时间:2021-07-01 10:21:17 帮助过:84人阅读
JSON文件tencent.json部分内容:
{"recruitNumber": "1", "name": "SD10-FPS俄语游戏海外PM(深圳)", "detailLink": "http://hr.tencent.com/position_detail.php?id=9587&keywords=&tid=0&lid=0", "publishTime": "2013-11-13", "catalog": "产品/项目类", "workLocation":
"深圳"}
{"recruitNumber": "2", "name": "HY2-互动娱乐游戏网游財产安全运营专员(深圳)", "detailLink": "http://hr.tencent.com/position_detail.php?id=9482&keywords=&tid=0&lid=0", "publishTime": "2013-11-28", "catalog": "产品/项目类", "workLocation": "深圳"}
在phpMyadmin中创建数据库及表结构:
CREATE DATABASE itzhaopin;
CREATE TABLE IF NOT EXISTS `tencent` ( `id` int(11) NOT NULL auto_increment, `name` varchar(512) default NULL, `catalog` varchar(64) default NULL, `workLocation` varchar(64) default NULL, `recruitNumber` varchar(64) default NULL, `detailLink` varchar(1024) default NULL, `publishTime` varchar(64) default NULL, PRIMARY KEY (`ID`) ) ENGINE=MyISAM DEFAULT CHARSET=utf8 AUTO_INCREMENT=1;
#-*- coding: UTF-8 -*- import json data = [] with open(‘itzhaopin/tencent.json‘) as f: for line in f: data.append(json.loads(line)) #print json.dumps(data, ensure_ascii=False) str = "\r\n" for item in data: #print json.dumps(item) str = str + "insert into tencent(name,catalog,workLocation,recruitNumber,detailLink,publishTime) values " str = str + "(‘%s‘,‘%s‘,‘%s‘,‘%s‘,‘%s‘,‘%s‘);\r\n" % (item[‘name‘],item[‘catalog‘],item[‘workLocation‘],item[‘recruitNumber‘],item[‘detailLink‘],item[‘publishTime‘]) import codecs file_object = codecs.open(‘tencent.sql‘, ‘w‘ ,"utf-8") file_object.write(str) file_object.close() print "success"
运行该python脚本。在当前文件夹下将生成一个名为tencent.sql的文件。在phpMyadmin中导入并运行该文件,爬虫抓取的数据将导入MySQL数据库。
Python将JSON格式数据转换为SQL语句以便导入MySQL数据库
标签:脚本 ati detail oca value get sts data target