# 写 csv 文件
# newline='' 可以在读写时移除空白行
import csv
with open('eggs.csv', 'w', newline='') as csvfile:
    spamwriter = csv.writer(csvfile)
    spamwriter.writerow(['Spam'] * 5 + ['Baked Beans'])
    spamwriter.writerow(['Spam', 'Lovely Spam', 'Wonderful Spam'])

# cat eggs.csv            
# Spam,Spam,Spam,Spam,Spam,Baked Beans
# Spam,Lovely Spam,Wonderful Spam

# 一次性写多行
header = ['name', 'area', 'country_code2', 'country_code3']
data = [
    ['Albania', 28748, 'AL', 'ALB'],
    ['Angola', 1246700, 'AO', 'AGO']
]

with open('countries.csv', 'w', encoding='UTF8', newline='') as f:
    writer = csv.writer(f)
    # write the header
    writer.writerow(header)
    # write multiple rows
    writer.writerows(data)

# 如果数据以 dict 的格式出现，可以使用 DictWriter 简化操作
fieldnames = ['name', 'area', 'country_code2', 'country_code3']
# csv data
rows = [
    {'name': 'Algeria',
    'area': 2381741,
    'country_code2': 'DZ',
    'country_code3': 'DZA'},
    {'name': 'American Samoa',
    'area': 199,
    'country_code2': 'AS',
    'country_code3': 'ASM'}
]

with open('countries.csv', 'w', encoding='UTF8', newline='') as f:
    writer = csv.DictWriter(f, fieldnames=fieldnames)
    writer.writeheader()
    writer.writerows(rows)

# 读 csv 文件
import csv
with open('some.csv', newline='') as f:
    reader = csv.reader(f)
    for row in reader:
        print(row)
# ['Spam', 'Spam', 'Spam', 'Spam', 'Spam', 'Baked Beans']
# ['Spam', 'Lovely Spam', 'Wonderful Spam']

import csv
# 拿到 csv 的 _raw 列数据
context = []
rows = []
with open('dump_csv.csv', newline='') as csvfile:
   contexts = csv.reader(csvfile)
   # 使用 reader = csv.DictReader(csvfile) 的话可以使用 column name 取值
   # 例如: reader['companyId'], 不过缺点是要在 with loop 中处理完数据
   rows = [row[16] for row in contexts]
   rows = [1:]

# 分析 _raw 数据特性，决定使用正则匹配数据
# publishedAt:"(.*?)" 加 ? 表示 非贪婪
# publishedAt=(\d+)
# inactiveUserId": (\[.*?\])
# 以上表达式取 group 1 数据

import re
from datetime import datetime
# re.findAll
# re.match() 从开头开始匹配
# re.search(reg, src) 匹配任意位置

reg1 = 'publishedAt:"(.*?)"'
reg2 = 'publishedAt=(\d+)'
reg3 = 'inactiveUserId": (\[.*?\])'

rowlist = []
for row in rows:
    infolist = []
    timestr01 = re.search(reg1, row).group(1)
    d1 = datetime.strptime(timestr01, '%Y-%m-%d %H:%M:%S')
    infolist.append(d1)

    timestr2 = int(re.search(reg2, row).group(1))
    d2 = datetime.fromtimestamp(timestr2/1000.0)
    infolist.append(d2)

    users = re.search(reg3, row).group(1)
    ulist = eval(users) # string 转化为 list
    infolist.append(ulist)
    rowlist.append(infolist)

# 把数据根据时间先后排序
sortedList = sorted(rowlist, key=lambda sub: sub[1])

def printList(line):
    formatStr01 = '%y-%m-%d %H:%M:%S'
    print(line[0].strftime(formatStr01), end=' | ')
    print("%15f" % (line[1].timestamp()), end=' | ')
    arrStr = str(line[2][:5]) + "..." + str(len(line[2])) if len(line[2]) > 5 else str(line[2])
    print(arrStr)

for sub in sortedList:
    printList(sub)

import csv
with open('eggs.csv', 'w', newline='') as csvfile:
    spamwriter = csv.writer(csvfile)
    spamwriter.writerow(['Spam', 'Baked Beans'])

from datetime import datetime

# 获取当前时间
datetime.now()
# Out[18]: datetime.datetime(2020, 6, 18, 17, 2, 48, 14847)

# 感知型 now
from datetime import timezone
dt =datetime.now(timezone.utc)

# datetime 得到 s
dt.timestamp()
# Out[41]: 1592472504.59345

# s 转 datetime, ms 的话把时间除1000.0即可 1592472504.59345/1000.0
d = datetime.fromtimestamp(1592472504.59345)
# Out[43]: datetime.datetime(2020, 6, 18, 17, 28, 24, 593450)

