数据之路 - Python爬虫 - 数据存储

一、文件存储

1.txt文本存储

2.json文件存储

3.csv文件存储

二、MySQL关系型数据库存储

 

import pymysql
# connect()方法声明一个MySQL连接对象
db = pymysql.connect(host='localhost',user='root', password='123456', port=3306)
# cursor()方法获得MySQL的操作游标，利用游标来执行SQL语句
cursor = db.cursor()
# 创建students数据表
sql = 'CREATE TABLE IF NOT EXISTS students (id VARCHAR(255) NOT NULL, name VARCHAR(255) NOT NULL, age INT NOT NULL, PRIMARY KEY (id))'
cursor.execute(sql) 
===================================================================================================
id = '20120001'
user = 'Bob'
age = 20
sql = 'INSERT INTO students(id, name, age) values(%s, %s, %s)'

# 执行db对象的commit()方法才可实现数据插入
try:
    cursor.execute(sql, (id, user, age))
    db.commit()
# 如果执行失败，发生异常，则调用rollback()执行数据回滚
except:
    db.rollback()
db.close()
===================================================================================================
data = {
    'id': '20120001',
    'name': 'Bob',
    'age': 20
}
table = 'students'
keys = ', '.join(data.keys())
values = ', '.join(['%s'] * len(data))
sql = 'INSERT INTO {table}({keys}) VALUES ({values})'.format(table=table, keys=keys, values=values)
try:
   if cursor.execute(sql, tuple(data.values())):
       print('Successful')
       db.commit()
except:
    print('Failed')
    db.rollback()
db.close()

 

 

三、非关系型数据库存储