python学习 - 下载网页内所有的图片

下载网页内所有的图片

#codeing:utf-8

import urllib
import re
import sys
import os


url = 'http://tieba.baidu.com/p/1753935195'
# with open('F:\hack\python\python_project\html\htmlpage.html', 'w') as f:
#     f.write(htmlcode)

def getHtml(url):
    page = urllib.urlopen(url)
    htmlcode = page.read()
    return htmlcode


def getPicList(htmlcode):
    reg = r'src="(.+?\jpg)" width'
    reg_pic = re.compile(reg)
    piclist = reg_pic.findall(htmlcode)
    return piclist

def downPic(piclist):
    cur_dir = sys.path[0]
    img_dir = cur_dir + '\\img_dir\\'
    if not os.path.exists(img_dir):
        os.makedirs(img_dir)

    for pic in piclist:
        str_array = pic.split('/')
        filename = str_array[len(str_array) - 1]
        file = img_dir + filename
        if os.path.exists(file):
            print(file + " existed")
        else:
            urllib.urlretrieve(pic,file)
        # x = x + 1


htmlcode = getHtml(url)
piclist = getPicList(htmlcode)

downPic(piclist)