1.range(x,y)
[x,y)
>>> range(0,4) #0,1,2,3
>>> range(1,4) #1,2,3
2.dics
dics.get(key, default=None)
当key在dics中不存在时返回default的值,返回一个函数也是可以的
>>> dics = {
0 : 'a',
1 : 'b',
2 : 'c'
}
>>> dics.get(1, 'not found')
'b'
>>> dics.get(4, 'not found')
'not found'
- 判断key在dic中是否存在
两种方法__contains__('key')
'key' in d.keys()
>>> d = {'name':'jack', 'sex':1, 'age':33}
>>> d
{'name': 'jack', 'sex': 1, 'age': 33}
>>> d.__contains__('name')
True
>>> 'name' in d.keys()
True
- foreach一个dic
j = {'key1' : 'value1', 'key2' : 'value2'}
for key, value in j.items(): # items()中每一项都是 tuple 类型,这里的key和value不是特定的关键字
print(key)
print(value)
# key1
# value1
# key2
# value2
单独循环key或者values
for k in j.keys():
print(k)
for v in j.values():
print(v)
3.读写文件
python中文件被分为两种,text or binary
- text
读到的字符串经过了编码
每一行都以EOL(End of Line)结尾
\n
on Unix
\r\n
on Windows
在写入的字符串中加入'\n'会自动换行
- binary
在mode后加上'b'
二进制方式读写文件
基本流程
open
write | read
close
with 相当于 using,自动close()
# mode r w a(append) r+(read and write)
with open('filepath','mode', encoding = 'utf-8') as file:
file.write('aaa')
file.read(size) # 读size个字符或byte
file.readline()
# from_what 0 (default)beginning of the file
# 1 current file position
# 2 end of file
file.seek(offset, from_what)
file.readlines()
写json
import json
with open('filepath', 'w', encoding = 'utf-8') as file:
data = json.dumps(u'data', ensure_ascii = False)
file.write(unicode(data))
python的json库只能序列化python的内置类型,如果是自定义的数据结构无法使用json.dumps序列化
可以使用jsonpickle
import jsonpickle
class Thing(object):
def __init__(self, name):
self.name = name
obj = Thing('Awesome')
jsn = jsonpickle.encode(obj) # 序列化,会带上类型信息用于反序列化
jsonpickle.decode(jsn) # 反序列化
jsn = jsonpickle.encode(obj, unpicklable=False) #序列化,不带类型信息
4. 判断某个class是否存在某个attribute
hasattr(class_a, 'attribute')
5. 判断某个变量是否是list
a = [1, 2, 3]
if isinstance(a, list):
print('a is a list')
6. list.append(),引用传递
在li.append(a)
之后对a进行修改,li中的数据也会改变
此时的a与li[0]指向同一块内存
>>> import scrapy
>>>
>>> class A(scrapy.Item):
... post_id = scrapy.Field()
... author_id = scrapy.Field()
>>>
>>> a = A(post_id = "post_id_1", author_id = "author_id_1")
>>> li = []
>>> li.append(a)
>>> print(li)
[{'author_id': 'author_id_1', 'post_id': 'post_id_1'}]
>>> a['post_id'] = 'post_id_2'
>>> print(li)
[{'author_id': 'author_id_1', 'post_id': 'post_id_2'}]