from urllib.request import urlopen

from urllib.request import urlretrieve

from bs4 import BeautifulSoup as da

import re

import os

import shutil

name=0

print('这是一个爬虫程序，爬取的是壁纸，下载地址是：d:/tupianpachongtest')

print('下载图片很多，若要中断：Ctrl+C-----------wanglei')

try:

     os.mkdir(r'd:/tupianpachongtest')#初始化文件夹

except FileExistsError as e:

     shutil.rmtree('d:/tupianpachongtest')

     os.mkdir(r'd:/tupianpachongtest')

def get_urllist():#获取每期的网址

     url0='http://www.acfun.cn'

     urllist=[]

     page=1

     while page <=11:

          url="http://www.acfun.cn/u/1094623.aspx#page="+str(page)

          html= urlopen(url)

          bs0bj=da(html,"lxml")

          imglist = bs0bj.findAll("a",{"href":re.compile("/a/ac")})

     #imgdict=dict(imglist.attrs)

     #imgt=imgdict['herf']

     #print(type(imglist))

          for img in imglist:

               imgdict=dict(img.attrs)

               imgt=imgdict['href']

               urllist.append(url0+imgt)

          page +=1

     return(urllist)#图片网址列表

urllist=get_urllist()

ulist=[]

def getlink(url):#获取图片链接

    html= urlopen(url)

    bs0bj=da(html,"lxml")

    imglist = bs0bj.findAll("img",{"src":re.compile("http://imgs.*?live.*?jpg")})

    for img in imglist:

        imgdict=dict(img.attrs)

        imgt=imgdict['src']

        ulist.append(imgt)

    return(ulist)

s=1

print('爬取进度：0%')

for url0 in urllist:#对每个网址提取图片链接

     imgurllist=getlink(url0)

     b=len(imgurllist)

     #os.mkdir(r'd:/tupianpachongtest/%s'%s)

     for url in imgurllist:#下载每个链接并保存

          #urlretrieve(url,'d:\\tupianpachongtest\\%s\\%s.jpg'%(s,name))

          urlretrieve(url,'d:\\tupianpachongtest\\%s.jpg'%name)

          name+=1

          #print(int((name/len(imgurllist))*100),'%')

     print('爬取进度：',end='')

     print(int((s/len(urllist))*100),'%')

     s=s+1