import jieba.posseg as pseg

seg_list = pseg.cut("我爱北京天安门")

for word,flag in seg_list:

    print(word)

    print(flag)

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

TypeError                                 Traceback (most recent call last)

<ipython-input-5-f105f6980f88> in <module>()

      1 import jieba.posseg as pseg

      2 seg_list = pseg.cut("我爱北京天安门")

----> 3 for word,flag in seg_list:

      4     print(word)

      5     print(flag)



TypeError: cannot unpack non-iterable pair object

原因是新版本中seg_list是一个生成器，所以只能 for win seg_list

然后从word中解包出来

print(w.word)

print(w.flag)

这样问题就解决了。

from lxml.html import etree

from lxml.html import fromstring, HtmlElement



test_html = '''<p><span>hello</span><span>world</span></p>'''

test_element = fromstring(test_html)

etree.strip_tags(test_element,'span') # 清除span标签

etree.tostring(test_element)

url = 'http://xyhz.huizhou.gov.cn/static/js/common/jigsaw/images/{}.jpg'

headers={'User-Agent':'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'}

async def getPage(num):



    async with aiohttp.ClientSession() as session:

        async with session.get(url.format(num),headers=headers) as resp:

            if resp.status==200:

                f= await aiofiles.open('{}.jpg'.format(num),mode='wb')

                await f.write(await resp.read())

                await f.close()



loop = asyncio.get_event_loop()

tasks = [getPage(i) for i in range(5)]

loop.run_until_complete(asyncio.wait(tasks))

# -*-coding=utf-8-*-



# @Time : 2019/9/9 9:25

# @File : mail_backup.py

# @Author : 

import codecs

import re

import config

import os

from exchangelib import DELEGATE, Account, Credentials, Configuration, NTLM, Message, Mailbox, HTMLBody,FileAttachment,ItemAttachment

from exchangelib.protocol import BaseProtocol, NoVerifyHTTPAdapter





#此句用来消除ssl证书错误，exchange使用自签证书需加上

BaseProtocol.HTTP_ADAPTER_CLS = NoVerifyHTTPAdapter





# 输入你的域账号如example\xxx

cred = Credentials(r'example\xxx', 你的邮箱密码)



configx = Configuration(server='mail.credlink.com', credentials=cred, auth_type=NTLM)

a = Account(

    primary_smtp_address='你的邮箱地址', config=configx, autodiscover=False, access_type=DELEGATE

)





for item in a.inbox.all().order_by('-datetime_received')[:100]:

    print(item.subject, item.sender, item.unique_body,item.datetime_received)

   

    name = item.subject

    name = re.sub('[\/:*?"<>|]', '-', name)

    local_path = os.path.join('inbox', name+'.html')

    with codecs.open(local_path, 'w','utf-8') as f:

        f.write(item.unique_body)



    for attachment in item.attachments:

        if isinstance(attachment, FileAttachment):

            name = attachment.name

            name = re.sub('[\/:*?"<>|]','-',name)

            local_path = os.path.join('inbox', attachment.name)

            with codecs.open(local_path, 'wb') as f:

                f.write(attachment.content)

            print('Saved attachment to', local_path)



        elif isinstance(attachment, ItemAttachment):

            if isinstance(attachment.item, Message):

                name=attachment.item.subject

                name = re.sub('[\/:*?"<>|]', '-', name)

                local_path = os.path.join('inbox', 'attachment')

                with codecs.open(local_path, 'w') as f:

                    f.write(attachment.item.body)

import time



LOOP = 2*10**8



def add(x,y):

    return x+y



def cpu_pressure(loop):

