async def fetch(session,url, data):

    async with session.post(url=url, data=data, headers=headers) as response:

        return await response.json()

import aiohttp

import asyncio



page = 30



post_data = {

    'page': 1,

    'pageSize': 10,

    'keyWord': '',

    'dpIds': '',

}



headers = {

    

    "Accept-Encoding": "gzip, deflate",

    "Accept-Language": "en-US,en;q=0.9",

    "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.108 Safari/537.36",

    "X-Requested-With": "XMLHttpRequest",

}



result=





async def fetch(session,url, data):

    async with session.post(url=url, data=data, headers=headers) as response:

        return await response.json()



async def parse(html):

    xzcf_list = html.get('newtxzcfList')

    if xzcf_list is None:

        return

    for i in xzcf_list:

        result.append(i)



async def downlod(page):

    data=post_data.copy()

    data['page']=page

    url = 'http://credit.chaozhou.gov.cn/tfieldTypeActionJson!initXzcfListnew.do'

    async with aiohttp.ClientSession() as session:

            html=await fetch(session,url,data)

            await parse(html)



loop = asyncio.get_event_loop()

tasks=[asyncio.ensure_future(downlod(i)) for i in range(1,page)]

tasks=asyncio.gather(*tasks)

# print(tasks)

loop.run_until_complete(tasks)

# loop.close()

# print(result)

count=0

for i in result:

    print(i.get('cfXdrMc'))

    count+=1

print(f'total {count}')

import requests

from lxml import etree

import asyncio

import aiohttp

import pandas

import re

import math

import time



loction_info = '''    1→杭州

    2→武汉

    3→北京

    按ENTER确认：'''

loction_select = input(loction_info)

loction_dic = {'1': 'hz',

               '2': 'wh',

               '3': 'bj'}

city_url = 'https://{}.lianjia.com/ershoufang/'.format(loction_dic[loction_select])

down = input('请输入价格下限（万）:')

up = input('请输入价格上限（万）:')



inter_list = [(int(down), int(up))]





def half_inter(inter):

    lower = inter[0]

    upper = inter[1]

    delta = int((upper - lower) / 2)

    inter_list.remove(inter)

    print('已经缩小价格区间', inter)

    inter_list.append((lower, lower + delta))

    inter_list.append((lower + delta, upper))





pagenum = {}





def get_num(inter):

    url = city_url + 'bp{}ep{}/'.format(inter[0], inter[1])

    r = requests.get(url).text

    print(r)

    num = int(etree.HTML(r).xpath("//h2[@class='total fl']/span/text()")[0].strip())

    pagenum[(inter[0], inter[1])] = num

    return num





totalnum = get_num(inter_list[0])



judge = True

while judge:

    a = [get_num(x) > 3000 for x in inter_list]

    if True in a:

        judge = True

    else:

        judge = False

    for i in inter_list:

        if get_num(i) > 3000:

            half_inter(i)

print('价格区间缩小完毕！')



url_lst = []

url_lst_failed = []

url_lst_successed = []

url_lst_duplicated = []



for i in inter_list:

    totalpage = math.ceil(pagenum[i] / 30)

    for j in range(1, totalpage + 1):

        url = city_url + 'pg{}bp{}ep{}/'.format(j, i[0], i[1])

        url_lst.append(url)

print('url列表获取完毕！')



info_lst = []





async def get_info(url):

    async with aiohttp.ClientSession() as session:

        async with session.get(url, timeout=5) as resp:

            if resp.status != 200:

                url_lst_failed.append(url)

            else:

                url_lst_successed.append(url)

            r = await resp.text()

            nodelist = etree.HTML(r).xpath("//ul[@class='sellListContent']/li")

