在输入文件中找到特定的单词，并从PySpark中的下一行读取数据

from pyspark.sql import SparkSession

spark = SparkSession.builder \
    .appName("WordSearch") \
    .getOrCreate()

input_file = "path/to/input/file.txt"

df = spark.read.text(input_file)

word = "specific_word"

filtered_df = df.filter(df.value.contains(word))

from pyspark.sql.functions import lead

next_line_df = filtered_df.select(lead(df.value).over(Window.orderBy("value")).alias("next_line"))

output_file = "path/to/output/file.txt"

next_line_df.write.text(output_file)