处理数据案例

import pandas as pd
import pyhdb


def get_connection():
    conn = pyhdb.connect(
        host="10.33.67.12",
        port=30015,
        user="***",
        password="***"
    )
    return conn


def every_strand(list_temp, n):
    for i in range(0, len(list_temp), n):
        yield list_temp[i:i + n]


def write_item(item):
    mark = []
    for _ in item:
        mark.append("%s")
    sql = 'INSERT INTO _SYS_.{}(`col1`, `col2`) VALUES({})'.format(table_name, ','.join(mark))
    print(sql)
    print(item)
    cursor.executemany(sql, item)
    conn.commit()
    print("====插入成功====")


# 读取数据
read_csv_name = 'read_excel.csv'
table_name = 'xxx'
num = 100  # 每次插入的条数

# 处理
conn = get_connection()
cursor = conn.cursor()
df = pd.read_csv(read_csv_name)
df_column = df.columns

list_data = []
for idx, row in df.iterrows():
    val = [row['col1'], row['col2']]
    list_data.append(val)

result = [list_data[i * num:(i + 1) * num] for i in range(int(len(list_data) / num) + 1) if
          list_data[i * num:(i + 1) * num]]
for item in result:
    write_item(item)
cursor.close()
conn.close()