Python小爬虫，用Python3.X编写

import urllib.request  # 导入urlib.request模块
import re  # 导入re模块


# 获得每一页的网址并返回
def get_url(pageNumber):
    new_url = "http://jandan.net/ooxx/" + 'page-' + 
              str(pageNumber) + '#comments'
    return new_url


# 打开网址并返回
def url_open(url):
    # 添加文件头，看上去像是浏览器的访问
    f = urllib.request.Request(url)
    f.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; WOW64) 
      AppleWebKit/537.36 (KHTML, like Gecko)
       Chrome/56.0.2924.87 Safari/537.36')
    # 打开网页并保存在变量中
    response = urllib.request.urlopen(url)
    html = response.read()
    return html


# 获取页码并返回
def get_page(url):
    htmlCode = url_open(url).decode('utf-8')
    pageA = htmlCode.find('current-comment-page') + 23
    pageB = htmlCode.find(']', pageA)
    pageNumber = htmlCode[pageA:pageB]
    return pageNumber


# 煎蛋网主页
main_url = "http://jandan.net/ooxx"

# *通过循环对每一页进行访问
pageNumber = int(get_page(main_url))
while pageNumber > 0:
    print(pageNumber)
    new_url = get_url(pageNumber)
    print(new_url)
    html = url_open(new_url)
    new_html = html.decode('utf-8')
    # 用正则表达式寻找图片的地址
    imageList = re.findall('src=".*.(?:jpg|gif)', new_html)

    # *对一页中的每一张图片进行遍历，抓取每一张图片
    n = 1
    for i in imageList:
        # 获取图片的地址
        j = i.split('=')[-1]
        imgUrl = 'http:' + j.split('"')[1]
        # 保存图片到文件夹（D://pythonprogram/ooxx），文件夹可自行指定

        if '.jpg' in imgUrl:
            urllib.request.urlretrieve(imgUrl, 
                                   'D://pythonprogram/ooxx/%d-%d.jpg' % (pageNumber, n))
        else:
            urllib.request.urlretrieve(imgUrl, 
                                       'D://pythonprogram/ooxx/%d-%d.gif' % (pageNumber, n))
        n += 1

    pageNumber -= 1