Python中經(jīng)常使用的代碼片段

更新時(shí)間：2022年01月26日 10:48:02 作者：rs勿忘初心

大家好，本篇文章主要講的是Python中經(jīng)常使用的代碼片段，感興趣的同學(xué)趕快來看一看吧，對你有幫助的話記得收藏一下

日期生成

獲取過去 N 天的日期

import datetime
 
 
def get_nday_list(n):
    before_n_days = []
    # [::-1]控制日期排序
    for i in range(1, n + 1)[::-1]:
        before_n_days.append(str(datetime.date.today() - datetime.timedelta(days=i)))
    return before_n_days
 
 
a = get_nday_list(30)
print(a)

輸出：

['2021-12-26', '2021-12-27', '2021-12-28', '2021-12-29', '2021-12-30', '2021-12-31', '2022-01-01', '2022-01-02', '2022-01-03', '2022-01-04', '2022-01-05', '2022-01-06', '2022-01-07', '2022-01-08', '2022-01-09', '2022-01-10', '2022-01-11', '2022-01-12', '2022-01-13', '2022-01-14', '2022-01-15', '2022-01-16', '2022-01-17', '2022-01-18', '2022-01-19', '2022-01-20', '2022-01-21', '2022-01-22', '2022-01-23', '2022-01-24']

生成一段時(shí)間區(qū)間內(nèi)的日期

import datetime
 
 
def create_assist_date(datestart = None,dateend = None):
    # 創(chuàng)建日期輔助表
    if datestart is None:
        datestart = '2016-01-01'
    if dateend is None:
        dateend = datetime.datetime.now().strftime('%Y-%m-%d')
 
    # 轉(zhuǎn)為日期格式
    datestart=datetime.datetime.strptime(datestart,'%Y-%m-%d')
    dateend=datetime.datetime.strptime(dateend,'%Y-%m-%d')
    date_list = []
    date_list.append(datestart.strftime('%Y-%m-%d'))
    while datestart<dateend:
        # 日期疊加一天
        datestart+=datetime.timedelta(days=+1)
        # 日期轉(zhuǎn)字符串存入列表
        date_list.append(datestart.strftime('%Y-%m-%d'))
    return date_list
 
 
d_list = create_assist_date(datestart='2021-12-27', dateend='2021-12-30')
print(d_list)

輸出：

['2021-12-27', '2021-12-28', '2021-12-29', '2021-12-30']

保存數(shù)據(jù)到CSV

保存數(shù)據(jù)到 CSV 算是比較常見的操作了，下面代碼如果運(yùn)行正確會(huì)生成"2022_data_2022-01-25.csv"文件。

import os
 
 
def save_data(data, date):
    """
    :param data:
    :param date:
    :return:
    """
    if not os.path.exists(r'2022_data_%s.csv' % date):
        with open("2022_data_%s.csv" % date, "a+", encoding='utf-8') as f:
            f.write("標(biāo)題,熱度,時(shí)間,url\n")
            for i in data:
                title = i["title"]
                extra = i["extra"]
                time = i['time']
                url = i["url"]
                row = '{},{},{},{}'.format(title,extra,time,url)
                f.write(row)
                f.write('\n')
    else:
        with open("2022_data_%s.csv" % date, "a+", encoding='utf-8') as f:
            for i in data:
                title = i["title"]
                extra = i["extra"]
                time = i['time']
                url = i["url"]
                row = '{},{},{},{}'.format(title,extra,time,url)
                f.write(row)
                f.write('\n')
 
 
data = [{"title": "demo", "extra": "hello", "time": "1998-01-01", "url": "https://www.baidu.com/"}]
date = "2022-01-25"
 
save_data(data, date)

requests 庫調(diào)用

據(jù)統(tǒng)計(jì)，requests 庫是 Python 家族里被引用的最多的第三方庫，足見其江湖地位之高大！

發(fā)送 GET 請求

import requests
 
 
headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36',
  'cookie': 'some_cookie'
}
response = requests.request("GET", url, headers=headers)

