Effective Python (Pythonic Thinking)
Know the differences Between bytes,str and unicode
In Python 3, there are two types that represent sequences of characters: bytes and str. Instances of bytes contain raw 8-bit values. Instances of str contain Unicode characters.
# to_str
def to_str(bytes_or_str):
if isinstance(bytes_to_str, bytes):
value = bytes_or_str.decode('utf-8')
else:
value = bytes_or_str
return value # Instance of str
# to_bytes
def to_bytes(bytes_or_str):
if isinstance(bytes_to_str, str):
value = bytes_to_str.encode('utf-8')
else:
value = bytes_to_str
return value # Instance of bytes
In Python 2, there are two types that represent sequences of characters: str andunicode. In contrast to Python 3, instances of str contain raw 8-bit values. Instances ofunicode contain Unicode characters.
# to_unicode
def to_unicode(unicode_or_str):
if isinstance(unicode_or_str, str):
value = unicode_or_str.encode('utf-8')
else:
value = unicode_or_str
return value # Instance of unicode
# to_str
def to_str(unicode_or_str):
if isinstance(unicode_or_str, unicode):
value = unicode_or_str.decode('utf-8')
else:
value = unicode_or_str
return value # Instance of str
如果你要读取/写入二进制数据至文件中，请使用”rb“或者”wb“:
import os
with open('/tmp/random.bin', 'wb') as f:
f.write(os.urandom(10))
Use List Comprehensions Instead of map and filter （用列表解析代替map和filter）
a = [1, 2, 3, 4]
squares = [x ** 2 for x in a]
squares = map(lambda x: x ** 2, a)
even_squares = [x ** 2 for x in a if x % 2 == 0]
alt = map(lambda x: x ** 2, filter(lambda x: x % 2 == 0, a))
# 对调字典的key与value
chile_ranks = {'ghost': 1, 'habanero': 2, 'cayenne': 3}
rank_dict = {rank: name for name, rank in chile_ranks.items()}
chile_len_set = {len(name) for name in rank_dict.values()}
Consider Generator Expressions for Large Comprehensions（用生成器表达式代替大的列表解析）
value = [len(x) for x in open('/tmp/my_file.txt')]
print(value)
it = (len(x) for x in open('/tmp/my_file.txt'))
print(next(it))
# 生成器表达式可以由另外一个生成器表达式构成
roots = ((x, x**0.5) for x in it)
print(next(roots))
Prefer enumerate Over range
# 当迭代一个列表，同时想知道当前元素的索引(计数)时；使用enumerate而不是range
flavor_list = ['vanilla', 'chocolate', 'pecan', 'strawberry']
# use range
for i in range(len(flavor_list)):
print('%d: %s' % (i, flavor_list[i]))
# use enumerate
for i, flavor in enumerate(flavor_list): # enumerate(flavor_list, 1)可为enumerate指定开始计数值
print('%d: %s' % (i, flavor))
Use zip to Process Iterators in Parallel
# 使用zip并行处理迭代器 names = ['Cecilia', 'Lise', 'Marie'] letters = [len(n) for n in names] max_letters = 0 for name, count in zip(names, letters): if count > max_letters: longest_name = name max_letters = count # 注意：在Python3中zip是一个元组生成器；在Python2中zip是一个由元组组成的列表。
Avoid else Blocks After for and while Loops
# 避免在for与while循环之后使用else # 1，在没有break的for/while循环结束后，会马上执行else中的语句 # 2，避免在循环之后使用else，因为else不确定是否执行 for i in in range(5): print i else: print 'else run' for i in range(5): break else: print 'else not run'
Take Advantage of Each Block in try/except/else/finally
# 使用finally 去可靠的关机文件句柄、socket等
handle = open('/tmp/random_data.txt') # May raise IOError
try:
data = handle.read() # May raise UnicodeDecodeError
finally:
try:
handle.close() # Always runs after try
except Exception:
pass
# 使用else 减少try block里面的代码量、提高可读性
# 如：从字符串中加载一个json dict并返回某个key的value
def load_json_key(data, key):
try:
result_dict = json.loads(data) # May raise ValueError
except ValueError as e:
raise KeyError from e
else:
return result_dict[key] # May raise KeyError
#
UNDEFINED = object()
def divide_json(path):
handle = open(path, 'r+') # May raise IOError
try:
data = handle.read() # May raise UnicodeDecodeError
op = json.loads(data) # May raise ValueError
value = (op['numerator'] / op['denominator']) # May raise ZeroDivisonError
except ZeroDivisionError as e:
return UNDEFINED
else:
op['result'] = value
result = json.dumps(op)
handle.seek(0)
handle.write(result) # May raise IOError
return value
finally:
try:
handle.close() # Always runs
except Exception:
pass