Python基礎2 列表、字典、集合
阿新 • • 發佈：2017-07-20
列表、字典、集合
本節內容
列表、元組操作
字符串操作
字典操作
集合操作
文件操作
字符編碼與轉碼
1. 列表、元組操作
列表是我們最以後最常用的數據類型之一，通過列表可以對數據實現最方便的存儲、修改等操作
定義列表
names = [‘Alex‘,"Tenglan",‘Eric‘]通過下標訪問列表中的元素，下標從0開始計數
>>> names[0]‘Alex‘>>> names[2]‘Eric‘>>> names[-1]‘Eric‘>>> names[-2] #還可以倒著取‘Tenglan‘切片:取多個元素
>>> names = ["Alex","Tenglan","Eric","Rain","Tom","Amy"] >>> names[1:4] #取下標1至下標4之間的數字，包括1，不包括4[‘Tenglan‘, ‘Eric‘, ‘Rain‘] >>> names[1:-1] #取下標1至-1的值，不包括-1[‘Tenglan‘, ‘Eric‘, ‘Rain‘, ‘Tom‘] >>> names[0:3] [‘Alex‘, ‘Tenglan‘, ‘Eric‘] >>> names[:3] #如果是從頭開始取，0可以忽略，跟上句效果一樣[‘Alex‘, ‘Tenglan‘, ‘Eric‘] >>> names[3:] #如果想取最後一個，必須不能寫-1，只能這麽寫[‘Rain‘, ‘Tom‘, ‘Amy‘] >>> names[3:-1] #這樣-1就不會被包含了[‘Rain‘, ‘Tom‘] >>> names[0::2] #後面的2是代表，每隔一個元素，就取一個[‘Alex‘, ‘Eric‘, ‘Tom‘] >>> names[::2] #和上句效果一樣[‘Alex‘, ‘Eric‘, ‘Tom‘]
追加
>>> names
[‘Alex‘, ‘Tenglan‘, ‘Eric‘, ‘Rain‘, ‘Tom‘, ‘Amy‘]
>>> names.append("我是新來的")
>>> names
[‘Alex‘, ‘Tenglan‘, ‘Eric‘, ‘Rain‘, ‘Tom‘, ‘Amy‘, ‘我是新來的‘]插入
>>> names [‘Alex‘, ‘Tenglan‘, ‘Eric‘, ‘Rain‘, ‘Tom‘, ‘Amy‘, ‘我是新來的‘] >>> names.insert(2,"強行從Eric前面插入") >>> names [‘Alex‘, ‘Tenglan‘, ‘強行從Eric前面插入‘, ‘Eric‘, ‘Rain‘, ‘Tom‘, ‘Amy‘, ‘我是新來的‘] >>> names.insert(5,"從eric後面插入試試新姿勢") >>> names [‘Alex‘, ‘Tenglan‘, ‘強行從Eric前面插入‘, ‘Eric‘, ‘Rain‘, ‘從eric後面插入試試新姿勢‘, ‘Tom‘, ‘Amy‘, ‘我是新來的‘]
修改
>>> names [‘Alex‘, ‘Tenglan‘, ‘強行從Eric前面插入‘, ‘Eric‘, ‘Rain‘, ‘從eric後面插入試試新姿勢‘, ‘Tom‘, ‘Amy‘, ‘我是新來的‘] >>> names[2] = "該換人了" >>> names [‘Alex‘, ‘Tenglan‘, ‘該換人了‘, ‘Eric‘, ‘Rain‘, ‘從eric後面插入試試新姿勢‘, ‘Tom‘, ‘Amy‘, ‘我是新來的‘]
刪除
>>> del names[2]
>>> names
[‘Alex‘, ‘Tenglan‘, ‘Eric‘, ‘Rain‘, ‘從eric後面插入試試新姿勢‘, ‘Tom‘, ‘Amy‘, ‘我是新來的‘]
>>> del names[4]
>>> names
[‘Alex‘, ‘Tenglan‘, ‘Eric‘, ‘Rain‘, ‘Tom‘, ‘Amy‘, ‘我是新來的‘]
>>>
>>> names.remove("Eric") #刪除指定元素
>>> names
[‘Alex‘, ‘Tenglan‘, ‘Rain‘, ‘Tom‘, ‘Amy‘, ‘我是新來的‘]
>>> names.pop() #刪除列表最後一個值
‘我是新來的‘
>>> names
[‘Alex‘, ‘Tenglan‘, ‘Rain‘, ‘Tom‘, ‘Amy‘]擴展
>>> names [‘Alex‘, ‘Tenglan‘, ‘Rain‘, ‘Tom‘, ‘Amy‘] >>> b = [1,2,3] >>> names.extend(b) >>> names [‘Alex‘, ‘Tenglan‘, ‘Rain‘, ‘Tom‘, ‘Amy‘, 1, 2, 3]