發(fā)送 POST 請求

import requests
 
 
payload={}
files=[]
headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36',
  'cookie': 'some_cookie'
}
response = requests.request("POST", url, headers=headers, data=payload, files=files)

Python 操作各種數(shù)據(jù)庫

操作 Redis

連接 Redis

import redis
 
 
def redis_conn_pool():
    pool = redis.ConnectionPool(host='localhost', port=6379, decode_responses=True)
    rd = redis.Redis(connection_pool=pool)
    return rd

寫入 Redis

from redis_conn import redis_conn_pool
 
 
rd = redis_conn_pool()
rd.set('test_data', 'mytest')

操作 MongoDB

連接 MongoDB

from pymongo import MongoClient
 
 
conn = MongoClient("mongodb://%s:%s@ipaddress:49974/mydb" % ('username', 'password'))
db = conn.mydb
mongo_collection = db.mydata

批量插入數(shù)據(jù)

res = requests.get(url, params=query).json()
commentList = res['data']['commentList']
mongo_collection.insert_many(commentList)

操作 MySQL

連接 MySQL

 
import MySQLdb
 
# 打開數(shù)據(jù)庫連接
db = MySQLdb.connect("localhost", "testuser", "test123", "TESTDB", charset='utf8' )
 
# 使用cursor()方法獲取操作游標(biāo) 
cursor = db.cursor()

執(zhí)行 SQL 語句

# 使用 execute 方法執(zhí)行 SQL 語句
cursor.execute("SELECT VERSION()")
 
# 使用 fetchone() 方法獲取一條數(shù)據(jù)
data = cursor.fetchone()
 
print "Database version : %s " % data
 
# 關(guān)閉數(shù)據(jù)庫連接
db.close()

本地文件整理

整理文件涉及需求的比較多，這里分享的是將本地多個(gè) CSV 文件整合成一個(gè)文件

import pandas as pd
import os
 
 
df_list = []
for i in os.listdir():
    if "csv" in i:
        day = i.split('.')[0].split('_')[-1]
        df = pd.read_csv(i)
        df['day'] = day
        df_list.append(df)
df = pd.concat(df_list, axis=0)
df.to_csv("total.txt", index=0)

多線程代碼

多線程也有很多實(shí)現(xiàn)方式，我們選擇自己最為熟悉順手的方式即可

import threading
import time
 
exitFlag = 0
 
class myThread (threading.Thread):
    def __init__(self, threadID, name, delay):
        threading.Thread.__init__(self)
        self.threadID = threadID
        self.name = name
        self.delay = delay
    def run(self):
        print ("開始線程：" + self.name)
        print_time(self.name, self.delay, 5)
        print ("退出線程：" + self.name)
 
def print_time(threadName, delay, counter):
    while counter:
        if exitFlag:
            threadName.exit()
        time.sleep(delay)
        print ("%s: %s" % (threadName, time.ctime(time.time())))
        counter -= 1
 
# 創(chuàng)建新線程
thread1 = myThread(1, "Thread-1", 1)
thread2 = myThread(2, "Thread-2", 2)
 
# 開啟新線程
thread1.start()
thread2.start()
thread1.join()
thread2.join()
print ("退出主線程")

異步編程代碼

異步爬取網(wǎng)站代碼示例：

import asyncio
import aiohttp
import aiofiles
 
async def get_html(session, url):
    try:
        async with session.get(url=url, timeout=8) as resp:
            if not resp.status // 100 == 2:
                print(resp.status)
                print("爬取", url, "出現(xiàn)錯(cuò)誤")
            else:
                resp.encoding = 'utf-8'
                text = await resp.text()
                return text
    except Exception as e:
        print("出現(xiàn)錯(cuò)誤", e)
        await get_html(session, url)

使用異步請求之后，對應(yīng)的文件保存也需要使用異步，即是一處異步，處處異步

async def download(title_list, content_list):
    async with aiofiles.open('{}.txt'.format(title_list[0]), 'a',
                             encoding='utf-8') as f:
        await f.write('{}'.format(str(content_list)))