            # print('-------------------------------------------------------------')

            # print('开始抓取第{}个页面的数据,共计{}个页面'.format(url_lst.index(url),len(url_lst)))

            # print('开始抓取第{}个页面的数据,共计{}个页面'.format(url_lst.index(url), len(url_lst)))

            # print('开始抓取第{}个页面的数据,共计{}个页面'.format(url_lst.index(url), len(url_lst)))

            # print('-------------------------------------------------------------')

            info_dic = {}

            index = 1

            print('开始抓取{}'.format(resp.url))

            print('开始抓取{}'.format(resp.url))

            print('开始抓取{}'.format(resp.url))

            for node in nodelist:

                try:

                    info_dic['title'] = node.xpath(".//div[@class='title']/a/text()")[0]

                except:

                    info_dic['title'] = '/'

                try:

                    info_dic['href'] = node.xpath(".//div[@class='title']/a/@href")[0]

                except:

                    info_dic['href'] = '/'

                try:

                    info_dic['xiaoqu'] = \

                    node.xpath(".//div[@class='houseInfo']")[0].xpath('string(.)').replace(' ', '').split('|')[0]

                except:

                    info_dic['xiaoqu'] = '/'

                try:

                    info_dic['huxing'] = \

                    node.xpath(".//div[@class='houseInfo']")[0].xpath('string(.)').replace(' ', '').split('|')[1]

                except:

                    info_dic['huxing'] = '/'

                try:

                    info_dic['area'] = \

                    node.xpath(".//div[@class='houseInfo']")[0].xpath('string(.)').replace(' ', '').split('|')[2]

                except:

                    info_dic['area'] = '/'

                try:

                    info_dic['chaoxiang'] = \

                    node.xpath(".//div[@class='houseInfo']")[0].xpath('string(.)').replace(' ', '').split('|')[3]

                except:

                    info_dic['chaoxiang'] = '/'

                try:

                    info_dic['zhuangxiu'] = \

                    node.xpath(".//div[@class='houseInfo']")[0].xpath('string(.)').replace(' ', '').split('|')[4]

                except:

                    info_dic['zhuangxiu'] = '/'

                try:

                    info_dic['dianti'] = \

                    node.xpath(".//div[@class='houseInfo']")[0].xpath('string(.)').replace(' ', '').split('|')[5]

                except:

                    info_dic['dianti'] = '/'

                try:

                    info_dic['louceng'] = re.findall('\((.*)\)', node.xpath(".//div[@class='positionInfo']/text()")[0])

                except:

                    info_dic['louceng'] = '/'

                try:

                    info_dic['nianxian'] = re.findall('\)(.*?)年', node.xpath(".//div[@class='positionInfo']/text()")[0])

                except:

                    info_dic['nianxian'] = '/'

                try:

                    info_dic['guanzhu'] = ''.join(re.findall('[0-9]', node.xpath(".//div[@class='followInfo']/text()")[

                        0].replace(' ', '').split('/')[0]))

                except:

                    info_dic['guanzhu'] = '/'

                try:

                    info_dic['daikan'] = ''.join(re.findall('[0-9]',

                                                            node.xpath(".//div[@class='followInfo']/text()")[0].replace(

                                                                ' ', '').split('/')[1]))

                except:

                    info_dic['daikan'] = '/'

                try:

                    info_dic['fabu'] = node.xpath(".//div[@class='followInfo']/text()")[0].replace(' ', '').split('/')[

                        2]

                except:

                    info_dic['fabu'] = '/'

                try:

                    info_dic['totalprice'] = node.xpath(".//div[@class='totalPrice']/span/text()")[0]

                except:

                    info_dic['totalprice'] = '/'

                try:

                    info_dic['unitprice'] = node.xpath(".//div[@class='unitPrice']/span/text()")[0].replace('单价', '')

                except:

                    info_dic['unitprice'] = '/'

                if True in [info_dic['href'] in dic.values() for dic in info_lst]:

                    url_lst_duplicated.append(info_dic)

                else:

                    info_lst.append(info_dic)

                print('第{}条:    {}→房屋信息抓取完毕！'.format(index, info_dic['title']))

                index += 1

                info_dic = {}





start = time.time()



# 首次抓取url_lst中的信息，部分url没有对其发起请求，不知道为什么

tasks = [asyncio.ensure_future(get_info(url)) for url in url_lst]

loop = asyncio.get_event_loop()

loop.run_until_complete(asyncio.wait(tasks))



