python爬取贴吧图片

import urllib.request
import urllib.parse
import re
import os

"""
    爬取百度贴吧
"""

def getSubUrl(url):
    """
        获得该路径下子url
    """
    headers = {
        "User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36"
    }
    html = urllib.request.urlopen(urllib.request.Request(url,headers=headers)).read().decode('utf-8')
    subUrl = re.compile(r'href="(/p/.*?)"').findall(html)
    for i in subUrl:
        getImages("http://tieba.baidu.com"+i)



def getImages(url):
    """
        爬取该路径下面的图片，存放到文件夹中
    """
    print(url+"开始")
    html = urllib.request.urlopen(url).read().decode('utf-8')
    picture_url_list = re.compile('class="BDE_Image" src="(.*?)"').findall(html)
    if not os.path.exists('e:/photos'):
        os.mkdir('e:/photos')
        print("创建目录e:/photos")
    #os.chdir('e:/photos')
    #每个连接单独创建目录
    dir = 'e:/photos/'+url.split(r"/p/")[1]
    if not os.path.exists(dir):
        os.mkdir(dir)
        print("创建目录"+dir)
    os.chdir(dir)

    #下载图片
    for i in range(len(picture_url_list)):
        picture_name = url.split(r"/p/")[1] + str(i) + '.jpg'

        try:
            urllib.request.urlretrieve(picture_url_list[i], picture_name)
            print("成功下载： " + picture_url_list[i])
        except:
            print("Fail to download " + picture_url_list[i])

    #删除空文件夹
    if not os.listdir(dir):
        os.chdir('e:/photos')
        os.rmdir(dir)
        print("删除空文件夹：" + dir)


if __name__ == '__main__':
    kw = input("请输入贴吧名称")
    startPage = int(input("请输入起始页"))
    endPage = int(input("请输入结束页"))
    for i in range(startPage,endPage+1):
        url = "http://tieba.baidu.com/f?" + urllib.parse.urlencode({"kw":kw}) \
              + "&pn=" + str(i*50-50)
        getSubUrl(url)