    

    for i in range(loop):

        result = add(i,i+1)





if __name__ == '__main__':

    start = time.time()

    cpu_pressure(LOOP)

    print(f'time used {time.time()-start}s')

class Command(ScrapyCommand):



    requires_project = True



    def syntax(self):

        return '[options]'



    def short_desc(self):

        return 'Runs all of the spiders - My Defined'



    def run(self,args,opts):

        print('==================')

        print(type(self.crawler_process))

        spider_list = self.crawler_process.spiders.list() # 找到爬虫类



        for name in spider_list:

            print('=================')

            print(name)

            self.crawler_process.crawl(name,**opts.__dict__)



        self.crawler_process.start()

      def __init__(self, settings=None):

        if isinstance(settings, dict) or settings is None:

            settings = Settings(settings)

        self.settings = settings

        self.spider_loader = _get_spider_loader(settings) # 构造爬虫

        self._crawlers = set()

        self._active = set()

        self.bootstrap_failed = False

def _get_spider_loader(settings):



    cls_path = settings.get('SPIDER_LOADER_CLASS')

    

    # settings文件没有定义SPIDER_LOADER_CLASS，所以这里获取到的是系统的默认配置文件，

    # 默认配置文件在接下来的代码块A

    # SPIDER_LOADER_CLASS = 'scrapy.spiderloader.SpiderLoader'    

    

    loader_cls = load_object(cls_path) 

    # 这个函数就是根据路径转为类对象，也就是上面crapy.spiderloader.SpiderLoader 这个

    # 字符串变成一个类对象

    # 具体的load_object 对象代码见下面代码块B



    return loader_cls.from_settings(settings.frozencopy())

# 代码块A

#......省略若干

SCHEDULER = 'scrapy.core.scheduler.Scheduler'

SCHEDULER_DISK_QUEUE = 'scrapy.squeues.PickleLifoDiskQueue'

SCHEDULER_MEMORY_QUEUE = 'scrapy.squeues.LifoMemoryQueue'

SCHEDULER_PRIORITY_QUEUE = 'scrapy.pqueues.ScrapyPriorityQueue'



SPIDER_LOADER_CLASS = 'scrapy.spiderloader.SpiderLoader' 就是这个值

SPIDER_LOADER_WARN_ONLY = False



SPIDER_MIDDLEWARES = {}

# 代码块B 为了方便，我把异常处理的去除

from importlib import import_module #导入第三方库



def load_object(path):

    dot = path.rindex('.') 

    module, name = path[:dot], path[dot+1:]

    # 上面把路径分为基本路径+模块名

    

    mod = import_module(module)

    obj = getattr(mod, name)

    # 获取模块里面那个值

    

    return obj

In [33]: mod = import_module(module)                                                                                                                                             



In [34]: mod                                                                                                                                                                     

Out[34]: <module 'scrapy.spiderloader' from '/home/xda/anaconda3/lib/python3.7/site-packages/scrapy/spiderloader.py'>



In [35]: getattr(mod,name)                                                                                                                                                       

Out[35]: scrapy.spiderloader.SpiderLoader



In [36]: obj = getattr(mod,name)                                                                                                                                                 



In [37]: obj                                                                                                                                                                     

Out[37]: scrapy.spiderloader.SpiderLoader



In [38]: type(obj)                                                                                                                                                               

Out[38]: type

    def from_settings(cls, settings):

        return cls(settings)

class SpiderLoader(object):

    """

    SpiderLoader is a class which locates and loads spiders

    in a Scrapy project.

    """

    def __init__(self, settings):

        self.spider_modules = settings.getlist('SPIDER_MODULES') 

        # 获得settting中的模块名字，创建scrapy的时候就默认帮你生成了

        # 你可以看看你的settings文件里面的内容就可以找到这个值，是一个list

        

        self.warn_only = settings.getbool('SPIDER_LOADER_WARN_ONLY')

        self._spiders = {}

        self._found = defaultdict(list)

        self._load_all_spiders() # 加载所有爬虫

def _load_all_spiders(self):

        for name in self.spider_modules:            



                for module in walk_modules(name): # 这个遍历文件夹里面的文件，然后再转化为类对象，

                    # 保存到字典：self._spiders = {}       

                    self._load_spiders(module) # 模块变成spider



        self._check_name_duplicates() # 去重，如果名字一样就异常

def iter_spider_classes(module):

    from scrapy.spiders import Spider



    for obj in six.itervalues(vars(module)): # 找到模块里面的变量，然后迭代出来

        if inspect.isclass(obj) and \

           issubclass(obj, Spider) and \

           obj.__module__ == module.__name__ and \

           getattr(obj, 'name', None): # 有name属性，继承于Spider

           yield obj

* * * * * export DISPLAY=:0; gedit

import pyautogui as pag

import datetime



def neck_rest():

    f = open('neck_record.txt', 'a')

    ret = pag.prompt("Rest! Protect your neck !")

