seozed

import unicodedata
s = 'T-shirt\xa0\xa0短袖圆领衫,\u3000体恤衫\xa0买一件\t吧'
unicodedata.normalize('NFKC', s)
# T-shirt  短袖圆领衫, 体恤衫 买一件 吧 

# 日常爬虫抓取数据中常遇到此类问题，使用率较高


    def unicode_normalize(unistr, form='NFKC'):
        """

seozed

from jsonpath import jsonpath as _jsonpath


def jsonpath(obj, expr):
  """
  优先项：如果匹配到的结果只有一个，则直接pop出该结果
  """
  
    result = _jsonpath(obj, expr)
    if isinstance(result, list) and len(result) == 1:

seozed

from w3lib.html import remove_tags, strip_html5_whitespace
# keep参数为需要保留的标签名称
remove_tags(text, keep=('img',)) 


# 移除HTML标签，并删除前后的空白字符
def clean_tags(text, which_ones=(), keep=(), encoding=None) -> str:
  if not text:
    return None
  content = remove_tags(text, which_ones, keep, encoding)

seozed

import pymysql.cursors

# Connect to the database
connection = pymysql.connect(host='localhost',
                             user='user',
                             password='passwd',
                             db='db',
                             charset='utf8mb4',
                             cursorclass=pymysql.cursors.DictCursor)

seozed

def chunked(iterable, n):
    from itertools import islice
    from functools import partial

    def take(n, iterable):
        return list(islice(iterable, n))

    return iter(partial(take, n, iter(iterable)), [])

seozed

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Threading.Tasks;
using System.Net;
using System.IO;

namespace ConsoleApp1
{

seozed

ALPHABET = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"


def base62_encode(num, alphabet=ALPHABET):
    """Encode a number in Base X

    `num`: The number to encode
    `alphabet`: The alphabet to use for encoding
    """
    if (num == 0):

seozed

"""
多进程示例
"""
import time
from multiprocessing import Pool


def run(fn):
    time.sleep(1)
    print(fn)

seozed

import concurrent.futures
import math

PRIMES = [
    112272535095293,
    112582705942171,
    112272535095293,
    115280095190773,
    115797848077099,
    1099726899285419]

seozed

import concurrent.futures
import urllib.request

URLS = ['http://www.163.com/',
        'http://www.qq.com/',
        'http://www.baidu.com/',
        'http://www.v2ex.com/',
        'http://www.360.com']