from urllib import request
import threading
from time import sleep,ctime
from html import parser
def downjpg( filepath,FileName ="default.jpg" ):
 try:
  web = request.urlopen( filepath)
  print("訪問(wèn)網(wǎng)絡(luò)文件"+filepath+"\n")
  jpg = web.read()
  DstDir="E:\\image\\"
  print("保存文件"+DstDir+FileName+"\n")
  try:
   File = open( DstDir+FileName,"wb" )
   File.write( jpg)
   File.close()
   return
  except IOError:
   print("error\n")
   return
 except Exception:
  print("error\n")
  return
def downjpgmutithread( filepathlist ):
 print("共有%d個(gè)文件需要下載"%len(filepathlist))
 for file in filepathlist:
  print( file )
 print("開始多線程下載")
 task_threads=[] #存儲(chǔ)線程
 count=1
 for file in filepathlist:
  t= threading.Thread( target=downjpg,args=(file,"%d.jpg"%count) )
  count=count+1
  task_threads.append(t)
 for task in task_threads:
  task.start()
 for task in task_threads:
  task.join() #等待所有線程結(jié)束
 print("線程結(jié)束")
class parserLinks( parser.HTMLParser):
 filelist=[]
 def handle_starttag(self,tag,attrs):
  if tag == 'img':
   for name,value in attrs:
    if name == 'src':
     print( value)
     self.filelist.append(value)
     #print( self.get_starttag_text() )
 def getfilelist(self):
  return self.filelist
def main(WebUrl):
 #globals flist
 if __name__ == "__main__":
  lparser = parserLinks()
  web = request.urlopen( WebUrl )
  #context= web.read()
  for context in web.readlines():
   _str="%s"%context
   try:
    lparser.feed( _str)
   except parser.HTMLParseError:
    #print( "parser error")
    pass
  web.close()
  imagelist= lparser.getfilelist()
  downjpgmutithread( imagelist)  
  #downjpgmutithread( flist)
#WebUrl="http://www.baidu.com/" #要抓去的網(wǎng)頁(yè)鏈接,默認(rèn)保存到e盤
WebUrl="http://hi.baidu.com/yuyinxuezi/item/df0b59140a06be27f6625cd4"
main(WebUrl)