    if ret == 'rest':

        f.write(datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"))

        f.write('\t')

        f.write('Rest')

        f.write('\n')

    else:

        f.write(datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"))

        f.write('\t')

        f.write('Failed to rest')

        f.write('\n')

    f.close()



neck_rest()

redis://[:password]@localhost:6379/0

rediss://[:password]@localhost:6379/0

unix://[:password]@/path/to/socket.sock?db=0

db.test_tab.insert({array:[]})

db.test_tab.insert({array:[]})

db.test_tab.insert({array:[]})

db.test_tab.insert({array:[1,2,3,4,5]})

db.test_tab.insert({array:[1,2,3,4,5,6]})

db.getCollection("example").find({array:{$exists:true,$ne:[]}}); # 字段不为0

    from . import (constants, error, message, context,

ImportError: DLL load failed: 找不到指定的模块。

 # helper

    class RedisHelp(object):



        def __init__(self,channel):

            # self.pool = redis.ConnectionPool('10.18.6.46',port=6379)



            # self.conn = redis.Redis(connection_pool=self.pool)

            # 上面的方式无法使用订阅者 发布者模式



            self.conn = redis.Redis(host='10.18.6.46')

            self.publish_channel = channel

            self.subscribe_channel = channel





        def publish(self,msg):

            self.conn.publish(self.publish_channel,msg) # 1. 渠道名 ,2 信息



        def subscribe(self):

            self.pub = self.conn.pubsub()

            self.pub.subscribe(self.subscribe_channel)

            self.pub.parse_response()

            print('initial')

            return self.pub





    helper = RedisHelp('cuiqingcai')



    # 订阅者

    if sys.argv[1]=='s':

        print('in subscribe mode')

        pub = helper.subscribe()

        while 1:

            print('waiting for publish')

            pubsub.check_health()

            msg = pub.parse_response()



            s=str(msg[2],encoding='utf-8')

            print(s)

            if s=='exit':

                break





    # 发布者

    elif sys.argv[1]=='p':

        print('in publish mode')

        msg = sys.argv[2]

        print(f'msg -> {msg}')

        helper.publish(msg)

db.test.update({},{$rename:{'旧字段':'新字段'}},true,true)

db.getCollection('example').update({},{$rename:{'corp':'企业'}})

db.getCollection('example').update({},{$rename:{'corp.address':'corp.地址'}})

from random import randint



randint(0,1)

Out[25]: 1



randint(0,1)

Out[26]: 1



randint(0,1)

Out[27]: 1



randint(0,1)

Out[28]: 1



randint(0,1)

Out[29]: 0



randint(0,1)

Out[30]: 1

     file='test.txt'

     cmd = f'rsync -av  {file} root@10.18.6.46:/home/cjw/'



      p = subprocess.Popen(cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE,executable="/bin/bash")

      output, error = p.communicate()

      if p.returncode != 0:

          print("Error while running - %s" % cmd)

          print(error)

      print(output)

 p0 = multiprocessing.Process(name=str(0), target=foo, args=(0,))

    p0.start()

    p1 = multiprocessing.Process(name=str(1), target=foo, args=(1,))

    p1.start()

    p2 = multiprocessing.Process(name=str(2), target=foo, args=(2,))

    p2.start()

    p3 = multiprocessing.Process(name=str(3), target=foo, args=(3,))

    p3.start()

    p4 = multiprocessing.Process(name=str(4), target=foo, args=(4,))

    p4.start()



    p5 = multiprocessing.Process(name=str(5), target=foo, args=(5,))

    p5.start()

    

    p0.join()

    p1.join()

    p2.join()

    p3.join()

    p4.join()

    p5.join()