读取Python中的SQL文件以通过databricks对JDBC运行

import os
import pandas as pd
from pyspark.sql import SparkSession

spark = SparkSession.builder \
    .appName("JDBC Reading") \
    .getOrCreate()

sql_file_path = "/path/to/sql/file.sql"

with open(sql_file_path, 'r') as file:
    sql_query = file.read()

jdbc_url = "jdbc:mysql://your-database-url"
table_name = "your-table-name"
user = "your-username"
password = "your-password"

df = spark.read \
    .format("jdbc") \
    .option("url", jdbc_url) \
    .option("dbtable", table_name) \
    .option("user", user) \
    .option("password", password) \
    .option("driver", "com.mysql.jdbc.Driver") \
    .option("query", sql_query) \
    .load()

df_pandas = df.toPandas()

import os
import pandas as pd
from pyspark.sql import SparkSession

# 创建SparkSession对象
spark = SparkSession.builder \
    .appName("JDBC Reading") \
    .getOrCreate()

# 定义SQL文件路径和文件名
sql_file_path = "/path/to/sql/file.sql"

# 读取SQL文件内容
with open(sql_file_path, 'r') as file:
    sql_query = file.read()

# 通过JDBC运行SQL查询
jdbc_url = "jdbc:mysql://your-database-url"
table_name = "your-table-name"
user = "your-username"
password = "your-password"

df = spark.read \
    .format("jdbc") \
    .option("url", jdbc_url) \
    .option("dbtable", table_name) \
    .option("user", user) \
    .option("password", password) \
    .option("driver", "com.mysql.jdbc.Driver") \
    .option("query", sql_query) \
    .load()

# 将结果转换为Pandas DataFrame
df_pandas = df.toPandas()

# 打印结果
print(df_pandas.head())