes", "type" : "string"},
{"name" : "third_party_id", "type" : "string"},
{"name" : "email_address", "type" : "string"},
{"name" : "mobile_phone_number", "type" : "string"},
{"name" : "dateCreated", "type" : "string"}
]
}
"""
value_schema = schema.Parse(value_schema_str)
avroProducer = AvroProducer(AvroProducerConf, default_value_schema=value_schema)
with open('/Users/Downloads/documents_20190417/2_121_USER_ACTIVITY_20190301.csv') as file:
reader = csv.DictReader(file, delimiter=",")
for row in reader:
avroProducer.produce(topic='UserActivity', value=row)
avroProducer.flush()