python爬取Bing每天的图片

直接上代码

import os.path
import urllib
from urllib.request import urlopen, urlretrieve
from urllib.parse import unquote
from apscheduler.triggers.cron import CronTrigger

from apscheduler.schedulers.blocking import BlockingScheduler
from bs4 import BeautifulSoup
from datetime import datetime
import re

bing_url = 'https://cn.bing.com/'
download_dir = 'C:\\Users\\xianghua\\Pictures\\Saved Pictures\\'



def get_html():
    html = urlopen(bing_url)
    bing_html = BeautifulSoup(html, 'html.parser')
    return bing_html


def get_image_url(bing_html):
    dic_style = bing_html.find('div', {'class': 'hpapp'}). \
        find('div', {'class': 'hp_body'}). \
        find('div', {'class': 'img_cont'}).attrs['style']
    image_path = dic_style[(dic_style.index('(') + 1): dic_style.index(')')]
    print(bing_url + image_path)
    return bing_url + image_path


def get_filename(bing_html):
    filename_href = bing_html.find('div', {'class': 'hpapp'}). \
        find('div', {'class': 'hp_body'}). \
        find('div', {'class': 'bottom_row'}). \
        find('div', {'class': 'icon_text'}). \
        find('a', href=re.compile('^(/search)')).attrs['href']
    filename = filename_href[(filename_href.index('=') + 1): filename_href.index('&')]
    name = unquote(filename, encoding='UTF-8')
    print(name)
    return name


def job():
    print('Begin-----')
    print(datetime.now().strftime('%Y-%m-%d %H:%M:%S'))
    bing_html = get_html()
    image_url = get_image_url(bing_html)
    filename = get_filename(bing_html)
    dir = download_dir + filename + '.jpg';
    print(dir)
    if not os.path.exists(dir):
        urllib.request.urlretrieve(image_url, dir)
        print('downloading......OK')
    print('-----END')


c1 = CronTrigger(day_of_week='0-6', hour=11, minute=30, second=00)


if __name__ == '__main__':
    job()