本节内容
- 列表
- 元组操作
- 字符串操作
- 字典操作
- 集合操作
- 文件操作
- 字符编码与转码
1、列表
列表是我们最以后最常用的数据类型之一,通过列表可以对数据实现最方便的存储、修改等操作;列表有序、可变、元素可重。
# _*_ coding:utf-8 _*_ __author__ = "ZingP" name = ["alex", "zing-p", "jack", "Tom"] # 定义一个列表,列表有序、可变、元素可重。 print(name[0]) # result:alex 获取列表中的元素(第一个) print(name[-1]) # result:Tom 获取列表中的元素(最后一个) print(name[1:4]) # result:['zing-p', 'jack', 'Tom'] 切片:获取下标1到4的元素,包括1,不包括4 print(name[1:-1]) # result:['zing-p', 'jack'] 切片:获取下标1到-1的元素,包括1,不包括-1 print(name[:2]) # result:['alex', 'zing-p'] 切片:从头开始取,取到下标为2的元素,但不包括2 print(name[1:]) # result:['zing-p', 'jack', 'Tom'] 切片:从下标为1的元素开始取,取到最后一个元素 print(name[::2]) # result:['alex', 'jack'] 从头取到尾,每隔一个元素取一个
1.1追加
>>> names ['Alex', 'Tenglan', 'Eric', 'Rain', 'Tom', 'Amy'] >>> names.append("我是新来的") >>> names ['Alex', 'Tenglan', 'Eric', 'Rain', 'Tom', 'Amy', '我是新来的']
1.2插入
>>> names ['Alex', 'Tenglan', 'Eric', 'Rain', 'Tom', 'Amy', '我是新来的'] >>> names.insert(2,"从Eric前面插入") >>> names ['Alex', 'Tenglan', '从Eric前面插入', 'Eric', 'Rain', 'Tom', 'Amy', '我是新来的'] >>> names.insert(5,"从eric后面插入") >>> names ['Alex', 'Tenglan', '从Eric前面插入', 'Eric', 'Rain', '从eric后面插入', 'Tom', 'Amy', '我是新来的']
1.3修改
>>> names ['Alex', 'Tenglan', '从Eric前面插入', 'Eric', 'Rain', '从eric后面插入', 'Tom', 'Amy', '我是新来的'] >>> names[2] = "该换人了" >>> names ['Alex', 'Tenglan', '该换人了', 'Eric', 'Rain', '从eric后面插入', 'Tom', 'Amy', '我是新来的']
1.4删除
>>> del names[2] >>> names ['Alex', 'Tenglan', 'Eric', 'Rain', '从eric后面插入', 'Tom', 'Amy', '我是新来的'] >>> del names[4] >>> names ['Alex', 'Tenglan', 'Eric', 'Rain', 'Tom', 'Amy', '我是新来的'] >>> >>> names.remove("Eric") #删除指定元素 >>> names ['Alex', 'Tenglan', 'Rain', 'Tom', 'Amy', '我是新来的'] >>> names.pop() #删除列表最后一个值 '我是新来的' >>> names ['Alex', 'Tenglan', 'Rain', 'Tom', 'Amy']
1.5扩展
>>> names ['Alex', 'Tenglan', 'Rain', 'Tom', 'Amy'] >>> b = [1,2,3] >>> names.extend(b) >>> names ['Alex', 'Tenglan', 'Rain', 'Tom', 'Amy', 1, 2, 3]
1.6拷贝
>>> names ['Alex', 'Tenglan', 'Rain', 'Tom', 'Amy', 1, 2, 3] >>> name_copy = names.copy() >>> name_copy ['Alex', 'Tenglan', 'Rain', 'Tom', 'Amy', 1, 2, 3]
这里的copy只是浅copy,就是只copy一层的意思,如果列表中还有列表2,若列表2被修改,则copy后的也会跟着被修改。
1.7统计
>>> names ['Alex', 'Tenglan', 'Amy', 'Tom', 'Amy', 1, 2, 3] >>> names.count("Amy") 2
1.8排序&翻转
