今天纯干货分享!
1. 将 JSON 转换为 CSV
import json
if __name__ == '__main__':
try:
with open('input.json', 'r') as f:
data = json.loads(f.read())
output = ','.join([*data[0]])
for obj in data:
output += f'\n{obj["Name"]},{obj["age"]},{obj["birthyear"]}'
with open('output.csv', 'w') as f:
f.write(output)
except Exception as ex:
print(f'Error: {str(ex)}')
2. 密码生成器
import random
import string
total = string.ascii_letters + string.digits + string.punctuation
length = 16
password = "".join(random.sample(total, length))
print(password)
3. 从多个文件中搜索字符串
import os
text = input("input text : ")
path = input("path : ")
# os.chdir(path)
def getfiles(path):
f = 0
os.chdir(path)
files = os.listdir()
# print(files)
for file_name in files:
abs_path = os.path.abspath(file_name)
if os.path.isdir(abs_path):
getfiles(abs_path)
if os.path.isfile(abs_path):
f = open(file_name, "r")
if text in f.read():
f = 1
print(text + " found in ")
final_path = os.path.abspath(file_name)
print(final_path)
return True
if f == 1:
print(text + " not found! ")
return False
getfiles(path)
4. 从给定网页获取所有链接
import requests as rq
from bs4 import BeautifulSoup
url = input("Enter Link: ")
if ("https" or "http") in url:
data = rq.get(url)
else:
data = rq.get("https://" + url)
soup = BeautifulSoup(data.text, "html.parser")
links = []
for link in soup.find_all("a"):
links.append(link.get("href"))
# Writing the output to a file (myLinks.txt) instead of to stdout
# You can change 'a' to 'w' to overwrite the file each time
with open("myLinks.txt", 'a') as saved:
print(links[:10], file=saved)
5. 图像水印
import os
from PIL import Image
def watermark_photo(input_image_path,watermark_image_path,output_image_path):
base_image = Image.open(input_image_path)
watermark = Image.open(watermark_image_path).convert("RGBA")
# add watermark to your image
position = base_image.size
newsize = (int(position[0]*8/100),int(position[0]*8/100))
# print(position)
watermark = watermark.resize(newsize)
# print(newsize)
# return watermark
new_position = position[0]-newsize[0]-20,position[1]-newsize[1]-20
# create a new transparent image
transparent = Image.new(mode='RGBA',size=position,color=(0,0,0,0))
# paste the original image
transparent.paste(base_image,(0,0))
# paste the watermark image
transparent.paste(watermark,new_position,watermark)
image_mode = base_image.mode
print(image_mode)
if image_mode == 'RGB':
transparent = transparent.convert(image_mode)
else:
transparent = transparent.convert('P')
transparent.save(output_image_path,optimize=True,quality=100)
print("Saving"+output_image_path+"...")
folder = input("Enter Folder Path:")
watermark = input("Enter Watermark Path:")
os.chdir(folder)
files = os.listdir(os.getcwd())
print(files)
if not os.path.isdir("output"):
os.mkdir("output")
c = 1
for f in files:
if os.path.isfile(os.path.abspath(f)):
if f.endswith(".png") or f.endswith(".jpg"):
watermark_photo(f,watermark,"output/"+f)
6. 从WEB页面报废并下载所有图像
from selenium import webdriver
import requests as rq
import os
from bs4 import BeautifulSoup
import time
# path= E:\web scraping\chromedriver_win32\chromedriver.exe
path = input("Enter Path : ")
url = input("Enter URL : ")
output = "output"
def get_url(path, url):
driver = webdriver.Chrome(executable_path=r"{}".format(path))
driver.get(url)
print("loading.....")
res = driver.execute_script("return document.documentElement.outerHTML")
return res
def get_img_links(res):
soup = BeautifulSoup(res, "lxml")
imglinks = soup.find_all("img", src=True)
return imglinks
def download_img(img_link, index):
try:
extensions = [".jpeg", ".jpg", ".png", ".gif"]
extension = ".jpg"
for exe in extensions:
if img_link.find(exe) > 0:
extension = exe
break
img_data = rq.get(img_link).content
with open(output + "\\" + str(index + 1) + extension, "wb+") as f:
f.write(img_data)
f.close()
except Exception:
pass
result = get_url(path, url)
time.sleep(60)
img_links = get_img_links(result)
if not os.path.isdir(output):
os.mkdir(output)
for index, img_link in enumerate(img_links):
img_link = img_link["src"]
print("Downloading...")
if img_link:
download_img(img_link, index)
print("Download Complete!!")