# 将没有发起请求的url放入一个列表，对其进行循环抓取，直到所有url都被发起请求

url_lst_unrequested = []

for url in url_lst:

    if url not in url_lst_successed or url_lst_failed:

        url_lst_unrequested.append(url)

while len(url_lst_unrequested) > 0:

    tasks_unrequested = [asyncio.ensure_future(get_info(url)) for url in url_lst_unrequested]

    loop.run_until_complete(asyncio.wait(tasks_unrequested))

    url_lst_unrequested = []

    for url in url_lst:

        if url not in url_lst_successed:

            url_lst_unrequested.append(url)

end = time.time()

print('当前价格区间段内共有{}套二手房源\(包含{}条重复房源\),实际获得{}条房源信息。'.format(totalnum, len(url_lst_duplicated), len(info_lst)))

print('总共耗时{}秒'.format(end - start))



df = pandas.DataFrame(info_lst)

df.to_csv("ljwh.csv", encoding='gbk')

import matplotlib.pyplot as plt

import numpy as np

import time

from collections import OrderedDict



def softmax(a):

    a = a - np.max(a)

    exp_a = np.exp(a)

    exp_a_sum = np.sum(exp_a)

    return exp_a / exp_a_sum





def cross_entropy_error(t, y):

    delta = 1e-7

    s = -1 * np.sum(t * np.log(y + delta))

    #     print('cross entropy ',s)

    return s





class simpleNet:

    def __init__(self):

        self.W = np.random.randn(2, 3)



    def predict(self, x):

        print('current w',self.W)

        return np.dot(x, self.W)



    def loss(self, x, t):

        z = self.predict(x)

        #         print(z)

        #         print(z.ndim)

        y = softmax(z)

        #         print('y',y)

        loss = cross_entropy_error(y, t)  # y为预测的值

        return loss







def numerical_gradient_(f, x):  # 针对2维的情况 甚至是多维

    h = 1e-4  # 0.0001

    grad = np.zeros_like(x)



    it = np.nditer(x, flags=['multi_index'], op_flags=['readwrite'])

    while not it.finished:

        idx = it.multi_index

        print('idx', idx)

        tmp_val = x[idx]

        x[idx] = float(tmp_val) + h

        fxh1 = f(x)  # f(x+h)

        print('fxh1 ', fxh1)

        # print('current W', net.W)

        x[idx] = tmp_val - h

        fxh2 = f(x)  # f(x-h)

        print('fxh2 ', fxh2)

        # print('next currnet W ', net.W)

        grad[idx] = (fxh1 - fxh2) / (2 * h)



        x[idx] = tmp_val  # 还原值

        it.iternext()



    return grad







net = simpleNet()

x=np.array([0.6,0.9])

t = np.array([0.0,0.0,1.0])



def f(W):

    return net.loss(x,t)



grads =numerical_gradient_(f,net.W)

print(grads)

MTW881U3Z5-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-aKyalfjUfiV5UXfhaMGgOqrMzTYy2rnsmobL47k8tTpR/jvG6HeL3FxxleetI+W+Anw3ZSe8QAMsSxqVS4podwlQgIe7f+3w7zyAT1j8HMVlfl2h96KzygdGpDSbwTbwOkJ6/5TQOPgAP86mkaSiM97KgvkZV/2nXQHRz1yhm+MT+OsioTwxDhd/22sSGq6KuIztZ03UvSciEmyrPdl2ueJw1WuT9YmFjdtTm9G7LuXvCM6eav+BgCRm+wwtUeDfoQqigbp0t6FQgkdQrcjoWvLSB0IUgp/f4qGf254fA7lXskT2VCFdDvi0jgxLyMVct1cKnPdM6fkHnbdSXKYDWw==-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

x=np.array([[1,2,3,4],[5,6,7,8]])

array([[1, 2, 3, 4],

       [5, 6, 7, 8]])

x.flatten()

array([1, 2, 3, 4, 5, 6, 7, 8])

def function_2(x):

    return x[0]**2+x[1]**2

def numerical_gradient(f,x):

    grad = np.zeros_like(x)

    h=1e-4

    for idx in range(x.size):

        temp_v = x[idx]

        x[idx]=temp_v+h

        f1=f(x)

        print(x,f1)

        x[idx]=temp_v-h

        f2=f(x)

        print(x,f2)

        ret = (f1-f2)/(2*h)