>>> names ['Alex', 'Tenglan', 'Amy', 'Tom', 'Amy', 1, 2, 3] >>> names.sort() #排序 Traceback (most recent call last): File "<stdin>", line 1, in <module> TypeError: unorderable types: int() < str() #3.x 里不同数据类型不能放在一起排序了 >>> names[-3] = ' >>> names[-2] = ' >>> names[-1] = ' >>> names ['] >>> names.sort() >>> names [', 'Alex', 'Amy', 'Amy', 'Tenglan', 'Tom'] >>> names.reverse() #反转 >>> names [']
1.9获取下标
>>> names ['] >>> names.index("Amy") 2 #只返回找到的第一个下标
2.元组
元组其实跟列表差不多,也是存一组数,只不是它一旦创建,便不能再修改,所以又叫只读列表;元组有序、不可变、元素可重。
定义:
names = ('h','h',2)
操作:元组同列表一样可以切片,支持索引,它只有2个方法,一个是count,一个是index,完毕。
3.字符串操作
一些蛋疼的语法:
# _*_ coding:utf-8 _*_ __author__ = "ZingP" name_arg = {"name": "zing-p", "age": 25} tell = "{name} is {age} years old..." t = tell.format_map(name_arg) print(t) # result:zing-p is 25 years old... n = "Hello World" print(n.ljust(30, "=")) # result:Hello World=================== print(n.rjust(30, "*")) # result:*******************Hello World s = "Hello World!" p = str.maketrans("abcdefg","3!@#$%^") w = s.translate(p) print(w) # result:H$llo Worl#! b = "ddefdsdff_哈哈" y = b.isidentifier() # result:检测一段字符串可否被当作标志符,即是否符合变量命名规则 print(y) # result:True
4.字典
字典一种key - value 的数据类型,字典无序、可变;key值唯一,天生去重。
4.0创建字典的方法:
(1)直接创建
dict = {'}
(2)工厂创建
items = [(')] dict2 = dict(items) print(dict2) # {'port': '80', 'name': 'earth'} dict1 = dict((['])) print(dict1) # {'port': '80', 'name': 'earth'}
(3)fromkeys()方法
dict1 = {}.fromkeys(('x', 'y'), -1) print(dict1) # {'x': -1, 'y': -1} dict2 = {}.fromkeys(('x', 'y')) print(dict2) # {'x': None, 'y': None}
语法:
info = { 'stu1101': "TengLan Wu", 'stu1102': "LongZe Luola", 'stu1103': "XiaoZe Maliya", }
4.1增加
>>> info["stu1104"] = "苍井空" >>> info {'stu1102': 'LongZe Luola', 'stu1104': '苍井空', 'stu1103': 'XiaoZe Maliya', 'stu1101': 'TengLan Wu'}
4.2修改
>>> info['stu1101'] = "武藤兰" >>> info {'stu1102': 'LongZe Luola', 'stu1103': 'XiaoZe Maliya', 'stu1101': '武藤兰'}
4.3删除
>>> info {'stu1102': 'LongZe Luola', 'stu1103': 'XiaoZe Maliya', 'stu1101': '武藤兰'} >>> info.pop("stu1101") #标准删除姿势 '武藤兰' >>> info {'stu1102': 'LongZe Luola', 'stu1103': 'XiaoZe Maliya'} >>> del info['stu1103'] #换个姿势删除 >>> info {'stu1102': 'LongZe Luola'} >>> >>> >>> >>> info = {'stu1102': 'LongZe Luola', 'stu1103': 'XiaoZe Maliya'} >>> info {'stu1102': 'LongZe Luola', 'stu1103': 'XiaoZe Maliya'} #随机删除 >>> info.popitem() ('stu1102', 'LongZe Luola') >>> info {'stu1103': 'XiaoZe Maliya'}
4.4获取
