1、pickle
可以将我们python中的任意数据类型转化成bytes并写入到文件中. 同样也可以把文件中写好的bytes转换回我们python的数据.
pickle可以直接序列化对象.
1 class Fruit: 2 def __init__(self,name,color): 3 self.name = name 4 self.color = color 5 6 def eat(self): 7 return "haochi" 8 9 p1 = Fruit("apple1","red1") 10 p2 = Fruit("apple2","red4") 11 p3 = Fruit("apple3","red2") 12 p4 = Fruit("apple4","red6") 13 lst = [p1,p2,p3,p4] 14 15 pickle.dump(lst,open("fruit_info","wb")) 16 17 lst = pickle.load(open("fruit_info","rb")) 18 for i in lst: 19 print(i.name)
2、shelve
shelve提供python的持久化操作. 什么叫持久化操作呢? 说白话,就是把数据写到硬盘上. 在操作shelve的时候非常的像操作一个字典. 这个东西到后期. 就像redis差不多.
1 # shelve 数据的持久化操作, 像操作字典一样去操作shelve ----------------------------------------------------------------- 2 d = shelve.open("shelve_file") 3 d["wlh"] = "王力宏" 4 d["ljj"] = {"name":"林俊杰","id":"singer"} 5 d["zj"] = {"name":"张杰","wife":{"name":"谢娜","gender":"女","worke":"大本营"}} 6 d.close() 7 8 9 d = shelve.open("shelve_file") 10 d.pop("zj") # 能删除,但是再查询时会报错. 11 d.close() 12 13 14 d = shelve.open("shelve_file",writeback=True) # 如果是嵌套字典的话, 必须得加上writeback回写参数, 不然没法修改 15 d["ljj"]["id"] = "歌手" 16 print(d["ljj"]["id"]) 17 d.close()
3、configparser
该模块适用于配置文件的格式与windows ini文件类似,可以包含一个或多个节(section), 每个节可以有多个参数(键=值)
1 import configparser 2 config = configparser.ConfigParser() 3 config["DEFAULT"] = { # DEFAULT 是默认配置, 下面的一些子配置都会带上DEFAULT 里面的配置. 4 "默认设置1":"...1", 5 "默认设置2":"....2", 6 "默认设置3":".....3", 7 } 8 config["配置11"] = { 9 "设置11":"11", 10 "设置12":"12", 11 "设置13":"13", 12 } 13 config["配置22"] = { 14 "设置21":"21", 15 "设置22":"22", 16 "设置23":"23", 17 } 18 config["配置33"] = { 19 "设置31":"31", 20 "设置32":"32", 21 "设置33":"33", 22 } 23 24 with open("peizhi.ini","w",encoding="utf8") as f: 25 config.write(f) # 这里的write()方法是configparser自己重新写的,不是调用的文件操作的write() 26 27 # 查 28 config = configparser.ConfigParser() 29 config.read("peizhi.ini",encoding="utf8") 30 print(config.sections()) # ['配置11', '配置22', '配置33'] 31 print(config["配置33"]["设置33"]) # 33 32 33 # 添加一个章节 先读取文件, 再修改, 最后写入文件 34 config = configparser.ConfigParser() 35 config.read("peizhi.ini",encoding="utf8") 36 config.add_section("配置44") 37 config["配置44"] = { 38 "设置41": "41", 39 "设置42": "42", 40 "设置43": "43", 41 } 42 config.write(open("peizhi.ini","w",encoding="utf8")) 43 44 # 修改章节 45 config = configparser.ConfigParser() 46 config.read("peizhi.ini",encoding="utf8") 47 config.set("配置44","设置43","443") 48 config.write(open("peizhi.ini","w",encoding="utf8")) 49 50 # 删除章节或 章节元素 51 config = configparser.ConfigParser() 52 config.read("peizhi.ini",encoding="utf8") 53 config.remove_section("配置44") # 删除"配置44"章节 54 config.remove_option("配置44","设置43") # 删除"配置44"里的"设置43"元素 55 config.write(open("peizhi.ini","w",encoding="utf8")) 56 57 # 对config的所有修改操作都是先创建config对象,然后用config读取内容, 修改完之后再将config写进文件.
4、json
json是所有语言都通用的模块
4.1 json和pickle的比较?