# strftime: string from time, 即格式化输出时间, 对象方法
now = datetime.now()
now.strftime('[%y%m%d]-[%H:%M:%S]')
# Out[22]: '[200618]-[17:12:46]'

# strptime: string parse to time, 即将字符串转化为时间, 类方法
dt = datetime.strptime('[200618]-[17:12:46]', '[%y%m%d]-[%H:%M:%S]')
# Out[24]: datetime.datetime(2020, 6, 18, 17, 12, 46)

from datetime import timedelta
delta = timedelta(days=50, seconds=27, microseconds=10, milliseconds=29000, minutes=5, hours=8, weeks=2)
# Out[16]: datetime.timedelta(days=64, seconds=29156, microseconds=10)

# 可以通过 datetime 做计算得到
now - dt
# Out[26]: datetime.timedelta(seconds=329, microseconds=894908)

import json
a = {'name': 'jack'}
json.dump(a)
# Out[6]: '{"name": "jack"}'

with open('data.json', 'w') as file:
    json.dump([a, a], file)
# 当前目录下会生产名为 data.json 的文件，内容为 [{"name": "jack"}, {"name": "jack"}]

ret = json.loads('{"name": "jack"}')
ret, type(ret)
# Out[11]: ({'name': 'jack'}, dict)

with open('data.json') as file:
    ret = json.load(file)
print(ret)
# [{'name': 'jack'}, {'name': 'jack'}]

me = {'name': '我'}
with open('dump3.json', 'w', encoding='utf-8') as file:
    json.dump(me, file, ensure_ascii=False)

with open('dump3.json', encoding='utf-8') as file:
    ret = json.load(file)
    print(ret)
# {'name': '我'}

# 该例子中，Person 是自定义的类，所以调用 dumps 时，如果直接传入，会抛 exception: TypeError: Object of type Person is not JSON serializable
class Person:
    def __init__(self, name, age):
        self.name = name
        self.age = age

# 可以通过指定 default 参数，给出转化规则

def PersonConvert(person):
    if isinstance(person, Person):
        return person.__dict__
    else:
        raise TypeError

p = Person('jack',30)
json.dumps(p, default=PersonConvert)
# Out[28]: '{"name": "jack", "age": 30}'

# 也可以通过指定 cls 参数，给出转化规则
class PersonEncoder(json.JSONEncoder):
    def default(self, obj):
        if isinstance(obj, Person):
            return obj.__dict__
        else:
            return json.JSONEncoder.default(self, obj)

json.dumps(p, cls=PersonEncoder)
# Out[30]: '{"name": "jack", "age": 30}'

# 如果此时我们对 Person 做一下升级，添加一个 datetime 属性
class Person:
    def __init__(self, name, age):
        self.name = name
        self.age = age
        self.create_date = datetime.now()

# 那么之前的函数就不够用了，我们除了要处理 Person 的逻辑，还要处理 datetime 的逻辑
def PersonConvertV2(obj):
    if isinstance(obj, Person):
        return obj.__dict__
    elif isinstance(obj, datetime):
        return obj.timestamp()
    else:
        raise TypeError

p2 = Person('Tom', 31)
json.dumps(p2, default=PersonConvertV2)
# Out[46]: '{"name": "Tom", "age": 31, "create_date": 1592802400.657711}'

