Script Python

import org.apache.spark._
import org.apache.spark.streaming._
import org.apache.spark.streaming.twitter._
import org.apache.spark.streaming.StreamingContext._
import twitter4j.auth.Authorization
import twitter4j.Status
import twitter4j.auth.AuthorizationFactory
import twitter4j.conf.ConfigurationBuilder
import org.apache.spark.streaming.api.java.JavaStreamingContext
import org.apache.spark.rdd.RDD
import org.apache.spark.SparkContext
import org.apache.spark.mllib.feature.HashingTF
import org.apache.spark.mllib.linalg.Vector
import org.apache.spark.SparkConf
import org.apache.spark.api.java.JavaSparkContext
import org.apache.spark.api.java.function.Function
import org.apache.spark.streaming.Duration
import org.apache.spark.streaming.api.java.JavaDStream
import org.apache.spark.streaming.api.java.JavaReceiverInputDStream
val consumerKey = "[TU_CONSUMERKEY_AQUÍ]"
val consumerSecret = "[TU_CONSUMERSECRET_AQUÍ]"
val accessToken = "[TU_ACCESSTOKEN_AQUÍ]"
val accessTokenSecret = "[TU_ACCESSTOKENSECRET_AQUÍ]"
val url = "https://stream.twitter.com/1.1/statuses/filter.json"
val documents: RDD[Seq[String]] = spark.sparkContext.textFile("").map(_.split(" ").toSeq)
// Twitter Streaming
val ssc = new JavaStreamingContext(spark.sparkContext,Seconds(2))
val conf = new ConfigurationBuilder()
conf.setOAuthAccessToken(accessToken)
conf.setOAuthAccessTokenSecret(accessTokenSecret)
conf.setOAuthConsumerKey(consumerKey)
conf.setOAuthConsumerSecret(consumerSecret)
conf.setStreamBaseURL(url)
conf.setSiteStreamBaseURL(url)
val filter = Array("Hola", "ApacheSpark")
val auth = AuthorizationFactory.getInstance(conf.build())
val tweets : JavaReceiverInputDStream[twitter4j.Status] = TwitterUtils.createStream(ssc,
auth, filter)
val statuses = tweets.dstream.map(status => status.getText)
statuses.print()
ssc.start()