Python爬虫之抓图

　　从"百度图片（http://image.baidu.com/）"的首页下载图片

 

# -*- coding: utf-8 -*-
import urllib
import re
import sys

url = 'http://image.baidu.com/'

# 获取URL的源代码
def get_html(url):
    page = urllib.urlopen(url)
    html = page.read()
    return html

# 下载图片到本地
def get_image():
    pattern_image = re.compile('img src="(.+\.jpg)')
    image_list = re.findall(pattern_image, get_html(url))
    for image in image_list:
        temp = [] 
        temp = image.split('/')
        filename = './image/' + temp[-1]
        print '开始下载',image
        try:            
            urllib.urlretrieve(image, filename, download)
        except:
            print "Unexpected error:", sys.exc_info()[0]
        finally:
            print '下载完成'
    print '总共下载：',len(image_list),'张图片'

# 展示下载进度
def download(a, b, c):
    per = 100.0 * a * b / c
    if per > 100 :
        per = 100
    print '%.2f%%' % per
    
get_image()

View Code