Eric的新家

导航

七月在线爬虫班学习笔记（二）——Python基本语法及面向对象

第二课主要内容如下：

  • 代码格式
  • 基本语法
  • 关键字
  • 循环判断
  • 函数
  • 容器
  • 面向对象
  • 文件读写
  • 多线程
  • 错误处理

代码格式

syntax基本语法

 1 a = 1234
 2 print(a)
 3 a = 'abcd'
 4 print(a)
 5 
 6 try:
 7     print(b)
 8 except Exception as e:
 9     print(e)
10 
11 a = [1, 2, 3 , 4]
12 
13 def func(a):
14     a[0] = 2
15 
16 func(a)
17 print(a)
18 
19 try:
20     # Python 2.x 支持
21     print(100, 200, 300)
22 except Exception as e:
23     print(e)
1 1234
2 abcd
3 name 'b' is not defined
4 [2, 2, 3, 4]
5 100 200 300

condition_and_loop 循环判断

 1 score = 80
 2 if score > 90:
 3     print('A')
 4 elif score > 70:
 5     print('B')
 6 elif score >= 60:
 7     print('C')
 8 else:
 9     print('D')
10 
11 total = 0
12 i = 1
13 while i <= 100:
14     total += i
15     i += 1  # 没有++i或者--i
16 print(total)
17 
18 '''
19 for循环只作用于容器！！！
20 没有这种写法：
21   for (i = 0; i < 100; ++i):
22       # TODO
23 上面这种循环只能用while实现
24 '''
25 
26 i = 0
27 while i < 3:
28     j = 0 
29     while j <= 3:
30         if j == 2:
31             j += 1
32             continue  # 又去了while j <= 3
33         print(i, j)
34         j += 1
35     i += 1
 1 B
 2 5050
 3 0 0
 4 0 1
 5 0 3
 6 1 0
 7 1 1
 8 1 3
 9 2 0
10 2 1
11 2 3

func函数

def hello(who = 'world'):
    print('hello %s!' % (who))

hello()
hello('sea')

# f(x) = x * 5 + 100
# g(x) = x * 5; f(x) = x + 100
# => f(g(x)) = x * 5 + 100
def g(x):
    return x * 5
def f(gf, x):
    return gf(x) + 100
print(f(g, 100))
print(f(lambda x: x * 5, 100))

def f(gf, x, y):
    return gf(x, y) + 100
print(f(lambda x, y: x * y, 100, 200))

#输出结果
hello world!
hello sea!
600
600
20100

ct_list数组

# list就是数组
li = [1, 2, 3, 4, 5]
# 遍历
for i in li:
    # print(i)
    pass
# 用range模拟for (i = 0; i < x; ++i)
# range(x) => [0, x - 1]
# range(x, y) => [x, y - 1]
# range(x, y, z) => [x, x + z,..., < y]
for i in range(len(li)):
    # print(li[i])
    pass

for i in range(1, 10, 2):
    print(i)

#输出结果
1
3
5
7
9
1 # 负数索引
2 print(li[-1])
3 print(li[-2])
4 
5 # 负数step的range => [x, x - z, ..., > z]
6 for i in range(3, -1, -1):
7     print(i)
1 #输出结果
2 5
3 4
4 3
5 2
6 1
7 0
 1 # 添加元素
 2 li = []
 3 li.append(1)
 4 li.append(2)
 5 li.append('abc')
 6 li.append(['d', 'e', 'f'])
 7 print(li)
 8 
 9 # 按元素添加数组
10 li = [1, 2]
11 li_2 = [3, 4, 5]
12 # 我们想要[1, 2, 3, 4, 5]
13 # li.append(li_2) => [1, 2, [3, 4, 5]]
14 li.extend(li_2)
15 print(li)
16 
17 # 删除元素
18 li.pop()    # => [1, 2, 3, 4]
19 print(li)
20 li.pop(2)   # => [1, 2, 4]
21 print(li)
22 
23 
24 #输出结果
25 [1, 2, 'abc', ['d', 'e', 'f']]
26 [1, 2, 3, 4, 5]
27 [1, 2, 3, 4]
28 [1, 2, 4]
 1 li = [5, 8, 7, 4, 2, 3]
 2 li.sort()
 3 print(li)
 4 # lambda帮助排序
 5 li = [[5, 2], [3, 8], [2, 11], [7, 6]]
 6 # li.sort(key = lambda x: x[0]) # 参数名字
 7 # 与lamda等价写法
 8 def item_key(x):
 9     return x[0]
10 li.sort(key = item_key)
11 print(li)
12 
13 
14 #输出结果
15 [2, 3, 4, 5, 7, 8]
16 [[2, 11], [3, 8], [5, 2], [7, 6]]

ct_tuple只读数组

1 # 只读数组
2 tp = (1, 2, 3)
3 try:
4     tp[0] = 100
5 except Exception as e:
6     print(e)

ct_set没有重复元素的数组

1 s = set([1, 2, 2, 3, 3, 4, 5])
2 print(s)
3 s = set((2, 3, 4, 5, 6, 2, 1, 9))
4 print(s)
5 
6 #输出
7 {1, 2, 3, 4, 5}
8 {1, 2, 3, 4, 5, 6, 9}

ct_dict 字典（哈希表）

 1 # key<->value对应的hash表
 2 di = {'k1': 'v1', 'k2': 'v2'}
 3 di['k3'] = 'v3'
 4 di['k4'] = 'v4'
 5 
 6 for k in di:
 7     print(di[k])
 8 
 9 for k, v in di.items():
10     print(k, v)
11 
12 
13 #输出
14 v3
15 v4
16 v2
17 v1
18 k3 v3
19 k4 v4
20 k2 v2
21 k1 v1

