如何将流数据从spark下沉到MongoDB？

Question

from __future__ import print_function
import sys
from pyspark.sql.functions import udf
from pyspark.sql import SparkSession
from pyspark import SparkContext
from pyspark.streaming import StreamingContext
from pyspark.streaming.kafka import KafkaUtils
from pyspark.sql.types import StructType
from pyspark.sql.types import *
import json
from pyspark.sql.functions import struct
from pyspark.sql.functions import *
import datetime

json_schema = StructType([
  StructField("twitterid", StringType(), True),
  StructField("created_at", StringType(), True),
  StructField("tweet", StringType(), True),
  StructField("screen_name", StringType(), True)
])

def parse_json(df):
    twitterid   = json.loads(df[0])['id']
    created_at  = json.loads(df[0])['created_at']
    tweet       = json.loads(df[0])['text']
    tweet       = json.loads(df[0])['text']
    screen_name = json.loads(df[0])['user']['screen_name']
    return [twitterid, created_at, tweet, screen_name]

def convert_twitter_date(timestamp_str):
    output_ts = datetime.datetime.strptime(timestamp_str.replace('+0000 ',''), '%a %b %d %H:%M:%S %Y')
    return output_ts

if __name__ == "__main__":

        spark = SparkSession\
                        .builder\
                        .appName("StructuredNetworkWordCount")\
                        .config("spark.mongodb.input.uri","mongodb://192.168.1.16:27017/twitter.test")\
                        .config("spark.mongodb.output.uri","mongodb://192.168.1.16:27017/twitter.test")\
                        .getOrCreate()
        events = spark\
                        .readStream\
                        .format("kafka")\
                        .option("kafka.bootstrap.servers", "localhost:9092")\
                        .option("subscribe", "twitter")\
                        .load()
        events = events.selectExpr("CAST(value as String)")

        udf_parse_json = udf(parse_json , json_schema)
        udf_convert_twitter_date = udf(convert_twitter_date, TimestampType())
        jsonoutput = events.withColumn("parsed_field", udf_parse_json(struct([events[x] for x in events.columns]))) \
                                        .where(col("parsed_field").isNotNull()) \
                                        .withColumn("created_at", col("parsed_field.created_at")) \
                                        .withColumn("screen_name", col("parsed_field.screen_name")) \
                                        .withColumn("tweet", col("parsed_field.tweet")) \
                                        .withColumn("created_at_ts", udf_convert_twitter_date(col("parsed_field.created_at")))

        windowedCounts = jsonoutput.groupBy(window(jsonoutput.created_at_ts, "1 minutes", "15 seconds"),jsonoutput.screen_name)$

        mongooutput = jsonoutput \
                        .writeStream \
                        .format("com.mongodb.spark.sql.DefaultSource")\
                        .option("com.mongodb.spark.sql.DefaultSource","mongodb://localhost:27017/twitter.test")\
                        .start()
        mongooutput.awaitTermination()

我看过mongodb文档，它支持spark到mongo sink

https://docs.mongodb.com/spark-connector/master/scala/streaming/

Answer 1

我看过mongodb文档，它支持spark到mongo sink

文档声称，您可以使用标准RDDAPI来使用遗留流(DStream)API编写每个RDD。

这并不表明MongoDB支持结构化流，它也不支持。由于您使用的是PySpark，其中foreachwriter是不可访问的，因此您必须等待，直到（如果有的话）MongoDB包被更新以支持流操作。