拷貝
>>> names [‘Alex‘, ‘Tenglan‘, ‘Rain‘, ‘Tom‘, ‘Amy‘, 1, 2, 3] >>> name_copy = names.copy() >>> name_copy [‘Alex‘, ‘Tenglan‘, ‘Rain‘, ‘Tom‘, ‘Amy‘, 1, 2, 3]
統計
>>> names
[‘Alex‘, ‘Tenglan‘, ‘Amy‘, ‘Tom‘, ‘Amy‘, 1, 2, 3]
>>> names.count("Amy")
2排序&翻轉
>>> 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() #3.0裏不同數據類型不能放在一起排序了，擦 >>> names[-3] = ‘1‘ >>> names[-2] = ‘2‘ >>> names[-1] = ‘3‘ >>> names [‘Alex‘, ‘Amy‘, ‘Amy‘, ‘Tenglan‘, ‘Tom‘, ‘1‘, ‘2‘, ‘3‘] >>> names.sort() >>> names [‘1‘, ‘2‘, ‘3‘, ‘Alex‘, ‘Amy‘, ‘Amy‘, ‘Tenglan‘, ‘Tom‘] >>> names.reverse() #反轉 >>> names [‘Tom‘, ‘Tenglan‘, ‘Amy‘, ‘Amy‘, ‘Alex‘, ‘3‘, ‘2‘, ‘1‘]
獲取下標
>>> names
[‘Tom‘, ‘Tenglan‘, ‘Amy‘, ‘Amy‘, ‘Alex‘, ‘3‘, ‘2‘, ‘1‘]
>>> names.index("Amy")
2 #只返回找到的第一個下標元組
元組其實跟列表差不多，也是存一組數，只不是它一旦創建，便不能再修改，所以又叫只讀列表
語法
names = ("alex","jack","eric")它只有2個方法，一個是count,一個是index，完畢。
2. 字符串操作
特性：不可修改
name.capitalize() 首字母大寫
name.casefold() 大寫全部變小寫
name.center(50,"-") 輸出 ‘---------------------Alex Li----------------------‘
name.count(‘lex‘) 統計 lex出現次數
name.encode() 將字符串編碼成bytes格式
name.endswith("Li") 判斷字符串是否以 Li結尾
"Alex\tLi".expandtabs(10) 輸出‘Alex Li‘， 將\t轉換成多長的空格
name.find(‘A‘) 查找A,找到返回其索引， 找不到返回-1
format :
>>> msg = "my name is {}, and age is {}"
>>> msg.format("alex",22)
‘my name is alex, and age is 22‘
>>> msg = "my name is {1}, and age is {0}"
>>> msg.format("alex",22)
‘my name is 22, and age is alex‘
>>> msg = "my name is {name}, and age is {age}"
>>> msg.format(age=22,name="ale")
‘my name is ale, and age is 22‘
format_map
>>> msg.format_map({‘name‘:‘alex‘,‘age‘:22})
‘my name is alex, and age is 22‘
msg.index(‘a‘) 返回a所在字符串的索引
‘9aA‘.isalnum() True
‘9‘.isdigit() 是否整數
name.isnumeric
name.isprintable
name.isspace
name.istitle
name.isupper
"|".join([‘alex‘,‘jack‘,‘rain‘])
‘alex|jack|rain‘
maketrans
>>> intab = "aeiou" #This is the string having actual characters.
>>> outtab = "12345" #This is the string having corresponding mapping character
>>> trantab = str.maketrans(intab, outtab)
>>>
>>> str = "this is string example....wow!!!"
