#encoding=utf-8#author: walker#date: 2016-04-14#summary: 用協(xié)程/線程池并發(fā)檢驗代理有效性import os, sys, timeimport requestsfrom concurrent import futurescur_dir_fullpath = os.path.dirname(os.path.abspath(__file__))Headers = {      'Accept': '*/*',      'User-Agent': 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET4.0C; .NET4.0E)',    }#檢驗單個代理的有效性#如果有效，返回該proxy；否則，返回空字符串def Check(desturl, proxy, feature):  proxies = {'http': 'http://' + proxy}  r = None #聲明  exMsg = None  try:    r = requests.get(url=desturl, headers=Headers, proxies=proxies, timeout=3)  except:    exMsg = '* ' + traceback.format_exc()    #print(exMsg)  finally:    if 'r' in locals() and r:      r.close()  if exMsg:    return ''  if r.status_code != 200:    return ''  if r.text.find(feature) < 0:    return ''  return proxy#輸入代理列表(set/list)，返回有效代理列表def GetValidProxyPool(rawProxyPool, desturl, feature):  validProxyList = list()  #有效代理列表  pool = futures.ThreadPoolExecutor(8)  futureList = list()  for proxy in rawProxyPool:    futureList.append(pool.submit(Check, desturl, proxy, feature))  print('/n submit done, waiting for responses/n')  for future in futures.as_completed(futureList):    proxy = future.result()    print('proxy:' + proxy)    if proxy: #有效代理      validProxyList.append(proxy)  print('validProxyList size:' + str(len(validProxyList)))  return validProxyList#獲取原始代理池def GetRawProxyPool():  rawProxyPool = set()  #通過某種方式獲取原始代理池......  return rawProxyPoolif __name__ == "__main__":  rawProxyPool = GetRawProxyPool()  desturl = 'http://...'    #需要通過代理訪問的目標地址  feature = 'xxx'    #目標網(wǎng)頁的特征碼  validProxyPool = GetValidProxyPool(rawProxyPool, desturl, feature)