python网络爬虫爬取图片代码

因为刚学的python，有些地方的代码还需要改进。后续有时间会继续改进代码。
此文章是基于Python 3.6.0a4 进行的开发，目的是爬取网站的图片，打包成一个文件夹
本来的目的是想基于主页进行遍历所有的图集，进去之后再遍历所有的图片进行下载，结果发现url地址根本就不需要我遍历，直接用数字进行累加就可以，晕倒。
所以改成了一个很简单的代码。

import urllib.request
import re
import os

def  url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.106 Safari/537.36')
    response = urllib.request.urlopen(req)
    html = response.read()
    return html

def get_page(html):
    html = html.decode('utf-8')
    return html

def save_imgs(folder ,filename):
    name = filename.split('/')[-1]
    with open(name ,'wb') as f:
        img = url_open(filename)
        f.write(img)


def  download_pic(folder = 'picss2',pages = 1000):

    url = 'http://luluhei.tv/album/'
    os.mkdir(folder)
    os.chdir(folder)
    '''
    ip_address = 'http://luluhei.tv'

    re_main = re.compile(r'<a href="/album/.*>')
    html_main = url_open(url)
    find_main = re.findall(re_main,html_main)
    urllib.parse.quote()
    print(filename)
    '''

    for num in range(3510,3550):


        html_findimg = get_page(url_open(url + str(num)))

        re_findimg = re.compile(r'<img src=.*jpg')
        find_findimg = re.findall(re_findimg,html_findimg)

        for img_src in find_findimg:
            filename = img_src[10:]
            save_imgs(folder,filename)


if __name__ == '__main__':
    download_pic()