使用spark对dataframe的某一列调用HTTP请求并返回数据给dataframe

最新推荐文章于 2026-05-02 06:34:25 发布

原创最新推荐文章于 2026-05-02 06:34:25 发布 · 6.1k 阅读

8 ·

本内容遵循CC 4.0 BY-SA版权协议

标签

#spark #scala #datafrmae #HTTP请求

Spark 专栏收录该内容

7 篇文章

订阅专栏

本文介绍如何在Spark DataFrame操作中针对某一列执行HTTP请求，并将返回的数据整合到DataFrame中。通过示例代码和Maven配置，详细阐述这一过程。

代码

package cn.spark.sql

import java.net.URLEncoder
import org.apache.http.client.methods.HttpGet
import org.apache.http.impl.client.DefaultHttpClient
import org.apache.spark.sql.SparkSession
import scala.io.Source
import org.apache.spark.sql.functions._

object HttpForDataFrame{
  def main(args: Array[String]): Unit = {
    val spark = SparkSession
      .builder()
      .appName("HttpForDataFrame")
      .master("local")
      .getOrCreate()
    spark.sparkContext.setLogLevel("ERROR")

    import spark.implicits._

    //获取datafrme数据集
    val studentScoresDF = spark.read.json("E:\\SparkStudy\\testData\\student.json").repation(n)
    studentScoresDF.show()


    //http请求代码
    def send_http_request(kw: String): String = {
      //测试用url，返回值为json格式的字符串，url变量需用URLEncoder.encode(string, "UTF-8")进行转码，防止出现index编码错误
      val url = "http://baike.baidu.com/api/openapi/BaikeLemmaCardApi?scope="+URLEncoder.encode("103", "UTF-8")+"&format="+URLEncoder.encode("json", "UTF-8")+"&appid="+URLEncoder.encode("379020", "UTF-8")+"&bk_key="+URLEncoder.encode(kw, "UTF-8")+"&bk_length="+URLEncoder.encode("600", "UTF-8")
      println(url)

      val httpclient = new DefaultHttpClient()
      try {
        val response = httpclient.execute(new HttpGet(url))
        val entity = response.getEntity
        val result = Source.fromInputStream(entity.getContent).getLines().mkString("\n")
        //println(result)
        return result
      } catch {
        //case ex: Exception => ex.printStackTrace()
        case ex: Exception =>  {"Exception"}
      }
    }

    //注册udf
    val udf_url = udf(send_http_request _)
    val r = studentScoresDF.withColumn("res", udf_url($"name"))
    r.printSchema()
    r.show()
  }
}

maven配置

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>cn.spark.study</groupId>
    <artifactId>SparkStudy</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <maven.compiler.source>1.8</maven.compiler.source>
        <maven.compiler.target>1.8</maven.compiler.target>
        <scala.version>2.11.8</scala.version>
        <spark.version>2.2.0</spark.version>
        <hadoop.version>2.7.3</hadoop.version>
        <encoding>UTF-8</encoding>
    </properties>

    <dependencies>
        <!-- scala依赖-->
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <!-- spark依赖-->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <!-- hivecontext要用这个依赖-->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-hive_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <!-- hadoop依赖-->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <!--Scala HTTPclient依赖-->
        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.32</version>
        </dependency>

        <dependency>
            <groupId>org.apache.httpcomponents</groupId>
            <artifactId>httpcore</artifactId>
            <version>4.4.9</version>
        </dependency>

        <dependency>
            <groupId>org.apache.httpcomponents</groupId>
            <artifactId>httpclient</artifactId>
            <version>4.5.5</version>
        </dependency>

    </dependencies>

    <build>
        <pluginManagement>
            <plugins>
                <!-- 编译scala的插件 -->
                <plugin>
                    <groupId>net.alchim31.maven</groupId>
                    <artifactId>scala-maven-plugin</artifactId>
                    <version>3.2.2</version>
                </plugin>
                <!-- 编译java的插件 -->
                <plugin>
                    <groupId>org.apache.maven.plugins</groupId>
                    <artifactId>maven-compiler-plugin</artifactId>
                    <version>3.5.1</version>
                </plugin>
            </plugins>
        </pluginManagement>
        <plugins>
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <executions>
                    <execution>
                        <id>scala-compile-first</id>
                        <phase>process-resources</phase>
                        <goals>
                            <goal>add-source</goal>
                            <goal>compile</goal>
                        </goals>
                    </execution>
                    <execution>
                        <id>scala-test-compile</id>
                        <phase>process-test-resources</phase>
                        <goals>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <executions>
                    <execution>
                        <phase>compile</phase>
                        <goals>
                            <goal>compile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
            <!-- 打包插件 -->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>3.1.0</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <filters>
                                <filter>
                                    <artifact>*:*</artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SF</exclude>
                                        <exclude>META-INF/*.DSA</exclude>
                                        <exclude>META-INF/*.RSA</exclude>
                                    </excludes>
                                </filter>
                            </filters>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

</project>