针对工作生活中基础的功能和操作，梳理了下对应的几个Python代码片段，供参考：
日期生成
获取过去 N 天的日期
|
1
2
3
4
5
6
7
8
9
10
11
12
13
|
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) |
输出：
|
1
|
['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'] |
生成一段时间区间内的日期
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
|
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')print(d_list) |
输出：
|
1
|
['2021-12-27', '2021-12-28', '2021-12-29', '2021-12-30'] |
保存数据到CSV
保存数据到 CSV 算是比较常见的操作了，下面代码如果运行正确会生成"2022_data_2022-01-25.csv"文件。
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
|
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("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("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 库调用
据统计，requests 库是 Python 家族里被引用的最多的第三方库，足见其江湖地位之高大！
发送 GET 请求
|
1
2
3
4
5
6
7
8
|
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) |
发送 POST 请求
|
1
2
3
4
5
6
7
8
9
10
|
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 操作各种数据库
操作 Redis
连接 Redis
|
1
2
3
4
5
6
7
|
import redis def redis_conn_pool(): pool = redis.ConnectionPool(host='localhost', port=6379, decode_responses=True) rd = redis.Redis(connection_pool=pool) return rd |
写入 Redis
|
1
2
3
4
5
|
from redis_conn import redis_conn_pool rd = redis_conn_pool()rd.set('test_data', 'mytest') |
操作 MongoDB
连接 MongoDB
|
1
2
3
4
5
6
|
from pymongo import MongoClient conn = MongoClient("mongodb://%s:%s@ipaddress:49974/mydb" % ('username', 'password'))db = conn.mydbmongo_collection = db.mydata |
批量插入数据
|
1
2
3
|
res = requests.get(url, params=query).json()commentList = res['data']['commentList']mongo_collection.insert_many(commentList) |
操作 MySQL
连接 MySQL
|
1
2
3
4
5
6
7
|
import MySQLdb # 打开数据库连接db = MySQLdb.connect("localhost", "testuser", "test123", "TESTDB", charset='utf8' ) # 使用cursor()方法获取操作游标 cursor = db.cursor() |
执行 SQL 语句
|
1
2
3
4
5
6
7
8
9
10
|
# 使用 execute 方法执行 SQL 语句cursor.execute("SELECT VERSION()") # 使用 fetchone() 方法获取一条数据data = cursor.fetchone() print "Database version : %s " % data # 关闭数据库连接db.close() |
本地文件整理
整理文件涉及需求的比较多，这里分享的是将本地多个 CSV 文件整合成一个文件
|
1
2
3
4
5
6
7
8
9
10
11
12
13
|
import pandas as pdimport 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
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
|
import threadingimport 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
异步爬取网站代码示例：
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
|
import asyncioimport aiohttpimport 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
|
1
2
3
4
|
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))) |
总结
到此这篇关于Python中经常使用的代码片段的文章就介绍到这了,更多相关Python代码片段内容请搜索服务器之家以前的文章或继续浏览下面的相关文章希望大家以后多多支持服务器之家！
原文链接：https://blog.csdn.net/sinat_33718563/article/details/122679167
