PYTHON

read excel spark

    import org.apache.spark.sql._

val spark: SparkSession = ???
val df = spark.read
         .format("com.crealytics.spark.excel")
        .option("sheetName", "Daily") // Required
        .option("useHeader", "true") // Required
        .option("treatEmptyValuesAsNulls", "false") // Optional, default: true
        .option("inferSchema", "false") // Optional, default: false
        .option("addColorColumns", "true") // Optional, default: false
        .option("startColumn", 0) // Optional, default: 0
        .option("endColumn", 99) // Optional, default: Int.MaxValue
        .option("timestampFormat", "MM-dd-yyyy HH:mm:ss") // Optional, default: yyyy-mm-dd hh:mm:ss[.fffffffff]
        .option("maxRowsInMemory", 20) // Optional, default None. If set, uses a streaming reader which can help with big files
        .option("excerptSize", 10) // Optional, default: 10. If set and if schema inferred, number of rows to infer schema from
        .schema(myCustomSchema) // Optional, default: Either inferred schema, or all columns are Strings
        .load("Worktime.xlsx")

read excel spark

def readExcel(file: String): DataFrame = sqlContext.read
    .format("com.crealytics.spark.excel")
    .option("location", file)
    .option("useHeader", "true")
    .option("treatEmptyValuesAsNulls", "true")
    .option("inferSchema", "true")
    .option("addColorColumns", "False")
    .load()

val data = readExcel("path to your excel file")

data.show(false)

spark read excel file

spark = SparkSession.builder 
.master("local") 
.appName("Word Count") 
.config("spark.jars.packages", "com.crealytics:spark-excel_2.11:0.12.2") 
.getOrCreate()

df = spark.read.format("com.crealytics.spark.excel") 
.option("useHeader", "true") 
.option("inferSchema", "true") 
.option("dataAddress", "NameOfYourExcelSheet") 
.load("your_file"))