>>> info = {'stu1102': 'LongZe Luola', 'stu1103': 'XiaoZe Maliya'} >>> >>> "stu1102" in info #标准用法 True >>> info.get("stu1102") #获取 'LongZe Luola' >>> info["stu1102"] #同上,但是看下面 'LongZe Luola' >>> info["stu1105"] #如果一个key不存在,就报错,get不会,不存在只返回None Traceback (most recent call last): File "<stdin>", line 1, in <module> KeyError: 'stu1105'
4.5多级字典嵌套
av_catalog = { "欧美":{ "www.youporn.com": ["很多免费的,世界最大的","质量一般"], "www.pornhub.com": ["很多免费的,也很大","质量比yourporn高点"], "letmedothistoyou.com": ["多是自拍,高质量图片很多","资源不多,更新慢"], "x-art.com":["质量很高,真的很高","全部收费,屌比请绕过"] }, "日韩":{ "tokyo-hot":["质量怎样不清楚,个人已经不喜欢日韩范了","听说是收费的"] }, "大陆":{ ":["全部免费,真好,好人一生平安","服务器在国外,慢"] } } av_catalog["][1] += ",可以用爬虫爬下来" "]) #ouput ['全部免费,真好,好人一生平安', '服务器在国外,慢,可以用爬虫爬下来']
4.6其他知识:
#values >>> info.values() dict_values(['LongZe Luola', 'XiaoZe Maliya']) #keys >>> info.keys() dict_keys(['stu1102', 'stu1103']) #setdefault >>> info.setdefault("stu1106","Alex") 'Alex' >>> info {'stu1102': 'LongZe Luola', 'stu1103': 'XiaoZe Maliya', 'stu1106': 'Alex'} >>> info.setdefault("stu1102","龙泽萝拉") 'LongZe Luola' >>> info {'stu1102': 'LongZe Luola', 'stu1103': 'XiaoZe Maliya', 'stu1106': 'Alex'} #update >>> info {'stu1102': 'LongZe Luola', 'stu1103': 'XiaoZe Maliya', 'stu1106': 'Alex'} >>> b = {1:2,3:4, "stu1102":"龙泽萝拉"} >>> info.update(b) >>> info {'stu1102': '龙泽萝拉', 1: 2, 3: 4, 'stu1103': 'XiaoZe Maliya', 'stu1106': 'Alex'} #items info.items() dict_items([('stu1102', '龙泽萝拉'), (1, 2), (3, 4), ('stu1103', 'XiaoZe Maliya'), ('stu1106', 'Alex')]) #通过一个列表生成默认dict,有个没办法解释的坑,少用吧这个 >>> dict.fromkeys([1,2,3],'testd') {1: 'testd', 2: 'testd', 3: 'testd'}
4.7循环、遍历
#方法1 for key in info: print(key,info[key]) #方法2 for k,v in info.items(): #会先把dict转成list,数据里大时莫用 print(k,v)
练习:三级菜单
源代码
__author__ = "ZingP" menu = { '四川省': { '成都市': ['锦江区', '武侯区', '高新区'], '绵阳市': ['三台县', '北川县', '江油县'], '宜宾市': ['长宁县', '兴文县', '高县'], }, '河北省': { '唐山市': ['滦南县', '玉田县', '滦县'], '邯郸市': ['永年县', '广平县', '武安县'], '秦皇岛市': ['青龙县', '卢龙县', '昌黎县'], }, '江苏省': { '南京市': ['江宁县', '江浦县', '高淳县'], '苏州市': ['昆山县', '吴江县', '太仓县'], '徐州市': ['铜山县', '丰县', '沛县'], }, } current_layer = menu father_layer = [] # 保存所有父级目录, 最后一个元素永远是父亲级 while True: for key in current_layer: print(key) choice = input(">>>:").strip() if len(choice) == 0: continue elif choice in current_layer: father_layer.append(current_layer) # 进入下一层目录时,把当前层(就是下一层的父亲级)添加到列表 current_layer = current_layer[choice] # 改为子层 elif choice == 'b': if father_layer: current_layer = father_layer.pop() # 用户选择b返回时,直接取最后一个元素,就是父亲级目录 else: print("无此项!")
