zoukankan      html  css  js  c++  java
  • 处理json大文件

    import json
    import pymysql
    
    # 读取review数据,并写入数据库
    # 导入数据库成功,总共4736897条记录
    def prem(db):
        cursor = db.cursor()
        cursor.execute("SELECT VERSION()")
        data = cursor.fetchone()
        print("Database version : %s " % data)  # 结果表明已经连接成功
        cursor.execute("DROP TABLE IF EXISTS review")  # 习惯性
        sql = """CREATE TABLE review (
                 review_id  VARCHAR(100),
                 user_id  VARCHAR(100),
                 business_id VARCHAR(200),
                 stars INT,
                 text VARCHAR(10000) NOT NULL,
                 useful INT,
                 funny INT,
                 cool INT)"""
        cursor.execute(sql)  # 根据需要创建一个表格
    
    
    def reviewdata_insert(db):
    
        with open('E:/data/yelp_data/dataset/review.json', encoding='utf-8') as f:
            i = 0
            while True:
                i += 1
                print(u'正在载入第%s行......' % i)
                try:
                    lines = f.readline()  # 使用逐行读取的方法
                    review_text = json.loads(lines)  # 解析每一行数据
                    result = []
                    result.append((review_text['review_id'], review_text['user_id'],            review_text['business_id'],review_text['stars'], review_text['text'], review_text['useful'],
                                review_text['funny'], review_text['cool']))
                    print(result)
    
                    inesrt_re = "insert into review(review_id, user_id, business_id, stars, text, useful,            funny, cool) values (%s, %s, %s, %s,%s, %s,%s, %s)"
                    cursor = db.cursor()
                    cursor.executemany(inesrt_re, result)
                    db.commit()
                except Exception as e:
                    db.rollback()
                    print(str(e))
                    break
    
    
    if __name__ == "__main__":  # 起到一个初始化或者调用函数的作用
        db = pymysql.connect("localhost", "root", "password(你的密码)", "数据库名称", charset='utf8')
        cursor = db.cursor()
        prem(db)
        reviewdata_insert(db)
        cursor.close()
    

      

  • 相关阅读:
    Java Socket通信读取相关信息代码
    Java Socket编程如何建立两者关系
    浅谈JAVA中如何利用socket进行网络编程(二)
    浅谈JAVA中如何利用socket进行网络编程(一)
    【Java TCP/IP Socket】TCP Socket(含代码)
    HTTP协议
    HTTP协议详解
    TCP/IP协议与Http协议的区别
    MultipartResolver实现文件上传功能
    ***CodeIgnite/CI 去掉 index.php的 配置
  • 原文地址:https://www.cnblogs.com/yspass/p/9346446.html
Copyright © 2011-2022 走看看