• redis、mysql、mongodb数据库


    # -*- coding:utf-8 -*-
    #
    item_mongodb.py
    import redis
    import pymongo
    import json
    
    
    def main():
        redis_connect = redis.StrictRedis(host='127.0.0.1', port=6379, db=0)
        mongo_connect = pymongo.MongoClient(host='127.0.0.1', port=27017)
    
        db = mongo_connect['sina']
        collection = db['sina_articles']
    
        while True:
            source, data = redis_connect.blpop(['sina:items'])
            item = json.loads(data)
            collection.insert(item)
    
    
    if __name__ == '__main__':
        main()
    # -*- coding:utf-8 -*-
    # item_mysql.py
    import MySQLdb
    import mysql.connector
    import redis
    import json
    
    
    def main():
        redis_connect = redis.StrictRedis(host='localhost', password='123456', port=6379, db=0)
        mysql_connect = mysql.connector.connect(host='127.0.0.1', port=3306, user='root', passwd='123456', database='sina', use_unicode=True)
    
    
        while redis_connect.exists('sina:items'):
            source, data = redis_connect.blpop('sina:items')
            item = json.loads(data, encoding='utf-8')
            print (item)
            cur = mysql_connect.cursor()
            cur.execute(
                'insert into sina_articles(parent_title, parent_url, sub_title, sub_url, sub_path, file_url, '
                'file_title, file_content, crawled, spider) values(%s, %s, %s, %s, %s, %s, %s, %s, %s, %s)',
                (item['parent_title'], item['parent_url'], item['sub_title'], item['sub_url'], item['sub_path'],
                 item['file_url'], item['file_title'], item['file_content'], item['crawled'], item['spider']))
            mysql_connect.commit()
            cur.close()
        mysql_connect.close()
    
    
    if __name__ == "__main__":
        main()
    # -*- coding:utf-8 -*-
    # redis数据库 到 Excel
    import redis
    import json
    from openpyxl import Workbook
    
    
    def main():
        # redis_connect = redis.StrictRedis(host='localhost', port=6379, db=0)
        redis_connect = redis.StrictRedis(host='localhost', password='123456', port=6379, db=0)
        a = 1
        while redis_connect.exists('hungry:items'):
            source, data = redis_connect.blpop('hungry:items')
            item = json.loads(data, encoding='utf-8')
            print (item)
            a =a + 1
            ws.append([item['id'],
                       item['classification'],
                       item['shopName'],
                       item['address'],
                       item['foodInformation'][0]['rating'],
                       item['foodInformation'][0]['price'],
                       int(item['foodInformation'][0]['sale']),
                       int(item['foodInformation'][0]['Evaluation']),
                       item['foodInformation'][0]['foodName'],
                       ])
        wb.save('nba.xlsx')  # 保存文件
        print ('a:', a)
    
    
    if __name__ == "__main__":
        wb = Workbook()  # class实例化
        ws = wb.active  # 激活工作表
        ws.title = "New Shit"
        title_list = ['id', 'classification', 'shopName', 'address', 'rating', 'price', 'Evaluation', 'foodName', 'sale']
        ws['A1'] = '饿了么'
        ws.append(title_list)  # 添加一行数据
    
        main()
  • 相关阅读:
    wxGlade: a GUI builder for wxWidgets/wxPython
    wxPython or PyQt or PySide哪一个比较好
    wxpython学习笔记
    C++实现发送HTTP请求 CoderZh 博客园
    Lucene如何分布式(WWW与Lucene服务器分离)
    MVC中一个表单实现多个提交按钮(一个action搞定添删改)
    何为.Net Remoting
    Lucene实用的分词匹配
    我心中的核心组件(可插拔的AOP)~第十四回 全文检索架构~终于设计了一个自己满意的Lucene架构
    【学习opencv第五篇】霍夫线变换
  • 原文地址:https://www.cnblogs.com/Mint-diary/p/9752841.html
Copyright © 2020-2023  润新知