>>> str.translate(trantab)
‘th3s 3s str3ng 2x1mpl2....w4w!!!‘
msg.partition(‘is‘) 輸出 (‘my name ‘, ‘is‘, ‘ {name}, and age is {age}‘)
>>> "alex li, chinese name is lijie".replace("li","LI",1)
‘alex LI, chinese name is lijie‘
msg.swapcase 大小寫互換
>>> msg.zfill(40)
‘00000my name is {name}, and age is {age}‘
>>> n4.ljust(40,"-")
‘Hello 2orld-----------------------------‘
>>> n4.rjust(40,"-")
‘-----------------------------Hello 2orld‘
>>> b="ddefdsdff_哈哈"
>>> b.isidentifier() #檢測一段字符串可否被當作標誌符，即是否符合變量命名規則
True3. 字典操作
字典一種key - value 的數據類型，使用就像我們上學用的字典，通過筆劃、字母來查對應頁的詳細內容。
語法:
info = {
‘stu1101‘: "TengLan Wu",
‘stu1102‘: "LongZe Luola",
‘stu1103‘: "XiaoZe Maliya",
}字典的特性：
dict是無序的
key必須是唯一的,so 天生去重
增加
>>> info["stu1104"] = "蒼井空"
>>> info
{‘stu1102‘: ‘LongZe Luola‘, ‘stu1104‘: ‘蒼井空‘, ‘stu1103‘: ‘XiaoZe Maliya‘, ‘stu1101‘: ‘TengLan Wu‘}修改
>>> info[‘stu1101‘] = "武藤蘭"
>>> info
{‘stu1102‘: ‘LongZe Luola‘, ‘stu1103‘: ‘XiaoZe Maliya‘, ‘stu1101‘: ‘武藤蘭‘}刪除
>>> info
{‘stu1102‘: ‘LongZe Luola‘, ‘stu1103‘: ‘XiaoZe Maliya‘, ‘stu1101‘: ‘武藤蘭‘}
>>> info.pop("stu1101") #標準刪除姿勢
‘武藤蘭‘
>>> info
{‘stu1102‘: ‘LongZe Luola‘, ‘stu1103‘: ‘XiaoZe Maliya‘}
>>> del info[‘stu1103‘] #換個姿勢刪除
>>> info
{‘stu1102‘: ‘LongZe Luola‘}
>>>
>>>
>>>
>>> info = {‘stu1102‘: ‘LongZe Luola‘, ‘stu1103‘: ‘XiaoZe Maliya‘}
>>> info
{‘stu1102‘: ‘LongZe Luola‘, ‘stu1103‘: ‘XiaoZe Maliya‘} #隨機刪除
>>> info.popitem()
(‘stu1102‘, ‘LongZe Luola‘)
>>> info
{‘stu1103‘: ‘XiaoZe Maliya‘}查找
>>> info = {‘stu1102‘: ‘LongZe Luola‘, ‘stu1103‘: ‘XiaoZe Maliya‘}
>>>
>>> "stu1102" in info #標準用法
True
>>> info.get("stu1102") #獲取
‘LongZe Luola‘
>>> info["stu1102"] #同上，但是看下面
‘LongZe Luola‘
>>> info["stu1105"] #如果一個key不存在，就報錯，get不會，不存在只返回None
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
KeyError: ‘stu1105‘多級字典嵌套及操作
av_catalog = {
"歐美":{
"www.youporn.com": ["很多免費的,世界最大的","質量一般"],
"www.pornhub.com": ["很多免費的,也很大","質量比yourporn高點"],
"letmedothistoyou.com": ["多是自拍,高質量圖片很多","資源不多,更新慢"],
"x-art.com":["質量很高,真的很高","全部收費,屌比請繞過"]
},
"日韓":{
"tokyo-hot":["質量怎樣不清楚,個人已經不喜歡日韓範了","聽說是收費的"]
},
"大陸":{
"1024":["全部免費,真好,好人一生平安","服務器在國外,慢"]
}
}
av_catalog["大陸"]["1024"][1] += ",可以用爬蟲爬下來"
print(av_catalog["大陸"]["1024"])
#ouput
[‘全部免費,真好,好人一生平安‘, ‘服務器在國外,慢,可以用爬蟲爬下來‘]其它姿勢
#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","龍澤蘿拉")
‘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":"龍澤蘿拉"}
>>> info.update(b)
>>> info
{‘stu1102‘: ‘龍澤蘿拉‘, 1: 2, 3: 4, ‘stu1103‘: ‘XiaoZe Maliya‘, ‘stu1106‘: ‘Alex‘}
#items
info.items()
dict_items([(‘stu1102‘, ‘龍澤蘿拉‘), (1, 2), (3, 4), (‘stu1103‘, ‘XiaoZe Maliya‘), (‘stu1106‘, ‘Alex‘)])
#通過一個列表生成默認dict,有個沒辦法解釋的坑，少用吧這個
>>> dict.fromkeys([1,2,3],‘testd‘)
{1: ‘testd‘, 2: ‘testd‘, 3: ‘testd‘}循環dict
#方法1
for key in info:
print(key,info[key])
#方法2
for k,v in info.items(): #會先把dict轉成list,數據裏大時莫用
print(k,v)4.集合操作
集合是一個無序的，不重復的數據組合，它的主要作用如下：
去重，把一個列表變成集合，就自動去重了
關系測試，測試兩組數據之前的交集、差集、並集等關系
常用操作
s = set([3,5,9,10]) #創建一個數值集合
t = set("Hello") #創建一個唯一字符的集合
a = t | s # t 和 s的並集
b = t & s # t 和 s的交集
c = t – s # 求差集（項在t中，但不在s中）
d = t ^ s # 對稱差集（項在t或s中，但不會同時出現在二者中）
基本操作：
t.add(‘x‘) # 添加一項
