python 常用小模块

1. dict为空，则dict.keys()=0

2. ",".join列表或元组变字符串

# first_check.py/get_hit_apps_rule_results
# application_ids = ",".join(str(u["application_id"]) for u in uid_info_dict.values())
uid_info_dict = {921137L:{'application_id':393049L,'uid':921137L},921138L:{'application_id':3934049L,'uid':921138L}}

a = (u for u in uid_info_dict.values())
print a  # <generator object <genexpr> at 0x05920DC8>
a = ",".join(str(u['application_id']) for u in uid_info_dict.values())
print a, type(a)  # 393049,3934049  <type 'str'>

for u in uid_info_dict.values():
    print u['application_id']  # 393049

3. ipython输出历史记录

%hist > xxx.txt

4. dict.get()和setdefault()功能基本相同，不同点：setdefault在key不存在时会把这个key添加到dict中，即新建了

5. pass,continue,break

stackoverflow 有个答案好懂：

>>> a = [0, 1, 2]
>>> for element in a:
...     if not element:
...         pass  # 不做任何动作，后续代码继续执行
...     print element
...
0
1
2
>>> for element in a:
...     if not element:
...         continue  # 跳过本次循环，if后续代码不执行
...     print element
...
1
2

6. pickle.dumps , pickle.dump

summer = Bird()
with open("summer.pkl", 'w') as f:
  pickle.dump(summer, f)   # 序列化并保存对象

pickle_string = pickle.dumps(summer)   # 分开两步 序列化对象
with open("summer.pkl",'wb') as f:
  f.write(pickle_string)

7. json.dumps , json.loads

json.loads 输出python对象
json.dumps 输出json对象

8. jupyter book 输出多个变量值

from IPython.core.interactiveshell import InteractiveShell
InteractiveShell.ast_node_interactivity = "all"

9. re 正则的使用

# 正则的使用，match , search, findall, pattern
import re
pattern = re.compile(r'\d+')
m = pattern.match('2323asa')  # match从头开始，若开始不是数字则匹配不到
search = pattern.search('sf34343')
print m, '\n', search.group()  # 34343
print m.group(), m.start(), m.end(), m.span()  # 2323 0 4
results = pattern.findall('hello 123456 789')
results2 = pattern.findall('one1two2three3four4', 0, 10)
print results, results2  # ['123456', '789'] ['1', '2']
# finditer  finditer 方法的行为跟 findall 的行为类似，也是搜索整个字符串，获得所有匹配的结果。但它返回一个顺序访问每一个匹配结果（Match 对象）的迭代器
p = re.compile(r'[\s\,\;]+')
print p.split('a,b;; c        d')
# ['a', 'b', 'c', 'd']


p2 = re.compile(r'(\w+) (\w+)')  # 空格
s = 'hello 123, hello 456'

def fun(m):
    return 'hi' + m.group(2)

print p2.sub(r'hello world', s) # hello world, hello world
print p2.sub(r'\2 \1', s)  # 123 hello, 456 hello
print p2.sub(fun, s)   # hi123, hi456
print p2.sub(fun, s, 1)         # 最多替换一次  hi123, hello 456

result_iter1 = pattern.finditer('hello 123456 789')
result_iter2 = pattern.finditer('one1two2three3four4', 0, 10)

print type(result_iter1)
print type(result_iter2)

print 'result1...'
for m1 in result_iter1:   # m1 是 Match 对象
    print 'matching string: {}, position: {}'.format(m1.group(), m1.span())

print 'result2...'
for m2 in result_iter2:
    print 'matching string: {}, position: {}'.format(m2.group(), m2.span())

10. for ... else ... for 有break/return则不执行else, continue会执行

11. 列表索引取值超过范围不会报错

12. 字符串拼接的6种方式

13. jupyter notebook 插入图片

![title](img/insert_image_book.png)

14. 虚拟环境venv

$ python3.7 -m venv ./py37async
$ source ./py37async/bin/activate # Windows: .\py37async\Scripts\activate.bat