Java tutorial
/** * Licensed to the Apache Software Foundation (ASF) under one * or more contributor license agreements. See the NOTICE file * distributed with this work for additional information * regarding copyright ownership. The ASF licenses this file * to you under the Apache License, Version 2.0 (the * "License"); you may not use this file except in compliance * with the License. You may obtain a copy of the License at * * http://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * See the License for the specific language governing permissions and * limitations under the License. */ package com.cloudera.earthquake; import java.io.IOException; import java.io.InputStream; import java.net.HttpURLConnection; import java.net.URL; import org.apache.commons.io.IOUtils; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.FSDataOutputStream; import org.apache.hadoop.fs.FileSystem; import org.apache.hadoop.fs.Path; public class GetData { public static void main(String[] args) throws IOException { URL url = new URL("http://earthquake.usgs.gov/earthquakes/feed/v1.0/summary/all_month.csv"); HttpURLConnection conn = (HttpURLConnection) url.openConnection(); conn.connect(); InputStream connStream = conn.getInputStream(); FileSystem hdfs = FileSystem.get(new Configuration()); FSDataOutputStream outStream = hdfs.create(new Path(args[0], "month.txt")); IOUtils.copy(connStream, outStream); outStream.close(); connStream.close(); conn.disconnect(); } }