[Python] Frequently used library code

Use json as config file

python

import json

settings = json.load(open('settings.json', encoding='utf8'))
print(settings['key'])

settings.json

{
    "key1" : "value1",
    "key2" : "value2"
}

txt file operation

Use txt file as input data (store in array)

python

with open('file.txt', mode='r', encoding='utf-8') as f:
    file = f.read()

files = file.split('\n')
print(files)

Use a txt file as output data (used in a for statement)

python

with open(filepath, mode='a', encoding='utf-8') as f:
    f.write('String\n')

File operations

Copy file

python

import shutil

shutil.copy2(path_src, path_dist)

Get date

python

import datetime

now = datetime.datetime.now()
now_disp = dt_now.strftime('%Y%m%d')

Get a list of files in a directory (array)

python

file_list = os.listdir(path=filepath)

#An excerpt of a file containing a specific character from the array of files obtained above
file_list_unique = [s for s in file_list if 'Specified character string' in s]

web scraping

terminal

pip install requests bs4

python

import requests
from bs4 import BeautifulSoup

url = 'website.com'
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
# soup = BeautifulSoup(response.text, 'lxml')
# soup = BeautifulSoup(response.text, 'html5lib')

#Single acquisition
print(soup.select_one('.css-selector').text) #Get a string
print(soup.select_one('.css-selector').attrs['href']) #Get the value of an attribute

#If there are more than one`select`Get it with and turn it with for
htmls = soup.select('.css-selector')
for html in htmls:
    print(html.select_one('.css-selector').text)

Excel operation

terminal

pip install openpyxl

python

import openpyxl

wb = openpyxl.load_workbook(filepath)
ws = wb['Sheet name']

#Get the value of a specific cell (A1 is row=1, column=1）
cell_obj = ws.cell(row=1, column=1).value

#Enter a value in a specific cell
ws.cell(row=1, column=1).value = 'value'

#Get all the values ​​in a specific column (* Note: 0 is column A in the array index)
for cell_obj in list(ws.columns)[0]:
    print(cell_obj.value)

#Get all the values ​​in a specific row (* Note: 0 is column A in the array index)
for cell_obj in list(ws.rows)[0]:
    print(cell_obj.value)

#Sheet save
wb.save(filepath)

Browser automatic operation

Download chromedriver and place it directly under the project https://chromedriver.chromium.org/downloads

terminal

pip install selenium pyperclip

python

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.keys import Keys
import pyperclip

#Chrome Driver settings
driver_path = './chromedriver'
options = Options()
options.add_argument('--window-size=1600,900')
driver = webdriver.Chrome(options=options, executable_path=driver_path)

IMPLICITLY_INTERVAL = 10
driver.implicitly_wait(IMPLICITLY_INTERVAL)

#Chrome Driver operation
##Show argument URL
driver.get('https://sample.com')

##Click the specified selector
driver.find_element_by_css_selector('.css-selector').click()

##Character input (send)_Since keys is slow, copy the character string with pyperclip and paste it)
pyperclip.copy('The character string you want to enter')
driver.find_element_by_css_selector('.css-selector').send_keys(Keys.CONTROL, 'v')

##Javascript execution (Example: Set the display property of the specified selector to none)
driver.execute_script('document.querySelector(".css-selector").style.display="none";')

##Quit Chrome Driver
driver.quit()

Make it an executable file

terminal

pip install pyinstaller

terminal

pyinstaller filename.py

pyinstaller filename.py --onefile #One.Put together in an exe file
pyinstaller filename.py --noconsole # .Do not show console when running exe
pyinstaller filename.py --onefile --noconsole #Both of the above