        print(ret)

        x[idx]=temp_v

        grad[idx]=ret

        

    return grad

numerical_gradient(function_2,np.array([3,4]))

a=np.array([[[1,2],[3,4]],[[11,12],[13,14]]])

array([[[ 1,  2],

        [ 3,  4]],



       [[11, 12],

        [13, 14]]])

a.sum(axis=0)

array([[12, 14],

       [16, 18]])

a.sum(axis=1)

array([[ 4,  6],

       [24, 26]])

a.sum(axis=-3)

array([[12, 14],

       [16, 18]])

n1=np.array([0,1,0,0,0,0,1,0,0,0,0,0,0,1])

n1.nonzero()

(array([ 1,  6, 13], dtype=int64),)

np.array([1,2,3,4])

{	"size":0,

	"aggs":

	{

		"color":

		{

		"terms":{

			"field":"color"

		}

		}

	}

}

curl -X POST "10.18.6.102:9200/cars/transactions/_bulk" -H 'Content-Type: application/json' -d'

{ "index": {}}

{ "price" : 10000, "color" : "red", "make" : "honda", "sold" : "2014-10-28" }

{ "index": {}}

{ "price" : 20000, "color" : "red", "make" : "honda", "sold" : "2014-11-05" }

{ "index": {}}

{ "price" : 30000, "color" : "green", "make" : "ford", "sold" : "2014-05-18" }

{ "index": {}}

{ "price" : 15000, "color" : "blue", "make" : "toyota", "sold" : "2014-07-02" }

{ "index": {}}

{ "price" : 12000, "color" : "green", "make" : "toyota", "sold" : "2014-08-19" }

{ "index": {}}

{ "price" : 20000, "color" : "red", "make" : "honda", "sold" : "2014-11-05" }

{ "index": {}}

{ "price" : 80000, "color" : "red", "make" : "bmw", "sold" : "2014-01-01" }

{ "index": {}}

{ "price" : 25000, "color" : "blue", "make" : "ford", "sold" : "2014-02-12" }

'

PUT my_index/_mapping/_doc

{

  "properties": {

    "my_field": { 

      "type":     "text",

      "fielddata": true

    }

  }

}

ps -ef | grep "进程名" | grep -v grep | cut -c 10-16 | xargs kill -9

class First(object):

    def __init__(self):

        print("first")



class Second(First):

    def __init__(self):

        print("second")



class Third(First,Second):

    def __init__(self):

        print("third")

---------------------------------------------------------------------------

TypeError                                 Traceback (most recent call last)

<ipython-input-6-c90f7b77d3e0> in <module>()

      7         print("second")

      8 

----> 9 class Third(First,Second):

     10     def __init__(self):

     11         print("third")



TypeError: Cannot create a consistent method resolution order (MRO) for bases First, Second

import time

import gevent

import requests

def foo():

    print('Running in foo')



    r=requests.get('http://30daydo.com')

    print(r.status_code)

    print('Explicit context switch to foo again')



def bar():

    print('Explicit context to bar')



    r=requests.get('http://www.qq.com') # 

    print(r.status_code)

    print('Implicit context switch back to bar')



start=time.time()

gevent.joinall([

    gevent.spawn(foo),

    gevent.spawn(bar),

])

print('time used {}'.format(time.time()-start))

import time

import gevent

import requests

def foo():

    print('Running in foo')

    time.sleep(2) # 这样子不起作用

    print('Explicit context switch to foo again')



def bar():

    print('Explicit context to bar')

    time.sleep(2)

    print('Implicit context switch back to bar')



start=time.time()

gevent.joinall([

    gevent.spawn(foo),

    gevent.spawn(bar),

])

print('time used {}'.format(time.time()-start))

import time

import gevent

import requests

def foo():

    print('Running in foo')



    gevent.sleep(2) # 通过它各自yield向对方



    print('Explicit context switch to foo again')



def bar():

    print('Explicit context to bar')



    gevent.sleep(2)



    print('Implicit context switch back to bar')



start=time.time()

gevent.joinall([

    gevent.spawn(foo),

    gevent.spawn(bar),

])

print('time used {}'.format(time.time()-start))

