python 图片爬虫

#!/usr/bin/env python

#coding:utf-8

import urllib

import re

def GetHtml(url):

    """获取HTML页面所有元素."""

    page =  urllib.urlopen(url)

    html = page.read()

    return html

def GetImg(html):

    """ 获取HTML页面所有.jpg图片."""

    reg = r'src="(.+?\.jpg)"'

    imgre = re.compile(reg)

    imglist = re.findall(imgre, html)

    x = 0

    for imgurl in imglist:

        urllib.urlretrieve(imgurl, '%s.jpg' %x, cbx)

        x += 1

        print "img: %s is done!" %x

def cbx(a, b, c):

    """显示下载进度.

    @a: 已经下载的数据块

    @b: 数据块大小

    @c: 远程文件的大小

    """

    per = 100.0 * a * b / c

    if per > 100:

        per = 100

    print "%.2f%%" %per

html = GetHtml("http://www.baidu.com")

print GetImg(html)