5.集合
集合是一个无序的,不重复的数据组合,它的主要作用如下:
- 去重,把一个列表变成集合,就自动去重了
- 关系测试,测试两组数据之前的交集、差集、并集等关系
s = set([3,5,9,10]) #创建一个数值集合 t = set("Hello") #创建一个唯一字符的集合 a = t | s # t 和 s的并集 b = t & s # t 和 s的交集 c = t – s # 求差集(项在t中,但不在s中) d = t ^ s # 对称差集(项在t或s中,但不会同时出现在二者中) 基本操作: t.add('x') # 添加一项 s.update([10,37,42]) # 在s中添加多项 使用remove()可以删除一项: t.remove('H') len(s) set 的长度 x in s 测试 x 是否是 s 的成员 x not in s 测试 x 是否不是 s 的成员 s.issubset(t) s <= t 测试是否 s 中的每一个元素都在 t 中 s.issuperset(t) s >= t 测试是否 t 中的每一个元素都在 s 中 s.union(t) s | t 返回一个新的 set 包含 s 和 t 中的每一个元素 s.intersection(t) s & t 返回一个新的 set 包含 s 和 t 中的公共元素 s.difference(t) s - t 返回一个新的 set 包含 s 中有但是 t 中没有的元素 s.symmetric_difference(t) s ^ t 返回一个新的 set 包含 s 和 t 中不重复的元素 s.copy() 返回 set “s”的一个浅复制
6.文件操作
对文件操作流程
- 打开文件,得到文件句柄并赋值给一个变量
- 通过句柄对文件进行操作
- 关闭文件
现有文件如下
Somehow, it seems the love I knew was always the most destructive kind 不知为何,我经历的爱情总是最具毁灭性的的那种 Yesterday when I was young 昨日当我年少轻狂 The taste of life was sweet 生命的滋味是甜的 As rain upon my tongue 就如舌尖上的雨露 I teased at life as if it were a foolish game 我戏弄生命 视其为愚蠢的游戏 The way the evening breeze 就如夜晚的微风 May tease the candle flame 逗弄蜡烛的火苗 The thousand dreams I dreamed 我曾千万次梦见 The splendid things I planned 那些我计划的绚丽蓝图 I always built to last on weak and shifting sand 但我总是将之建筑在易逝的流沙上 I lived by night and shunned the naked light of day 我夜夜笙歌 逃避白昼赤裸的阳光 And only now I see how the time ran away 事到如今我才看清岁月是如何匆匆流逝 Yesterday when I was young 昨日当我年少轻狂 So many lovely songs were waiting to be sung 有那么多甜美的曲儿等我歌唱 So many wild pleasures lay in store for me 有那么多肆意的快乐等我享受 And so much pain my eyes refused to see 还有那么多痛苦 我的双眼却视而不见 I ran so fast that time and youth at last ran out 我飞快地奔走 最终时光与青春消逝殆尽 I never stopped to think what life was all about 我从未停下脚步去思考生命的意义 And every conversation that I can now recall 如今回想起的所有对话 Concerned itself with me and nothing else at all 除了和我相关的 什么都记不得了 The game of love I played with arrogance and pride 我用自负和傲慢玩着爱情的游戏 And every flame I lit too quickly, quickly died 所有我点燃的火焰都熄灭得太快 The friends I made all somehow seemed to slip away 所有我交的朋友似乎都不知不觉地离开了 And only now I'm left alone to end the play, yeah 只剩我一个人在台上来结束这场闹剧 Oh, yesterday when I was young 噢 昨日当我年少轻狂 So many, many songs were waiting to be sung 有那么那么多甜美的曲儿等我歌唱 So many wild pleasures lay in store for me 有那么多肆意的快乐等我享受 And so much pain my eyes refused to see 还有那么多痛苦 我的双眼却视而不见 There are so many songs in me that won't be sung 我有太多歌曲永远不会被唱起 I feel the bitter taste of tears upon my tongue 我尝到了舌尖泪水的苦涩滋味 The time has come for me to pay for yesterday 终于到了付出代价的时间 为了昨日 When I was young 当我年少轻狂
f = open('lyrics') #打开文件 first_line = f.readline() print('first line:',first_line) #读一行 print('我是分隔线'.center(50,'-')) data = f.read()# 读取剩下的所有内容,文件大时不要用 print(data) #打印文件 f.close() #关闭文件
打开文件的模式有:
- r,只读模式(默认)。
- w,只写模式。【不可读;不存在则创建;存在则删除内容;】
- a,追加模式。【可读; 不存在则创建;存在则只追加内容;】
"+" 表示可以同时读写某个文件
- r+,可读写文件。【可读;可写;可追加】
- w+,写读
- a+,同a
"U"表示在读取时,可以将 \r \n \r\n自动转换成 \n (与 r 或 r+ 模式同使用)
- rU
- r+U
"b"表示处理二进制文件(如:FTP发送上传ISO镜像文件,linux可忽略,windows处理二进制文件时需标注)
- rb
- wb
- ab
其它语法