7. 低电量通知
# pip install psutil
import psutil
battery = psutil.sensors_battery()
plugged = battery.power_plugged
percent = battery.percent
if percent <= 30 and plugged!=True:
# pip install py-notifier
# pip install win10toast
from pynotifier import Notification
Notification(
title="Battery Low",
description=str(percent) + "% Battery remain!!",
duration=5, # Duration in seconds
).send()
8. 计算你的年龄
import time
from calendar import isleap
# judge the leap year
def judge_leap_year(year):
if isleap(year):
return True
else:
return False
# returns the number of days in each month
def month_days(month, leap_year):
if month in [1, 3, 5, 7, 8, 10, 12]:
return 31
elif month in [4, 6, 9, 11]:
return 30
elif month == 2 and leap_year:
return 29
elif month == 2 and (not leap_year):
return 28
name = input("input your name: ")
age = input("input your age: ")
localtime = time.localtime(time.time())
year = int(age)
month = year * 12 + localtime.tm_mon
day = 0
begin_year = int(localtime.tm_year) - year
end_year = begin_year + year
# calculate the days
for y in range(begin_year, end_year):
if (judge_leap_year(y)):
day = day + 366
else:
day = day + 365
leap_year = judge_leap_year(localtime.tm_year)
for m in range(1, localtime.tm_mon):
day = day + month_days(m, leap_year)
day = day + localtime.tm_mday
print("%s's age is %d years or " % (name, year), end="")
print("%d months or %d days" % (month, day))
9. 有组织的不同类别的下载文件夹
import os
import shutil
os.chdir("E:\downloads")
#print(os.getcwd())
#check number of files in directory
files = os.listdir()
#list of extension (You can add more if you want)
extentions = {
"images": [".jpg", ".png", ".jpeg", ".gif"],
"videos": [".mp4", ".mkv"],
"musics": [".mp3", ".wav"],
"zip": [".zip", ".tgz", ".rar", ".tar"],
"documents": [".pdf", ".docx", ".csv", ".xlsx", ".pptx", ".doc", ".ppt", ".xls"],
"setup": [".msi", ".exe"],
"programs": [".py", ".c", ".cpp", ".php", ".C", ".CPP"],
"design": [".xd", ".psd"]
}
#sort to specific folder depend on extenstions
def sorting(file):
keys = list(extentions.keys())
for key in keys:
for ext in extentions[key]:
# print(ext)
if file.endswith(ext):
return key
#iterat through each file
for file in files:
dist = sorting(file)
if dist:
try:
shutil.move(file, "../download-sorting/" + dist)
except:
print(file + " is already exist")
else:
try:
shutil.move(file, "../download-sorting/others")
except:
print(file + " is already exist")
10. 从 CSV 文件批量发送电子邮件
import csv
from email.message import EmailMessage
import smtplib
def get_credentials(filepath):
with open("credentials.txt", "r") as f:
email_address = f.readline()
email_pass = f.readline()
return (email_address, email_pass)
def login(email_address, email_pass, s):
s.ehlo()
# start TLS for security
s.starttls()
s.ehlo()
# Authentication
s.login(email_address, email_pass)
print("login")
def send_mail():
s = smtplib.SMTP("smtp.gmail.com", 587)
email_address, email_pass = get_credentials("./credentials.txt")
login(email_address, email_pass, s)
# message to be sent
subject = "Welcome to Python"
body = """Python is an interpreted, high-level,
general-purpose programming language.\n
Created by Guido van Rossum and first released in 1991,
Python's design philosophy emphasizes code readability\n
with its notable use of significant whitespace"""
message = EmailMessage()
message.set_content(body)
message['Subject'] = subject
with open("emails.csv", newline="") as csvfile:
spamreader = csv.reader(csvfile, delimiter=" ", quotechar="|")
for email in spamreader:
s.send_message(email_address, email[0], message)
print("Send To " + email[0])
# terminating the session
s.quit()
print("sent")
if __name__ == "__main__":
send_mail()
11. 获取网站的IP地址和主机名
# Get Ipaddress and Hostname of Website
# importing socket library
import socket
def get_hostname_IP():
hostname = input("Please enter website address(URL):")
try:
print (f'Hostname: {hostname}')
print (f'IP: {socket.gethostbyname(hostname)}')
except socket.gaierror as error:
print (f'Invalid Hostname, error raised is {error}')
get_hostname_IP()
12. 终端进度条
from tqdm import tqdm
from PIL import Image
import os
from time import sleep
def Resize_image(size, image):
if os.path.isfile(image):
try:
im = Image.open(image)
im.thumbnail(size, Image.ANTIALIAS)
im.save("resize/" + str(image) + ".jpg")
except Exception as ex:
print(f"Error: {str(ex)} to {image}")
path = input("Enter Path to images : ")
size = input("Size Height , Width : ")
size = tuple(map(int, size.split(",")))
os.chdir(path)
list_images = os.listdir(path)
if "resize" not in list_images:
os.mkdir("resize")
for image in tqdm(list_images, desc="Resizing Images"):
Resize_image(size, image)
sleep(0.1)
print("Resizing Completed!")
