python如何將json格式的數據快速的轉化成指定格式的數據呢?或者轉換成sql文件?
下面的例子是將json格式的數據准換成以#_#分割的文本數據,也可用於生成sql文件。
[root@bogon tutorial]# vi json2txt.py
#-*- coding: UTF-8 -*- import json data = [] with open('./tencent_test.json') as f: for line in f: data.append(json.loads(line)) #print json.dumps(data, ensure_ascii=False) import codecs file_object = codecs.open('tencent.txt', 'w' ,"utf-8") str = "\r\n" splitstr = "#_#" 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'\r\n" % (item['parentTitle'],item['parentLink'],item['author'],item['link'],item['title']) #print json.loads(item['author']) + "\r\n" str = "%s#_#%s#_#%s#_#%s#_#%s\r\n" % (item['parentTitle'],item['parentLink'],item['author'],item['link'],item['title'].strip()) file_object.write(str) #import codecs #file_object = codecs.open('tencent.txt', 'w' ,"utf-8") #file_object.write(str) file_object.close() print "success"
注:如果數據量過大不宜全部放在str里一次性寫入文件。可以考慮逐行寫入,或者到達一定程度時批量寫入。
另外:python通過strip(rm)替換字符串,當rm為空時,默認刪除空白符(包括'\n', '\r', '\t', ' ')。
測試:
json格式的數據
[root@bogon tutorial]# vi tencent_test.json {"author": "作者", "parentTitle": "父標題", "title": "標題", "pageUrl": "pageurl", "link": "linkurl", "parentLink": "parenturl"} {"author": "作者", "parentTitle": "父標題", "title": "標題", "pageUrl": "pageurl", "link": "linkurl", "parentLink": "parenturl"} {"author": "作者", "parentTitle": "父標題", "title": "標題", "pageUrl": "pageurl", "link": "linkurl", "parentLink": "parenturl"} {"author": "作者", "parentTitle": "父標題", "title": "標題", "pageUrl": "pageurl", "link": "linkurl", "parentLink": "parenturl"} {"author": "作者", "parentTitle": "父標題", "title": "標題", "pageUrl": "pageurl", "link": "linkurl", "parentLink": "parenturl"} {"author": "作者", "parentTitle": "父標題", "title": "標題", "pageUrl": "pageurl", "link": "linkurl", "parentLink": "parenturl"} {"author": "作者", "parentTitle": "父標題", "title": "標題", "pageUrl": "pageurl", "link": "linkurl", "parentLink": "parenturl"} {"author": "作者", "parentTitle": "父標題", "title": "標題", "pageUrl": "pageurl", "link": "linkurl", "parentLink": "parenturl"} {"author": "作者", "parentTitle": "父標題", "title": "標題", "pageUrl": "pageurl", "link": "linkurl", "parentLink": "parenturl"} {"author": "作者", "parentTitle": "父標題", "title": "標題", "pageUrl": "pageurl", "link": "linkurl", "parentLink": "parenturl"} {"author": "作者", "parentTitle": "父標題", "title": "標題", "pageUrl": "pageurl", "link": "linkurl", "parentLink": "parenturl"}
運行python json2txt.py
[root@bogon tutorial]# python json2txt.py success [root@bogon tutorial]# more tencent.txt 父標題#_#parenturl#_#作者#_#linkurl#_#標題 父標題#_#parenturl#_#作者#_#linkurl#_#標題 父標題#_#parenturl#_#作者#_#linkurl#_#標題 父標題#_#parenturl#_#作者#_#linkurl#_#標題 父標題#_#parenturl#_#作者#_#linkurl#_#標題 父標題#_#parenturl#_#作者#_#linkurl#_#標題 父標題#_#parenturl#_#作者#_#linkurl#_#標題 父標題#_#parenturl#_#作者#_#linkurl#_#標題 父標題#_#parenturl#_#作者#_#linkurl#_#標題 父標題#_#parenturl#_#作者#_#linkurl#_#標題 父標題#_#parenturl#_#作者#_#linkurl#_#標題