Some methods implemented in python can be used directly

1. Date generation

Many times we need to generate dates in batches. There are many methods. Here are two pieces of code:

Get dates for the past N days:

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']

Generate dates within a range of time:

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']

2. Save data to CSV

Saving data to CSV is an all too common operation

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')

3. Pyecharts with background color

As an excellent Python implementation of Echarts, Pyecharts is favored by many developers. When drawing with Pyecharts, using a comfortable background will also add a lot of color to our charts.

Take the pie chart as an example, change the background color by adding JavaScript code

def pie_rosetype(data) -> Pie:
    background_color_js = (
    "new echarts.graphic.LinearGradient(0, 0, 0, 1, "
    "[{offset: 0, color: '#c86589'}, {offset: 1, color: '#06a7ff'}], false)"
)
    c = (
        Pie(init_opts=opts.InitOpts(bg_color=JsCode(background_color_js)))
        .add(
            "",
            data,
            radius=["30%", "75%"],
            center=["45%", "50%"],
            rosetype="radius",
            label_opts=opts.LabelOpts(formatter="{b}: {c}"),
        )
        .set_global_opts(title_opts=opts.TitleOpts(title=""),
                        )
    )
    return c

4. requests library call

According to statistics, the requests library is the most cited third-party library in the Python family, which shows its high status in the world!

Send GET request

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)

Send POST request

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)

Loop requests based on certain conditions, such as based on the generated date

def get_data(mydate):
    date_list = create_assist_date(mydate)
    url = "https://test.test"
    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': ''
        }
    for d in date_list:
        payload={
    
    'p': '10',
        'day': d,
        'nodeid': '1',
        't': 'itemsbydate',
        'c': 'node'}
        for i in range(1, 100):
            payload['p'] = str(i)
            print("get data of %s in page %s" % (d, str(i)))
            response = requests.request("POST", url, headers=headers, data=payload, files=files)
            items = response.json()['data']['items']
            if items:
                save_data(items, d)
            else:
                break

5. Python operates various databases

Operating Redis

Connect to 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

Write to Redis

from redis_conn import redis_conn_pool


rd = redis_conn_pool()
rd.set('test_data', 'mytest')

Operating MongoDB

Connect to MongoDB

from pymongo import MongoClient


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

Insert data in batches

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

OperatingMySQL

Connect to MySQL

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()

Execute SQL statement

# 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()

Output:

Database version : 5.0.45

6. Multi-threaded code

There are many ways to implement multithreading

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")