13. Wifi密码弹出器
import subprocess
data = (
subprocess.check_output(["netsh", "wlan", "show", "profiles"])
.decode("utf-8")
.split("\n")
)
profiles = [i.split(":")[1][1:-1] for i in data if "All User Profile" in i]
for i in profiles:
results = (
subprocess
.check_output(["netsh", "wlan", "show", "profile", i, "key=clear"])
.decode("utf-8")
.split("\n")
)
results = [b.split(":")[1][1:-1] for b in results if "Key Content" in b]
try:
print("{:<30}| {:<}".format(i, results[0]))
except IndexError:
print("{:<30}| {:<}".format(i, ""))
14. 给定网站的快照
import sys
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
import chromedriver_binary
script_name = sys.argv[0]
options = Options()
options.add_argument('--headless')
driver = webdriver.Chrome(options=options)
try:
url = sys.argv[1]
driver.get(url)
page_width = driver.execute_script('return document.body.scrollWidth')
page_height = driver.execute_script('return document.body.scrollHeight')
driver.set_window_size(page_width, page_height)
driver.save_screenshot('screenshot.png')
driver.quit()
print("SUCCESS")
except IndexError:
print('Usage: %s URL' % script_name)
15. 将文件拆分成块
import sys
import os
import shutil
import pandas as pd
class Split_Files:
'''
Class file for split file program
'''
def __init__(self, filename, split_number):
'''
Getting the file name and the split index
Initializing the output directory, if present then truncate it.
Getting the file extension
'''
self.file_name = filename
self.directory = "file_split"
self.split = int(split_number)
if os.path.exists(self.directory):
shutil.rmtree(self.directory)
os.mkdir(self.directory)
if self.file_name.endswith('.txt'):
self.file_extension = '.txt'
else:
self.file_extension = '.csv'
self.file_number = 1
def split_data(self):
'''
spliting the input csv/txt file according to the index provided
'''
data = pd.read_csv(self.file_name, header=None)
data.index += 1
split_frame = pd.DataFrame()
output_file = f"{self.directory}/split_file{self.file_number}{self.file_extension}"
for i in range(1, len(data)+1):
split_frame = split_frame.append(data.iloc[i-1])
if i % self.split == 0:
output_file = f"{self.directory}/split_file{self.file_number}{self.file_extension}"
if self.file_extension == '.txt':
split_frame.to_csv(output_file, header=False, index=False, sep=' ')
else:
split_frame.to_csv(output_file, header=False, index=False)
split_frame.drop(split_frame.index, inplace=True)
self.file_number += 1
if not split_frame.empty:
output_file = f"{self.directory}/split_file{self.file_number}{self.file_extension}"
split_frame.to_csv(output_file, header=False, index=False)
if __name__ == '__main__':
file, split_number = sys.argv[1], sys.argv[2]
sp = Split_Files(file, split_number)
sp.split_data()
16. 加密和解密文本
from Crypto.Cipher import AES
from Crypto import Random
from binascii import b2a_hex
import sys
# get the plaintext
plain_text = sys.argv[1]
# The key length must be 16 (AES-128), 24 (AES-192), or 32 (AES-256) Bytes.
key = b'this is a 16 key'
# Generate a non-repeatable key vector with a length
# equal to the size of the AES block
iv = Random.new().read(AES.block_size)
# Use key and iv to initialize AES object, use MODE_CFB mode
mycipher = AES.new(key, AES.MODE_CFB, iv)
# Add iv (key vector) to the beginning of the encrypted ciphertext
# and transmit it together
ciphertext = iv + mycipher.encrypt(plain_text.encode())
# To decrypt, use key and iv to generate a new AES object
mydecrypt = AES.new(key, AES.MODE_CFB, ciphertext[:16])
# Use the newly generated AES object to decrypt the encrypted ciphertext
decrypttext = mydecrypt.decrypt(ciphertext[16:])
# output
file_out = open("encrypted.bin", "wb")
file_out.write(ciphertext[16:])
file_out.close()
print("The key k is: ", key)
print("iv is: ", b2a_hex(ciphertext)[:16])
print("The encrypted data is: ", b2a_hex(ciphertext)[16:])
print("The decrypted data is: ", decrypttext.decode())