6个实用的Python自动化脚本详解

import pyttsx3,PyPDF2 
pdfreader = PyPDF2.PdfFileReader(open('story.pdf','rb')) 
speaker = pyttsx3.init() 
for page_num in range(pdfreader.numPages):    
    text = pdfreader.getPage(page_num).extractText()  ## extracting text from the PDF 
    cleaned_text = text.strip().replace('\n',' ')  ## Removes unnecessary spaces and break lines 
    print(cleaned_text)                ## Print the text from PDF 
    #speaker.say(cleaned_text)        ## Let The Speaker Speak The Text 
    speaker.save_to_file(cleaned_text,'story.mp3')  ## Saving Text In a audio file 'story.mp3' 
    speaker.runAndWait() 
speaker.stop() 

import random, os 
music_dir = 'G:\\new english songs' 
songs = os.listdir(music_dir) 
song = random.randint(0,len(songs)) 
print(songs[song])  ## Prints The Song Name 
os.startfile(os.path.join(music_dir, songs[0]))  

import webbrowser 
with open('./websites.txt') as reader: 
    for link in reader: 
        webbrowser.open(link.strip()) 

import requests 
import json 
import logging as log 
 
def get_weather_wind(url): 
    r = requests.get(url) 
    if r.status_code != 200: 
        log.error("Can't get weather data!") 
    info = json.loads(r.content.decode()) 
 
    # get wind data 
    data = info['weatherinfo'] 
    WD = data['WD'] 
    WS = data['WS'] 
    return "{}({})".format(WD, WS) 
 
 
def get_weather_city(url): 
    # open url and get return data 
    r = requests.get(url) 
    if r.status_code != 200: 
        log.error("Can't get weather data!") 
 
    # convert string to json 
    info = json.loads(r.content.decode()) 
 
    # get useful data 
    data = info['weatherinfo'] 
    city = data['city'] 
    temp1 = data['temp1'] 
    temp2 = data['temp2'] 
    weather = data['weather'] 
    return "{} {} {}~{}".format(city, weather, temp1, temp2) 
 
 
if __name__ == '__main__': 
    msg = """**天气提醒**:   
 
{} {}   
{} {}   
 
来源: 国家气象局 
""".format( 
    get_weather_city('http://www.weather.com.cn/data/cityinfo/101021200.html'), 
    get_weather_wind('http://www.weather.com.cn/data/sk/101021200.html'), 
    get_weather_city('http://www.weather.com.cn/data/cityinfo/101020900.html'), 
    get_weather_wind('http://www.weather.com.cn/data/sk/101020900.html') 
) 
    print(msg) 

import contextlib 
from urllib.parse import urlencode 
from urllib.request import urlopen 
import sys 
 
def make_tiny(url): 
 request_url = ('http://tinyurl.com/api-create.php?' +  
 urlencode({'url':url})) 
 with contextlib.closing(urlopen(request_url)) as response: 
  return response.read().decode('utf-8') 
 
def main(): 
 for tinyurl in map(make_tiny, sys.argv[1:]): 
  print(tinyurl) 
 
if __name__ == '__main__': 
 main() 

import os 
import threading 
import time 
  
  
def get_file_list(file_path): 
#文件按最后修改时间排序 
    dir_list = os.listdir(file_path) 
    if not dir_list: 
        return 
    else: 
        dir_list = sorted(dir_list, key=lambda x: os.path.getmtime(os.path.join(file_path, x))) 
    return dir_list 
  
def get_size(file_path): 
    """[summary] 
    Args: 
        file_path ([type]): [目录] 
 
    Returns: 
        [type]: 返回目录大小，MB 
    """ 
    totalsize=0 
    for filename in os.listdir(file_path): 
        totalsize=totalsize+os.path.getsize(os.path.join(file_path, filename)) 
    #print(totalsize / 1024 / 1024) 
    return totalsize / 1024 / 1024 
  
def detect_file_size(file_path, size_Max, size_Del): 
    """[summary] 
    Args: 
        file_path ([type]): [文件目录] 
        size_Max ([type]): [文件夹最大大小] 
        size_Del ([type]): [超过size_Max时要删除的大小] 
    """ 
    print(get_size(file_path)) 
    if get_size(file_path) > size_Max: 
        fileList = get_file_list(file_path) 
        for i in range(len(fileList)): 
            if get_size(file_path) > (size_Max - size_Del): 
                print ("del :%d %s" % (i + 1, fileList[i])) 
                #os.remove(file_path + fileList[i]) 
     
  
def detectFileSize(): 
 #检测线程，每个5秒检测一次 
    while True: 
        print('======detect============') 
        detect_file_size("/Users/aaron/Downloads/", 100, 30) 
        time.sleep(5) 
   
if __name__ == "__main__": 
    #创建检测线程 
    detect_thread = threading.Thread(target = detectFileSize) 
    detect_thread.start()