Python学习历程

第一写博客，希望大家多提点意见！谢谢

python简单爬虫练习：

import urllib.request
import os  ##新建文件夹
## 爬取网页 HTML 的函数
def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.26 Safari/537.36 Core/1.63.6726.400 QQBrowser/10.2.2265.400')
    response = urllib.request.urlopen(url)
    html = response.read()
    return html

## 爬取首页信息
def get_page(url):
    html = url_open(url).decode('utf-8')
    a = html.find('current-comment-page') + 23
    b = html.find(']',a)
    return html[a:b]

## 爬取图片位置
def find_imgs(url):
    html = url_open(url).decode('utf-8')
    img_addrs = []
    a = html.find('img src=')
    while a != -1:
        b = html.find('.gif',a,a+255)
        if b != -1:
            img_addrs.append(html[a+11:b+4])
        else:
            b = a + 9
        a = html.find('img src=',b)
    return img_addrs
    	
## 保存爬取的图片
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 download(folder='保存到的文件名',pages = 7):
    os.mkdir(folder)
    os.chdir(folder)
    url = 'http://jandan.net/ooxx/'
    page_num = int(get_page(url))
    for i in range(pages):
        page_num -= i
        page_url = url + 'page-' + str(page_num) + '#comments'
        img_addrs = find_imgs(page_url)
        save_imgs(folder,img_addrs)
        
## 调用主函数
if __name__ == '__main__':
    download()

有什么不对，希望大家指出来！再次感谢