爬取必应首页大图 - Python 不废话，直接上代码# -*- coding: utf-8 -*- # @Author: Wang Hongbin # @Email: wanghongbin@ngoos.org # @Date: 2018-03-16 14:19:27 # @Last Modified by: Wang Hongbin # @Last Modified time: 2018-03-28 16:26:07 import requests import re import os import time #时间模块 local = time.strftime("%Y-%m-%d_") baseUrl = "https://cn.bing.com" headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36'} def getImgUrl(url): reg1 = r"(/az/hprichbg/rb/.*?.jpg)" con = requests.get(url) content = con.text imgUrl = re.findall(reg1, content, re.S)[0] # imgLink = baseUrl+imgUrl return imgUrl def getFilePath(): # filePath = '/var/www/html/biYinPic/images/' + time.strftime("%Y%m%d") + '/' filePath = 'C:/Users/Administrator/Pictures/MyDesktop/' if not os.path.exists(filePath): os.mkdir(filePath) return filePath def getImgName(url): reg2 = r"/az/hprichbg/rb/(.*?)_" imgName = re.findall(reg2, url, re.S)[0] imgName = local + imgName + '.jpg' return imgName def downloadByPic(url): imgUrl = getImgUrl(url) imgName = getImgName(imgUrl) filePath = getFilePath() fileName = filePath+imgName picUrl = baseUrl + imgUrl read = requests.get(picUrl) f = open(fileName, 'wb') f.write(read.content) f.close() # reg3 = r'<div class=\"hplaCata\"><div class=\"hplatt\">(.*)</div><div class=\"hplats\">(.*)</div><div id=\"hplaSnippet\">(.*)</div><div class=\"hplaPvd\">(.*)</div>' downloadByPic(baseUrl) print('is ok!')爬取结果下图是七月份至今的爬取图片，因为是在window上执行的，电脑不开机的时候不会执行，代码放在Linux上执行也没问题，使用crontab启个定时器就行了

爬取必应首页大图 - PHP 不废话，直接上代码<?php /** * 获取bing首页大图保存在本地 * @Author: Wang Hongbin * @Email: wanghongbin@ngoos.org * @Date: 2018-02-24 15:21:40 * @Last Modified by: Wang Hongbin * @Last Modified time: 2018-02-24 15:36:52 */ class GetBingPic { private $bingApiXml; private $bingApiJson; function __construct() { // 返回xml格式 $this->bingApiXml = "http://cn.bing.com/HPImageArchive.aspx?idx=0&n=1"; // 返回json格式 $this->bingApiJson = "http://cn.bing.com/HPImageArchive.aspx?format=js&idx=0&n=1"; } /** * xml格式数据 * @return [type] [description] */ public function getDataXml() { $url = $this->bingApiXml; $data = $this->httpGet($url); return $data; } /** * json格式数据 * @return [type] [description] */ public function getDataXml() { $url = $this->bingApiJson; $data = $this->httpGet($url); return $data; } private function httpGet($url) { $curl = curl_init(); curl_setopt($curl, CURLOPT_RETURNTRANSFER, true); curl_setopt($curl, CURLOPT_TIMEOUT, 500); curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, false); curl_setopt($curl, CURLOPT_SSL_VERIFYHOST, false); curl_setopt($curl, CURLOPT_URL, $url); $res = curl_exec($curl); curl_close($curl); return $res; } } $BingPic = new GetBingPic(); $xmldata = $BingPic->getDataXml(); var_dump($xmldata);爬取结果下图是七月份至今的爬取图片，因为是在window上执行的，电脑不开机的时候不会执行，代码放在Linux上执行也没问题，使用crontab启个定时器就行了啰嗦几句其实也没啥，就是还有python的版本 爬取必应首页大图 - Python