s.update([10,37,42]) # 在s中添加多項
使用remove()可以刪除一項：
t.remove(‘H‘)
len(s)
set 的長度
x in s
測試 x 是否是 s 的成員
x not in s
測試 x 是否不是 s 的成員
s.issubset(t)
s <= t
測試是否 s 中的每一個元素都在 t 中
s.issuperset(t)
s >= t
測試是否 t 中的每一個元素都在 s 中
s.union(t)
s | t
返回一個新的 set 包含 s 和 t 中的每一個元素
s.intersection(t)
s & t
返回一個新的 set 包含 s 和 t 中的公共元素
s.difference(t)
s - t
返回一個新的 set 包含 s 中有但是 t 中沒有的元素
s.symmetric_difference(t)
s ^ t
返回一個新的 set 包含 s 和 t 中不重復的元素
s.copy()
返回 set “s”的一個淺復制5. 文件操作
對文件操作流程
打開文件，得到文件句柄並賦值給一個變量
通過句柄對文件進行操作
關閉文件
現有文件如下
Somehow, it seems the love I knew was always the most destructive kind 不知為何，我經歷的愛情總是最具毀滅性的的那種 Yesterday when I was young 昨日當我年少輕狂 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 我戲弄生命 視其為愚蠢的遊戲 The way the evening breeze 就如夜晚的微風 May tease the candle flame 逗弄蠟燭的火苗 The thousand dreams I dreamed 我曾千萬次夢見 The splendid things I planned 那些我計劃的絢麗藍圖 I always built to last on weak and shifting sand 但我總是將之建築在易逝的流沙上 I lived by night and shunned the naked light of day 我夜夜笙歌 逃避白晝赤裸的陽光 And only now I see how the time ran away 事到如今我才看清歲月是如何匆匆流逝 Yesterday when I was young 昨日當我年少輕狂 So many lovely songs were waiting to be sung 有那麽多甜美的曲兒等我歌唱 So many wild pleasures lay in store for me 有那麽多肆意的快樂等我享受 And so much pain my eyes refused to see 還有那麽多痛苦 我的雙眼卻視而不見 I ran so fast that time and youth at last ran out 我飛快地奔走 最終時光與青春消逝殆盡 I never stopped to think what life was all about 我從未停下腳步去思考生命的意義 And every conversation that I can now recall 如今回想起的所有對話 Concerned itself with me and nothing else at all 除了和我相關的 什麽都記不得了 The game of love I played with arrogance and pride 我用自負和傲慢玩著愛情的遊戲 And every flame I lit too quickly, quickly died 所有我點燃的火焰都熄滅得太快 The friends I made all somehow seemed to slip away 所有我交的朋友似乎都不知不覺地離開了 And only now I‘m left alone to end the play, yeah 只剩我一個人在臺上來結束這場鬧劇 Oh, yesterday when I was young 噢 昨日當我年少輕狂 So many, many songs were waiting to be sung 有那麽那麽多甜美的曲兒等我歌唱 So many wild pleasures lay in store for me 有那麽多肆意的快樂等我享受 And so much pain my eyes refused to see 還有那麽多痛苦 我的雙眼卻視而不見 There are so many songs in me that won‘t be sung 我有太多歌曲永遠不會被唱起 I feel the bitter taste of tears upon my tongue 我嘗到了舌尖淚水的苦澀滋味 The time has come for me to pay for yesterday 終於到了付出代價的時間 為了昨日 When I was young 當我年少輕狂
基本操作
f = open(‘lyrics‘) #打開文件 first_line = f.readline() print(‘first line:‘,first_line) #讀一行 print(‘我是分隔線‘.center(50,‘-‘)) data = f.read()# 讀取剩下的所有內容,文件大時不要用 print(data) #打印文件 f.close() #關閉文件
打開文件的模式有：
r，只讀模式（默認）。
w，只寫模式。【不可讀；不存在則創建；存在則刪除內容；】
a，追加模式。【可讀； 不存在則創建；存在則只追加內容；】
"+" 表示可以同時讀寫某個文件
r+，可讀寫文件。【可讀；可寫；可追加】
w+，寫讀
a+，同a
"U"表示在讀取時，可以將 \r \n \r\n自動轉換成 \n （與 r 或 r+ 模式同使用）
rU
r+U
"b"表示處理二進制文件（如：FTP發送上傳ISO鏡像文件，linux可忽略，windows處理二進制文件時需標註）
rb
wb
ab
其它語法
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
"""
註意，不一定能全讀回來
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,沒人知道它是幹嘛用的
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.
"""
passwith語句
為了避免打開文件後忘記關閉，可以通過管理上下文，即：
with open(‘log‘,‘r‘) as f:
...如此方式，當with代碼塊執行完畢時，內部會自動關閉並釋放文件資源。
在Python 2.7 後，with又支持同時對多個文件的上下文進行管理，即：
with open(‘log1‘) as obj1, open(‘log2‘) as obj2:
pass本文出自 “阿明博客” 博客，謝絕轉載！
Python基礎2 列表、字典、集合