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

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 urllib.parse as urlparse
def get_url_param(url: str, param: str) -> str:
    url_parse = urlparse.urlparse(url)
    url_dict = dict(urlparse.parse_qsl(url_parse.query))
    return url_dict.get(param)

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

import csv

# 字典列表
result_list = []
with open('weibo_data.csv', 'w', newline='', encoding='gbk') as csv_file:
    # header field
    fieldnames = result_list[0].keys()
    writer = csv.DictWriter(csv_file, fieldnames=fieldnames)
    writer.writeheader()
    writer.writerows(result_list)

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

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']

seozed

from PyQt5 import QtCore, QtGui, QtWidgets
from PyQt5.QtWidgets import *
# 打开文件对话框， 
filename, filetype = QFileDialog.getOpenFileName(None, '选择文件', "", filter="txt (*.txt)")

seozed

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


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