python抓取bing首頁背景圖片

標籤：find   原因   ora   pattern   family   ace   ror   save   .com   

最初Python2寫法：#!/usr/bin/env python

# -*- coding:utf-8 -*-

# -*- author:nancy -*-

# python2抓取bing首頁所有背景圖片

import urllib,re,sys,os

def get_bing_backphoto():

    if (os.path.exists(‘photos‘)== False):

        os.mkdir(‘photos‘)

    for i in range(0,1000):

        url = ‘http://cn.bing.com/HPImageArchive.aspx?format=js&idx=‘+str(i)

               +‘&n=1&nc=1361089515117&FORM=HYLH1‘

        html = urllib.urlopen(url).read()

        if html == ‘null‘:

            print ‘open & read bing error!‘

            sys.exit(-1)

        reg = re.compile(‘"url":"(.*?)","urlbase"‘,re.S)

        text = re.findall(reg,html)

        #http://s.cn.bing.net/az/hprichbg/rb/LongJi_ZH-CN8658435963_1366x768.jpg

        for imgurl in text:

            right = imgurl.rindex(‘/‘)

            name = imgurl.replace(imgurl[:right+1],‘‘)

            savepath = ‘photos/‘+ name

            urllib.urlretrieve(imgurl, savepath)

            print name + ‘ save success!‘

get_bing_backphoto()

Python3與Python2的錯誤調整：TypeError: can‘t use a string pattern on a bytes-like object 原因為Python3 findall資料類型用bytes類型，因此在Regex前應添加html = html.decode(‘utf-8‘)。 “AttributeError: ‘module‘ object has no attribute ‘urlopen‘” 原因是Python3裡的urllib模組已經發生改變，此處的urllib都應該改成urllib.request。由於bing圖片對外介面的圖片json格式變了，python第三方庫的匯入格式有變化，因此代碼調整如下：

#!/usr/bin/env python

# -*- coding:utf-8 -*-

# -*- author:nancy-*-

# python3抓取bing首頁所有背景圖片

import urllib.request,re,sys,os

def get_bing_backphoto():

    if (os.path.exists(‘photos‘)== False):

        os.mkdir(‘photos‘)

    for i in range(0,10):

        url = ‘http://cn.bing.com/HPImageArchive.aspx?format=js&idx=‘+str(i)+‘&n=1&nc=1361089515117&FORM=HYLH1‘

        html = urllib.request.urlopen(url).read()

        if html == ‘null‘:

            print( ‘open & read bing error!‘)

            sys.exit(-1)

        html = html.decode(‘utf-8‘)

        html = html.replace(‘/az/‘,‘http://s.cn.bing.net/az/‘)

        reg = re.compile(‘"url":"(.*?)","urlbase"‘,re.S)

        text = re.findall(reg,html)

        for imgurl in text :

            right = imgurl.rindex(‘/‘)

            print(imgurl)

            name = imgurl.replace(imgurl[:right+1],‘‘)

            savepath = ‘photos/‘+ name

            urllib.request.urlretrieve(imgurl, savepath)

            print (name + ‘ save success!‘)

get_bing_backphoto()

python抓取bing首頁背景圖片