Python抓取每日必应壁纸

最新推荐文章于 2024-09-04 10:31:20 发布

詹凌

最新推荐文章于 2024-09-04 10:31:20 发布

阅读量852

点赞数

分类专栏：编程笔记文章标签： python bing

本文链接：https://blog.csdn.net/qq_15243795/article/details/70674026

版权

编程笔记专栏收录该内容

4 篇文章 0 订阅

订阅专栏

Python抓取每日必应壁纸

作者：Zhanling

import urllib2
import re
import os
import time
import thread
import logging

class BingBG:           
def __init__(self):                                             #初始化成员变量
    mTime = time.time()
    mOldTime = time.localtime(mTime)
    self.strOldTime = str(mOldTime.tm_year) + str(mOldTime.tm_mon) + str(mOldTime.tm_mday)      
    self.strNewTime = str("")                                   #OldTime与NewTime结合判断日期是否变更

    self. myUrl = "http://cn.bing.com"
    self.user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'  #伪装浏览器访问
    self.headers = {'User-Agent':  self.user_agent}

    self.picDir = r"D:\BingBG"                                  #图片保存地址
    logging.info("init app")                                    #初始化完成

def DownLoad(self):                                             #下载
    req = urllib2.Request(self.myUrl, headers=self.headers)     #封装请求
    logging.info("opening cn.bing.com")

    try:
        res = urllib2.urlopen(req)                              #打开必应
        page = res.read()                                       #读取网页内容
        items = re.findall(r"g_img={url: \".*\.jpg\"", page)    #正则匹配图片链接
        if items:
            mTime = time.time()                                 #获取当前日期
            mLocalTime = time.localtime(mTime)
            strLocalTime = str(mLocalTime.tm_year) + str(mLocalTime.tm_mon) + str(mLocalTime.tm_mday)

            picUrl = self.myUrl + items[0][13:-1]                   #拼接完整的必应图片地址
            img_name = self.picDir + "\\" + strLocalTime + ".jpg"   #以当前日期作为文件名
            img_data = urllib2.urlopen(picUrl).read()               #读取图片内容
            f = open(img_name, 'wb')                                #保存到文件
            f.write(img_data)
            f.close()

            logging.info("download success")
        else:
            logging.info("item not found")
    except:                                                         #出现异常
        logging.info("URL open exception")

def DownLoadThread(self):                                           #循环线程
    logging.info("thread start")
    while(1):
        if not os.path.exists(self.picDir):                         #判断是否存在保存图片的文件夹，不存在则创建
            os.mkdir(self.picDir)
            logging.info("not exist dir,create")
        if not os.listdir(self.picDir):                             #判断文件夹下面有没有文件，没有则马上下载当天壁纸
            mTime = time.time()
            mOldTime = time.localtime(mTime)
            self.strOldTime = str(mOldTime.tm_year) + str(mOldTime.tm_mon) + str(mOldTime.tm_mday)
            logging.info("empty, first download")
            self.DownLoad()
        else:                                                       #存在文件，判断日期是否变更
            mTime = time.time()
            mNewTime = time.localtime(mTime)
            self.strNewTime = str(mNewTime.tm_year) + str(mNewTime.tm_mon) + str(mNewTime.tm_mday)
            if self.strNewTime != self.strOldTime:                  #日期变更则下载图片
                self.strOldTime = self.strNewTime
                logging.info("check, day change, download")
                self.DownLoad()
            else:
                logging.info("check, day not change, keep on")
        time.sleep(14400)                                           #四小时循环一次

def start(self):
    thread.start_new_thread(self.DownLoadThread())


logging.basicConfig(level=logging.DEBUG,                                #Log配置
            format='%(asctime)s %(filename)s[line:%(lineno)d] %(levelname)s %(message)s',
            datefmt='%a, %d %b %Y %H:%M:%S',
            filename='BingBG.log',
            filemode='a')

bingBg = BingBG()                                                       #实例化对象
bingBg.start()                                                          #线程启动