python3.X爬虫-图片获取

通过python3.x 来实现一个简单的爬虫功能，把网页上想要的图片能通过代码爬取到本地。

#coding=utf-8

import re,codecs,sys,os,time
import urllib.request

def createFile():
    if (os.path.exists('photos')== False):
        os.mkdir('photos')

def extract(text, sub1, sub2):
    """
    extract a substring from text between first
    occurances of substrings sub1 and sub2
    """
    return text.split(sub1, 1)[-1].split(sub2, 1)[0]

def getHtml(url):
    createFile()
    fp = urllib.request.urlopen(url)
    url = fp.read()
    encoding = extract(str(url).lower(), 'charset=', '"')
    if encoding:
        html = url.decode(encoding)
    else:
        print("Encoding type not found!")
    fp.close()
    return html

def getImg(html):
    #print (html)
    #下面正则是匹配图片地址，可以根据页面实际代码进行修改
    reg = r'.+src="(.+?\.jpg.+)" data_org_bimg'
    imgre = re.compile(reg,re.I)
    imglist = imgre.findall(html)
    x = 0
    for imgurl in imglist:
        print (imgurl)
        now = int(time.time())
        #print (now)
        savepath = 'photos/'+ str(now)+'.jpg'
        print (savepath)
        urllib.request.urlretrieve(imgurl,savepath)
        x+=1
    if (x == 0):
        return "loading failed";
    else:
        return "loading successed";


html = getHtml("http://photo.poco.cn/lastphoto-htx-id-4877933-p-0.xhtml")
print (getImg(html))