python爬虫中采集中遇到的问题整理

ckjar = cookielib.MozillaCookieJar()
cookies = urllib2.HTTPCookieProcessor(ckjar)   #定义cookies对象
def httpRequest(url):
 '''''
 @summary: 网络请求
 '''
 try:
  ret = None
  SockFile = None
  request = urllib2.Request(url)
  request.add_header('User-Agent', 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; SV1; .NET CLR 1.1.4322)')
  request.add_header('Pragma', 'no-cache')
  opener = urllib2.build_opener(cookies)  #传递cookies对象
  SockFile = opener.open(request)
  ret = SockFile.read()
 finally:
  if SockFile:
   SockFile.close()
 return ret

content = content.decode('gbk', 'ignore')  #将gbk编码转为unicode编码

content = content.encode('utf-8', 'ignore') #将unicode编码转为utf-8编码