マルチスレッド HTTP ダウンローダーの Python 実装の例

#解析host和path
def analyHostAndPath(totalUrl):
  protocol,s1 = urllib.splittype(totalUrl)
  host, path = urllib.splithost(s1)
  if path == '':
    path = '/'
  return host, path

#解析port
def analysisPort(host):
  host, port = urllib.splitport(host)
  if port is None:
    return 80
  return port

#解析filename
def analysisFilename(path):
  filename = path.split('/')[-1]
  if '.' not in filename:
    return None
  return filename

import socket
from analysisUrl import port,host

ip = socket.gethostbyname(host)
s = socket.socket(socket.AF_INET,socket.SOCK_STREAM)
s.connect((ip, port))

print "success connected webServer！！"

from analysisUrl import path, host, port

packet = 'GET ' + path + ' HTTP/1.1\r\nHost: ' + host + '\r\n\r\n'　

def getLength(self):
    s.send(packet)
    print "send success!"
    buf = s.recv(1024)
    print buf
    p = re.compile(r'Content-Length: (\d*)')
    length = int(p.findall(buf)[0])
    return length, buf

def download(self):
    file = open(self.filename,'wb')
    length,buf = self.getLength()
    packetIndex = buf.index('\r\n\r\n')
    buf = buf[packetIndex+4:]
    file.write(buf)
    sum = len(buf)
    while 1:
      buf = s.recv(1024)
      file.write(buf)
      sum = sum + len(buf)
      if sum >= length:
        break
    print "Success!!"

if __name__ == "__main__":
  start = time.time()
  down = downloader()
  down.download()
  end = time.time()
  print "The time spent on this program is %f s"%(end - start)

def getLength(self):
    opener = urllib2.build_opener()
    req = opener.open(self.url)
    meta = req.info()
    length = int(meta.getheaders("Content-Length")[0])
    return length

def get_range(self):
    ranges = []
    length = self.getLength()
    offset = int(int(length) / self.threadNum)
    for i in range(self.threadNum):
      if i == (self.threadNum - 1):
        ranges.append((i*offset,''))
      else:
        ranges.append((i*offset,(i+1)*offset))
    return ranges

def downloadThread(self,start,end):
    req = urllib2.Request(self.url)
    req.headers['Range'] = 'bytes=%s-%s' % (start, end)
    f = urllib2.urlopen(req)
    offset = start
    buffer = 1024
    while 1:
      block = f.read(buffer)
      if not block:
        break
      with lock:
        self.file.seek(offset)
        self.file.write(block)
        offset = offset + len(block)

  def download(self):
    filename = self.getFilename()
    self.file = open(filename, 'wb')
    thread_list = []
    n = 1
    for ran in self.get_range():
      start, end = ran
      print 'starting:%d thread '% n
      n += 1
      thread = threading.Thread(target=self.downloadThread,args=(start,end))
      thread.start()
      thread_list.append(thread)

    for i in thread_list:
      i.join()
    print 'Download %s Success!'%(self.file)
    self.file.close()

from distutils.core import setup
import py2exe

setup(console=["multiThreadDownload.py"])