python 直接使用的代码

日期生成

很多时候我们需要批量生成日期，方法有很多，这里分享两段代码

获取过去 N 天的日期

import datetime

def get_nday_list(n):
    before_n_days = []
    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)

Output:

['2021-12-23', '2021-12-24', '2021-12-25', '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']

生成一段时间区间内的日期

import datetime

def create_assist_date(datestart = None,dateend = None):
    # 创建日期辅助表

    if datestart is None:
        datestart = '2016-01-01'
    if dateend is None:
        dateend = datetime.datetime.now().strftime('%Y-%m-%d')

    # 转为日期格式
    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:
        # 日期叠加一天
        datestart+=datetime.timedelta(days=+1)
        # 日期转字符串存入列表
        date_list.append(datestart.strftime('%Y-%m-%d'))
    return date_list

d_list = create_assist_date(datestart='2021-12-27', dateend='2021-12-30')
d_list

Output:

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

保存数据到CSV

def save_data(data, date):
    if not os.path.exists(r'2021_data_%s.csv' % date):
        with open("2021_data_%s.csv" % date, "a+", encoding='utf-8') as f:
            f.write("标题,热度,时间,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("2021_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')

多线程代码

多线程也有很多实现方式，我们选择自己最为熟悉顺手的方式即可

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 ("开始线程：" + self.name)
        print_time(self.name, self.delay, 5)
        print ("退出线程：" + 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

# 创建新线程
thread1 = myThread(1, "Thread-1", 1)
thread2 = myThread(2, "Thread-2", 2)

# 开启新线程
thread1.start()
thread2.start()
thread1.join()
thread2.join()
print ("退出主线程")

异步编程代码

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, "出现错误")
            else:
                resp.encoding = 'utf-8'
                text = await resp.text()
                return text
    except Exception as e:
        print("出现错误", e)
        await get_html(session, url)

使用异步请求之后，对应的文件保存也需要使用异步，即是一处异步，处处异步

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)))

转自