最流行的版本控制软件：git

========================



git已经是当前最流行的版本控制软件之一了。全世界的程序员都在使用它。它出自linus大神之手，现在被用于内

核的版本控制。在最流行的代码托管软件github，你几乎可以找到所有开源项目的代码。



版块控制软件：我需要吗？

-----------------------



的确对于许多人——尤其是非程序员，他们可能不会想到已经出现了专门的版本控制的软件。但其实多人对版本控

制其实都有类似的需求，举个例子，Tom是社团的秘书处成员，他们经常需要做的事情就是写活动文档，然后不停地

改改到大家都觉得可以了。



不幸运的话，Tom可能有个文件夹叫“openSUSE活动策划"，里面有这样的一堆文件”openSUSE活动策划", "活动策

划1", "活动策划2", "活动策划3", "活动策划4" ... "活动策划20" （可怜的Tom，一份文档改了不少于20次）



这种作法很有效，因为我们可能发现第5个版本的策划有问题，我们准备在第3个版本上面重新来过。但是也看到，

这个作法有些很丑陋的地方：一份文件，我们留了20个备份，而且还要注意文件名。



如果可以这样就好了：文件夹上只有一个“openSUSE活动策划"，但当我需要第5个版本的时候，我来一个”给我还

原到第5个版本吧！“，然后这时候我们打开这个文件，它就是第5个版本的了。类似的，我们可以取出任意的版本

。



这就是版本控制。这种事情在程序里面发生的太多了，于是出现了各种版本控制软件。事实上，有些项目已经发展

到第1000+甚至更高的版本数了……



单线的工作流

------------



我们可以把我们的一个项目想象为一个仓库，然后我们可以把我们的东西塞进仓库里面，也可以把想要的东西拿出

来。而git则是仓库的管理员。下面是一个例子，希望有一个直观的印象，不求完全的理解和掌握。



```bash

mkdir myproject // 假设myproject是工作目录

cd myproject    

git init        // git <- (init) ，告诉仓库管理员，在当前目录初始化

echo 'Eat the banana' > file   // 编辑了一个文件

git add file                   // 加入仓库

git commit -m 'add first file' // 提交更改

echo 'Eat the apply' > file    // 修改了这个文件

git add file                   // 加入仓库

git commit -m 'update first file' // 再提交更改

```



这时候我们就有两个commit了，我们来看看工作日志：



```bash

git log



# 以下是输出

# commit ac1371173b4e630ddaebda3f9f5d948b36146c07

# Author: Norman Mo <LTaoist@@@>

# Date:   Thu Jun 27 21:59:10 2013 +0800

#

#     update first file

#

# commit 3c43cc913454f92bb4b80c56ba45e4ffaf556fc0

# Author: Norman Mo <LTaoist6@@@@>

# Date:   Thu Jun 27 21:58:48 2013 +0800

#

#     add first file

```



看到了，我们提交了两次。我们来看看现在file里面是什么：



```bash

cat file # 显然输出是 'Eat the apply'

# 现在，我们来拿回第一个版本的file文件

git checkout 3c43cc913454f92bb4b80c56ba45e4ffaf556fc0 -- file

cat file # 这时候就是eat banana了

```



这种工作的方式是单人使用最常见的方式，写一点代码，提交一下到仓库里面。写一点，提交到仓库里面。然后出

问题的时候就回退过去。git非常强大，基本上你想到的他都可以做到，提交到仓库的数据基本不会丢失，像时间机

器一样控制着代码。



多人协作

--------



git非常强大，上面只是一个功能。考虑Tom的秘书处有两个人，他们在同时写。其中Tom写前6章，他的同伴写第7～

12章。



这时候可以考虑用这种工作的方式：设立一个公共的仓库。Tom维护自己的版本，他的同伴维护自己的版本。然后大

家定期把代码合并到公共仓库上面，然后定期把新的版本取回来合并再提交到公共仓库。



如果他们用纯文本，得益于一些文本分析的方法，几乎不需要校对就可以做到。



```

git commit -m 'finish ch5' // 假设此时Tom写完了第5章

git push // Tom将代码推送到远程仓库