 slice数组切片

 1 # [1, 2, 3, 4, 5]
 2 #  => [1, 2, 3]
 3 #  => [3, 4]
 4 li = [1, 2, 3, 4, 5]
 5 li_0_2 =li[0:3] # 0 <= ? < 3
 6 # 等价li[:3]
 7 print(li_0_2)
 8 # [start, end, step] => [start, start + step, ..., < end]
 9 # start默认是0，end默认-1，step默认1
10 li_last_3 = li[-1:-4:-1]
11 print(li_last_3)
12 
13 # 直接用切片反转数组
14 print(li[::-1])
15 print(li[-2::-1])
16 
17 # 切片是复制
18 li_0_2[-1] = 100
19 print(li)
20 
21 
22 #输出
23 [1, 2, 3]
24 [5, 4, 3]
25 [5, 4, 3, 2, 1]
26 [4, 3, 2, 1]
27 [1, 2, 3, 4, 5

list_string字符串与数组的关系

 1 s = 'abcdefg'
 2 try:
 3     str[0] = 'x'
 4 except Exception as e:
 5     print(e)
 6 
 7 # 修改字符串
 8 li = list(s)
 9 # print(li)
10 li[0] = 'x'
11 s = ''.join(li)
12 print(s)
13 s = '-'.join(li)
14 print(s)
15 
16 # 切割
17 s = 'abc,def,ghi'
18 p1, p2, p3 = s.split(',')
19 print(p1, p2, p3)
20 
21 # 下标访问和切片
22 s = 'abcdefg'
23 print(s[0], s[-1])
24 print(s[2:5])
25 
26 #输出
27 'type' object does not support item assignment
28 xbcdefg
29 x-b-c-d-e-f-g
30 abc def ghi
31 a g
32 cde

obj面向对象

1 # 用type查看对象类型
2 print(type([1, 2, 3, 4]))
3 print(type('abcd'))
4 print(type({1:2, 2:3}))
5 
6 # 用dir查看属性和方法
7 print(dir(list))
1 <class 'list'>
2 <class 'str'>
3 <class 'dict'>
4 ['__add__', '__class__', '__contains__', '__delattr__', '__delitem__', '__dir__', '__doc__', '__eq__', '__format__', '__ge__', '__getattribute__', '__getitem__', '__gt__', '__hash__', '__iadd__', '__imul__', '__init__', '__iter__', '__le__', '__len__', '__lt__', '__mul__', '__ne__', '__new__', '__reduce__', '__reduce_ex__', '__repr__', '__reversed__', '__rmul__', '__setattr__', '__setitem__', '__sizeof__', '__str__', '__subclasshook__', 'append', 'clear', 'copy', 'count', 'extend', 'index', 'insert', 'pop', 'remove', 'reverse', 'sort']
 1 class Clazz(object):
 2     # self参考C++的this指针！
 3     def __init__(self, x, y):
 4         self.x = x
 5         self.y = y
 6 
 7     # 声明成员函数的时候，第一个参数一定是self，不要忘记！
 8     def display(self):
 9         print(self.x, self.y)
10 
11 print(type(Clazz))
12 clz = Clazz(100, 200)
13 clz.display()  # => display(clz)
14 
15 class Base:
16     def run(self):
17         print('Base::run')
18 
19 class Tom(Base):
20     def run(self):
21         print('Tom::run')
22 
23 t = Tom()
24 print(isinstance(t, Base))
25 t.run()
<class 'type'>
100 200
True
Tom::run
 1 def run(runner):
 2     runner.run()
 3 
 4 class R1:
 5     def run(self):
 6         print('R1::run')
 7 
 8 class R2:
 9     def run(self):
10         print('R2::run')
11 
12 run(R1())
13 run(R2())
14 
15 #输出
16 R1::run
17 R2::run

file_rw文件读写

 1 # 打开文件操作可能失败,异常处理后不会造成资源泄露等情况
 2 with open('text.txt', 'w') as f:
 3     f.write('''1234
 4     abcd
 5     nefgh''')
 6 
 7 with open('text.txt', 'rb') as f:
 8     print(f.read())
 9 
10 with open('text.txt') as f:
11     for line in f.readlines():
12         print(line.strip())
13 
14 #输出
15 b'1234\r\n    abcd\r\n    nefgh'
16 1234
17 abcd
18 nefgh

threads多线程

 1 import threading
 2 
 3 def thread_func(x):
 4     # 自己加sleep和其它复杂操作看效果
 5     print('%d\n' % (x * 100))
 6 
 7 threads = []
 8 for i in range(5):
 9     threads.append(threading.Thread(target = thread_func, args = (100, )))
10 
11 for thread in threads:
12     thread.start()
13 
14 for thread in threads:
15     thread.join()
16 
17 
18 #输出
19 10000
20 
21 10000
22 
23 10000
24 
25 10000
26 
27 10000

error_handling错误和异常处理

 1 # 错误处理
 2 
 3 try:
 4     r = 10 / 0
 5 except ZeroDivisionError as e:
 6     print(type(e))
 7     print(e)
 8 finally:
 9     # 主要防止资源泄露(服务端。客户端一般不会资源泄露)！
10     print('Always come here.')
11 
12 #输出
13 <class 'ZeroDivisionError'>
14 division by zero
15 Always come here.
1 import logging
2 logging.basicConfig(filename='example.log',level=logging.DEBUG)
3 logging.debug('This message should go to the log file')
4 logging.info('So should this')
5 logging.warning('And this, too')

 

posted on 2018-05-07 15:52  Eric的新家  阅读(448)  评论(0)  编辑  收藏  举报