一个简单的爬虫抓取图片程序

一个简单的爬虫抓取图片小程序，能够快速获取大量图片，并将图片保存至指定文件夹，省去了一个一个下载图片的麻烦。

import urllib.request
import os
import random  #使用代理IP是用到此模块

def url_open(url):
    req=urllib.request.Request(url)
    #为请求设置user-agent,使得程序看起来更像一个人类
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36')
    #代理IP，使用户能以不同IP访问，从而防止被服务器发现
    '''iplist=['1.193.162.123:8000', '1.193.162.91:8000', '1.193.163.32:8000']
    proxy_support = urllib.request.ProxyHandler({'http':random.choice(iplist)})
    opener = urllib.request.build_opener(proxy_support)
    opener.addheaders = [('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.154 Safari/537.36 LBBROWSER')]

    urllib.request.install_opener(opener)'''

    response = urllib.request.urlopen(req)
    html = response.read()
    return html


def get_page(url):

    html = url_open(url).decode('utf-8')
    a = html.find('current-comment-page')+23
    b = html.find(']',a)

    #print(html[a:b])
    return html[a:b]


def find_imgs(url):
    html = url_open(url).decode('utf-8')
    img_addrs = []

    a=html.find('img src=')
    while a!=-1:
        b=html.find('.jpg', a, a+140)
        if b != -1:
            if html[a+9] != 'h':
                img_addrs.append('http:'+html[a+9:b+4])
            else:
                img_addrs.append(html[a+9:b+4])
        else:
            b = a + 9

        a = html.find('img src=', b)
 
    return img_addrs


def save_imgs(folder,img_addrs):
    for each in img_addrs:

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

#主函数：
def down(folder='net',pages=10):
    os.mkdir(folder)   #创建目录
    os.chdir(folder)   #修改目录途径

    url = "http://jandan.net/pic/"
    page_num = int(get_page(url))

    for i in range(pages):
        page_num -= 1
        page_url = url + 'page-' + str(page_num) + '#comments'
        img_addrs = find_imgs(page_url)
        save_imgs(folder, img_addrs)


if __name__ == '__main__':
    down()