import urllib.request 
import requests 
import time 
import os 
import shutil 
from lxml import html 
def getPage(): 
  ''''' 
  從網(wǎng)站首頁(yè)獲取妹子的網(wǎng)址 
  ''' 
  fres=open('res.txt','w') 
  htm=urllib.request.urlopen('http://www.mzitu.com/') 
  out=htm.read() 
  out=html.fromstring(out) 
  urls=[] 
  for res in out.xpath('//ul[@id="pins"]/li/a/@href'): 
    urls.append(res) 
  for r in urls: 
    fres.write(r) 
    fres.write('\n\r') 
  fres.close() 
  return urls 
def getPiclink(url): 
  ''''' 
  獲取一個(gè)妹子的標(biāo)題和她的所有圖片地址 
  ''' 
  i_headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:55.0) Gecko/20100101 Firefox/55.0'} 
  sel=urllib.request.Request(url, headers=i_headers) 
  #使用代理瀏覽器訪問(wèn)網(wǎng)站 
  sel.add_header('Referer', 'http://www.mzitu.com/') 
  #將referer字段添加到請(qǐng)求包里 
  sel=urllib.request.urlopen(sel).read() 
  sel=html.fromstring(sel) 
  total=sel.xpath('//div[@class="pagenavi"]/a[last()-1]/span/text()')[0] 
  title=sel.xpath('//h2[@class="main-title"]/text()')[0] 
  jpglist=[] 
  for i in range(int(total)): 
    link='{}/{}'.format(url, i+1) 
    s=html.fromstring(urllib.request.urlopen(link).read()) 
    jpg=s.xpath('//div[@class="main-image"]/p/a/img/@src')[0] 
    jpglist.append(jpg) 
  return title,jpglist 
def downloadJpg(title,piclist,link): 
  ''''' 
  下載getPiclink()獲取到的妹子的圖片 
  ''' 
  k=1 
  count=len(piclist) 
  dirname=u"[%sP]%s" %(str(count),title) 
  if os.path.exists(dirname): 
    shutil.rmtree(dirname) 
  os.mkdir(dirname) 
  i_header={} 
  i_header['Referer']=link 
  #將getPiclink()獲取到的妹子的首頁(yè)網(wǎng)址作為referer字段的值 
  for i in piclist: 
    filename='%s/%s/%s.jpg' %(os.path.abspath('.'),dirname, k) 
    with open(filename,'wb') as jpg: 
      jpg.write(requests.get(i, headers=i_header).content) 
    #將referer字段添加到請(qǐng)求包里并下載圖片 
      time.sleep(0.5) 
    k+=1 
if __name__=='__main__': 
  for link in getPage(): 
    title,pic=getPiclink(link) 
    downloadJpg(title,pic,link) 
  print('OK!')