```



```

git commit -m 'finish ch11' // 假设此时Tom的同伴完成了第11章

git pull // pull会将最新版本拉下来，合并，然后推送到远程仓库

```



实际上工作中，为了不混淆，会新开一个分支来开发新的特性，然后对分支进行合并。



代码自动发布

-----------



另一个很强大的功能是可以实现代码的自动发布。事实上，很多云就有使用这个。具体来说，利用git的hooks，当

服务器收到一个push，服务器可以自动运行一些脚本。也可以在客户端使用hooks，当客户端准备push的时候，客户

端先运行一些脚本。



例如，我们希望在每次服务器收到push以后，杀死全部的 `p` 进程，然后重开 `p` 进程。我们可以修改 `hooks/

post-receive` :



```

echo "Killing all p process..."

killall -9 p

echo "Restart p process..."

p

```



更多更多更多……

---------------



这份教程就到这里了，更多的自己马上动手去试试吧！



在openSUSE的安装方法：



```

sudo zypper in git

```



默认应该就装了。



一般linux命令查看帮助都是 `--help` 选项：



```

git --help

```



此外，对一个子命令也是有help看的：



```

git init --help

```



这里有一个交互教程，在浏览器上面跑的模拟git的运行的，有兴趣的试试：



<http://try.github.io/>



github的help文档写得很不错，推荐一下：



<https://help.github.com/>



书籍有个远近闻名的《Pro Git》，而且有中文版的，虽然我认为这本书太厚了。。。但似乎就这么一本书……



<http://git-scm.com/book/zh>



国内有个gitcafe，也是做git托管的，他们也有整理一份help：



<https://gitcafe.com/GitCafe/Help>



记得，上面只是一个演示，多试试push，多尝试。有一天你会喜欢用这个有效的工具的。



很有用！！！

127.0.0.1 qq.com

127.0.0.1 cnbeta.com

10.4.16.75 windows10.microdone.cn

50.112.79.106 mukodik

0.0.0.0 account.jetbrains.com

./kafka-server-start.sh -daemon ../config/server.properties

systemctl stop firewalld.service #关闭防火墙

systemctl disable firewalld.service #禁止启动防火墙

C:\ProgramData\Anaconda3\python.exe C:/git/base_function/kafka_usage.py

Traceback (most recent call last):

  File "C:/git/base_function/kafka_usage.py", line 6, in <module>

    from kafka import KafkaProducer

  File "C:\ProgramData\Anaconda3\lib\site-packages\kafka\__init__.py", line 23, in <module>

    from kafka.producer import KafkaProducer

  File "C:\ProgramData\Anaconda3\lib\site-packages\kafka\producer\__init__.py", line 4, in <module>

    from .simple import SimpleProducer

  File "C:\ProgramData\Anaconda3\lib\site-packages\kafka\producer\simple.py", line 54

    return '<SimpleProducer batch=%s>' % self.async

                                                  ^

SyntaxError: invalid syntax

line=Line()

line.add('可转债个数趋势',b,v,mark_line=["average"], mark_point=["max", "min"])

<class 'pandas.core.frame.DataFrame'>

RangeIndex: 307 entries, 0 to 306

Data columns (total 7 columns):

日期         307 non-null datetime64[ns]

指数         307 non-null float64

成交额(亿元)    307 non-null float64

涨跌         307 non-null float64

涨跌额        307 non-null float64

转债数目       307 non-null float64

剩余规模       307 non-null float64

dtypes: datetime64[ns](1), float64(6)

memory usage: 16.9 KB

[numpy.datetime64('2017-12-29T00:00:00.000000000'),

 numpy.datetime64('2018-01-02T00:00:00.000000000'),

 numpy.datetime64('2018-01-03T00:00:00.000000000'),

 numpy.datetime64('2018-01-04T00:00:00.000000000'),

 numpy.datetime64('2018-01-05T00:00:00.000000000'),

 numpy.datetime64('2018-01-08T00:00:00.000000000'),

 numpy.datetime64('2018-01-09T00:00:00.000000000'),

 numpy.datetime64('2018-01-10T00:00:00.000000000'),

 numpy.datetime64('2018-01-11T00:00:00.000000000'),

 numpy.datetime64('2018-01-12T00:00:00.000000000'),

 numpy.datetime64('2018-01-15T00:00:00.000000000'),

 numpy.datetime64('2018-01-16T00:00:00.000000000'),

 numpy.datetime64('2018-01-17T00:00:00.000000000'),

b=list(df['日期'].dt.to_pydatetime())