def close(self): # real signature unknown; restored from __doc__ """ Close the file. A closed file cannot be used for further I/O operations. close() may be called more than once without error. """ pass def fileno(self, *args, **kwargs): # real signature unknown """ Return the underlying file descriptor (an integer). """ pass def isatty(self, *args, **kwargs): # real signature unknown """ True if the file is connected to a TTY device. """ pass def read(self, size=-1): # known case of _io.FileIO.read """ 注意,不一定能全读回来 Read at most size bytes, returned as bytes. Only makes one system call, so less data may be returned than requested. In non-blocking mode, returns None if no data is available. Return an empty bytes object at EOF. """ return "" def readable(self, *args, **kwargs): # real signature unknown """ True if file was opened in a read mode. """ pass def readall(self, *args, **kwargs): # real signature unknown """ Read all data from the file, returned as bytes. In non-blocking mode, returns as much as is immediately available, or None if no data is available. Return an empty bytes object at EOF. """ pass def readinto(self): # real signature unknown; restored from __doc__ """ Same as RawIOBase.readinto(). """ pass #不要用,没人知道它是干嘛用的 def seek(self, *args, **kwargs): # real signature unknown """ Move to new file position and return the file position. Argument offset is a byte count. Optional argument whence defaults to SEEK_SET or 0 (offset from start of file, offset should be >= 0); other values are SEEK_CUR or 1 (move relative to current position, positive or negative), and SEEK_END or 2 (move relative to end of file, usually negative, although many platforms allow seeking beyond the end of a file). Note that not all file objects are seekable. """ pass def seekable(self, *args, **kwargs): # real signature unknown """ True if file supports random-access. """ pass def tell(self, *args, **kwargs): # real signature unknown """ Current file position. Can raise OSError for non seekable files. """ pass def truncate(self, *args, **kwargs): # real signature unknown """ Truncate the file to at most size bytes and return the truncated size. Size defaults to the current file position, as returned by tell(). The current file position is changed to the value of size. """ pass def writable(self, *args, **kwargs): # real signature unknown """ True if file was opened in a write mode. """ pass def write(self, *args, **kwargs): # real signature unknown """ Write bytes b to file, return number written. Only makes one system call, so not all of the data may be written. The number of bytes actually written is returned. In non-blocking mode, returns None if the write would block. """ pass
with语句
为了避免打开文件后忘记关闭,可以通过管理上下文,即:
with open('log','r') as f: f.---- pass
如此方式,当with代码块执行完毕时,内部会自动关闭并释放文件资源。
在Python 2.7 后,with又支持同时对多个文件的上下文进行管理,即:
with open('log1') as obj1, open('log2') as obj2: pass
7.字符串与编码
需知:
1.在python2默认编码是ASCII, python3里默认是utf-8
2.unicode 分为 utf-32(占4个字节),utf-16(占两个字节),utf-8(占1-4个字节), so utf-8就是unicode
3.在py3中encode,在转码的同时还会把string 变成bytes类型,decode在解码的同时还会把bytes变回string
python2:
#-*-coding:utf-8-*- __author__ = 'Alex Li' import sys print(sys.getdefaultencoding()) msg = "我爱北京*" msg_gb2312 = msg.decode("utf-8").encode("gb2312") gb2312_to_gbk = msg_gb2312.decode("gbk").encode("gbk") print(msg) print(msg_gb2312) print(gb2312_to_gbk)
python3:
#-*-coding:gb2312 -*- #这个也可以去掉 __author__ = 'Alex Li' import sys print(sys.getdefaultencoding()) msg = "我爱北京*" #msg_gb2312 = msg.decode("utf-8").encode("gb2312") msg_gb2312 = msg.encode("gb2312") #默认就是unicode,不用再decode,喜大普奔 gb2312_to_unicode = msg_gb2312.decode("gb2312") gb2312_to_utf8 = msg_gb2312.decode("gb2312").encode("utf-8") print(msg) print(msg_gb2312) print(gb2312_to_unicode) print(gb2312_to_utf8)