1 dic = {1:"青铜",2:"白银",3:"黄金",4:"铂金",5:"钻石"} 2 3 ret = json.dumps(dic,ensure_ascii=False) # 用 ensure_ascii=False 来处理非中文显示 4 print(ret,type(ret)) # json结果是 str 类型 5 # ret = pickle.dumps(dic) 6 # print(ret,type(ret)) # pickle结果是 bytes 类型
4.2 json写进文件
1 dic = {'王力宏':{"ji":"新加坡","gender":"男","album":"盖世英雄"}, 2 "林俊杰":"爱笑的眼睛", 3 "张靓颖":{"gender":"女","album":"如果这就是爱情"}, 4 "张杰":"云中的angle" 5 } 6 with open("singer_info.json","w",encoding="utf8") as f: 7 json.dump(dic,f,ensure_ascii=False,indent=4) # indent=4 即在json文件中改成好看点的格式 8 # 即下面格式: 9 # { 10 # "王力宏": { 11 # "ji": "新加坡", 12 # "gender": "男", 13 # "album": "盖世英雄" 14 # }, 15 # "林俊杰": "爱笑的眼睛", 16 # "张靓颖": { 17 # "gender": "女", 18 # "album": "如果这就是爱情" 19 # }, 20 # "张杰": "云中的angle" 21 # }
4.3 json也能处理对象, 也能将对象写进文件(通过间接方式将对象转成字典的形式,然后序列化字典写进文件)
1 class Fruit: 2 def __init__(self,name,color): 3 self.name = name 4 self.color = color 5 6 7 8 9 def trans1(obj): 10 return { 11 "name": obj.name, 12 "color": obj.color, 13 } 14 # 用json序列化对象 ??? 15 ap = Fruit("苹果","红色") 16 17 # 方法一: __dict__ 对obj的各种封装信息(也是字典)进行序列化 18 # ret = json.dumps(ap.__dict__, ensure_ascii=False) 19 # print(ret) 20 21 # 方法二: 对函数返回的结果进行序列化 22 ret = json.dumps(ap,default=trans1,ensure_ascii=False) # 把obj对象作为参数传进trans里,将返回的字典结果进行序列化 23 print(ret)
1 class Fruit: 2 def __init__(self,name,color): 3 self.name = name 4 self.color = color 5 6 7 def trans2(dic): 8 print(type(dic)) 9 return Fruit(dic["name"],dic["color"]) # 返回自己构造的Fruit对象 10 11 12 # 用json反序列化 13 s = '{"name": "苹果", "color": "红色"}' 14 ap = json.loads(s,object_hook=trans2) # 先将s进行反序列化, 然后将反序列化结果作为参数传进trans2 ,在函数里自己构造对象 15 print(ap.color)
4.4 如何将大量数据写进文件?
不用 dump. 改用dumps和loads. 对每一行分别进行处理.
用dumps将数据逐个序列化, 并写进文件; 用loads逐行将字符串反序列化, 并输出(不能用load, 逐行读出来的字符串是不符合json语法规范, 没法load, 会直接报错).
1 # 用json写进大量数据 2 dic1 = {"name":"乱世佳人","show_time":1975,"score":8.5,"time":"180min"} 3 dic2 = {"name":"闻香识女人","show_time":1998,"score":8.8,"time":"160min"} 4 dic3 = {"name":"飞越疯人院","show_time":1973,"score":8.7,"time":"140min"} 5 dic4 = {"name":"霸王别姬","show_time":2001,"score":9.3,"time":"150min"} 6 lst = [dic1,dic2,dic3,dic4] 7 # with open("movie.json","w",encoding="utf8") as f: 8 # for i in lst: 9 # s = json.dumps(i,ensure_ascii=False) 10 # f.write(s+"\n") 11 12 with open("movie.json","r",encoding="utf8") as f: 13 for line in f: 14 line = line.strip() 15 if not line: 16 continue 17 cont = json.loads(line) # 只是一个反序列化操作, 把字符串式的line转成字典形式. 18 # cont = json.load(line) # 错误写法, 这里line只是读取了json文件的一行,并没有全部读取, 19 # line里面所存的字符串是不符合json语法的,没法load, 所以读取出错. 20 print(cont)