[datetime.datetime(2017, 12, 29, 0, 0),

 datetime.datetime(2018, 1, 2, 0, 0),

 datetime.datetime(2018, 1, 3, 0, 0),

 datetime.datetime(2018, 1, 4, 0, 0),

 datetime.datetime(2018, 1, 5, 0, 0),

 datetime.datetime(2018, 1, 8, 0, 0),

 datetime.datetime(2018, 1, 9, 0, 0),

 datetime.datetime(2018, 1, 10, 0, 0),

 datetime.datetime(2018, 1, 11, 0, 0),

 datetime.datetime(2018, 1, 12, 0, 0),

 datetime.datetime(2018, 1, 15, 0, 0)

['2017-12-29',

 '2018-01-02',

 '2018-01-03',

 '2018-01-04',

 '2018-01-05',

 '2018-01-08',

 '2018-01-09',

 '2018-01-10',

 '2018-01-11',

 '2018-01-12',

 '2018-01-15',

 '2018-01-16',

 '2018-01-17',]

timestamp转换为datetime

要把timestamp转换为datetime，使用datetime提供的fromtimestamp()方法：



>>> from datetime import datetime

>>> t = 1429417200.0

>>> print(datetime.fromtimestamp(t))

2015-04-19 12:20:00

注意到timestamp是一个浮点数，它没有时区的概念，而datetime是有时区的。上述转换是在timestamp和本地时间做转换。



本地时间是指当前操作系统设定的时区。例如北京时区是东8区，则本地时间：



2015-04-19 12:20:00

实际上就是UTC+8:00时区的时间：



2015-04-19 12:20:00 UTC+8:00

而此刻的格林威治标准时间与北京时间差了8小时，也就是UTC+0:00时区的时间应该是：



2015-04-19 04:20:00 UTC+0:00

timestamp也可以直接被转换到UTC标准时区的时间：



>>> from datetime import datetime

>>> t = 1429417200.0

>>> print(datetime.fromtimestamp(t)) # 本地时间

2015-04-19 12:20:00

>>> print(datetime.utcfromtimestamp(t)) # UTC时间

2015-04-19 04:20:00

db.collection.findOneAndUpdate(

   <filter>,

   <update>,

   {

     projection: <document>,

     sort: <document>,

     maxTimeMS: <number>,

     upsert: <boolean>,

     returnNewDocument: <boolean>,

     collation: <document>,

     arrayFilters: [ <filterdocument1>, ... ]

   }

)

>>> db.example.find_one_and_update(

...     {'_id': 'userid'},

...     {'$inc': {'seq': 1}},

...     projection={'seq': True, '_id': False},

...     return_document=ReturnDocument.AFTER)

# Redis集群地址

REDIS_MASTER_NODES = [

    {"host": "192.168.10.233", "port": "30001"},

    {"host": "192.168.10.234", "port": "30002"},

    {"host": "192.168.10.235", "port": "30003"},

]



# 使用的哈希函数数，默认为6  

BLOOMFILTER_HASH_NUMBER = 6



# Bloomfilter使用的Redis内存位，30表示2 ^ 30 = 128MB，默认为22 (1MB 可去重130W URL)  

BLOOMFILTER_BIT = 22



# 不清空redis队列  

SCHEDULER_PERSIST = True  

# 调度队列  

SCHEDULER = "scrapy_redis_cluster.scheduler.Scheduler"  

# 去重 

DUPEFILTER_CLASS = "scrapy_redis_cluster.dupefilter.RFPDupeFilter"  

# queue  

SCHEDULER_QUEUE_CLASS = 'scrapy_redis_cluster.queue.PriorityQueue'

df

       A  B  C  D  E

    0  5  0  3  3  7

    1  9  3  5  2  4

    2  7  6  8  8  1

      A  B  C  D  E

0     5  0  3  3  7

1  1000  3  5  2  4

2  1000  6  8  8  1