streaming代码

2025-01-02 17:32:13 +08:00
parent eeda4a7e9b
commit 926b86d894
9 changed files with 28818 additions and 29 deletions
--- a/testnc.py
+++ b/testnc.py
@@ -0,0 +1,14 @@
+from pyspark.sql import SparkSession
+
+spark = SparkSession.builder.appName("StreamingApp").getOrCreate()  # 创建 SparkSession
+
+df = spark.readStream.format("socket").option("host", "niit-node2").option("port", "9999").load()
+
+
+df = df.selectExpr("explode(split(value, '\t'))as word") \
+    .groupBy("word") \
+    .count()
+
+
+
+df.writeStream.outputMode("complete").format("console").start().awaitTermination()