# 网上有给出比较多经典的转化方式，在转化过程中会携带 class, module 的信息，为反序列化做准备
def obj_to_dict(obj):
    if isinstance(obj, Person):
        d = {}
        d['__class__'] = obj.__class__.__name__
        d['__module__'] = obj.__module__
        d.update(obj.__dict__)
            return d
        elif isinstance(obj, datetime):
            return obj.timestamp()
        else:
            raise TypeError

json.dumps(p2, default=obj_to_dict)
# Out[54]: '{"__class__": "Person", "__module__": "__main__", "name": "Tom", "age": 31, "create_date": 1592802400.657711}'

 def dict_to_obj(d):
    if "level01" in d:
        print("l1: %s" % d)
        return d
    elif "level02" in d:
        print("l2: %s" %d)
        return d
    else:
        raise TypeError

json.loads(jstr, object_hook=dict_to_obj)
# l2: {'level02': 'true', 'age': 30}
# l1: {'level01': 'true', 'name': 'jack', 'info': {'level02': 'true', 'age': 30}}     
# Out[13]: {'level01': 'true', 'name': 'jack', 'info': {'level02': 'true', 'age': 30}}

def dict_to_obj(our_dict):
    """
    Function that takes in a dict and returns a custom object associated with the dict.
    This function makes use of the "__module__" and "__class__" metadata in the dictionary
    to know which object type to create.
    """
    if "__class__" in our_dict:
        # Pop ensures we remove metadata from the dict to leave only the instance arguments
        class_name = our_dict.pop("__class__")
        # Get the module name from the dict and import it
        module_name = our_dict.pop("__module__")
        # We use the built in __import__ function since the module name is not yet known at runtime
        module = __import__(module_name)
        # Get the class from the module
        class_ = getattr(module,class_name)
        # Use dictionary unpacking to initialize the object
        obj = class_.__new__(class_)
        for key, value in our_dict.items():
            if key == 'create_date':
                value = datetime.fromtimestamp(value)
            setattr(obj, key, value)
    else:
        obj = our_dict
    return obj

jstr = '{"__class__": "Person", "__module__": "__main__", "name": "Jack", "age": 30, "create_date": 1592805275.55762}'
jstr = '{"name":"jack", "info":{"level02": "true", "age":30}}'
o = json.loads(jstr, object_hook=dict_to_obj)
print(o.create_date)
print(type(o.create_date))
# 2020-06-22 13:54:35.557620
# <class 'datetime.datetime'>

class Person04:
    def __init__(self, name='', age=-1, pairs=None):
        self.name = name
        self.age = age
        if pairs:
            self.__dict__ = pairs

    def toJSON(self):
        return json.dumps(self,
                            default=lambda o: o.__dict__,
                            sort_keys=True,
                            indent=4)

import importlib
importlib.reload(PDFParser)

a = [1, 2, 3]
b = a

a == b # true
a is b # true

b = a[:]
a == b # true
a is b # false

class Person:
    def __init__(self, id, name):
        self.id = id
        self.name = name

    def __eq__(self, other):
        if not isinstance(other, Person):
            # don't attempt to compare against unrelated types
            return NotImplemented
        return self.id == other.id

p1 = Person(1, 'a')
p2 = Person(2, 'b')
p3 = Person(1, 'c')

p1 == p2 # false
p1 == p3 # true

class Person:
    def __init__(self, id, name):
        self.id = id
        self.name = name

    def __eq__(self, other):
        if not isinstance(other, Person):
            # don't attempt to compare against unrelated types
            return NotImplemented
        return self.id == other.id

    def __hash__(self):
        # necessary for instances to behave sanely in dicts and sets.
        return hash(self.id)

set([p1, p2, p3]) # only  p1, p2 will be stored

headers  = {'Authorization' : 'token xxx'}
url = 'https://github.domain.com/api/v3/users/ixxx'
resp = requests.get(url, headers=headers)

''' Error show as:
SSLError: HTTPSConnectionPool(host='github.wdf.sap.corp', port=443): Max retries exceeded with url: /api/v3/users/i332399 (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1076)')))

In [7]: resp = requests.get(url, headers=headers, verify=False)
/Users/i306454/gitStore/mycommands/.venv/lib/python3.7/site-packages/urllib3/connectionpool.py:851: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings
  InsecureRequestWarning)
'''