def __init__(self, postedUrlSet=None):
BaseParser.__init__(self)
self.baseurl = "http://news.163.com/rank/"
#
self.__postedUrlSet = postedUrlSet
#要抽取的类别在页面中 div(.tabBox)的序号。根据这个抽取指定的信息块的url
self.__typeIndexMap = {"ent": 5, "news": 1}
def __init__(self, postedUrlSet=None):
BaseParser.__init__(self)
self.baseurl = "http://news.163.com/rank/"
#
self.__postedUrlSet = postedUrlSet
#要抽取的类别在页面中 div(.tabBox)的序号。根据这个抽取指定的信息块的url
self.__typeIndexMap = {
"ent":5,
"news":1
}
def __init__(self, message):
BaseParser.__init__(self, message)
self.is_success()
def __init__(self, postedUrlSet=None):
BaseParser.__init__(self)
#已获取并发表的集合
self.__postedUrlSet = postedUrlSet
def __init__(self):
BaseParser.__init__(self)
self.name = "xiachufang"
self.baseurl = "http://www.xiachufang.com/recipe/"
#起始位置
self.__start = 0
def __init__(self):
BaseParser.__init__(self)
self.name = "xiachufang"
self.baseurl = "http://www.xiachufang.com/recipe/"
def __init__(self, postedUrlSet=None):
BaseParser.__init__(self)
#已获取并发表的集合
self.__postedUrlSet = postedUrlSet
def __init__(self, urlSet=None):
BaseParser.__init__(self)
self.baseUrl = "http://news.qq.com"
self.oriUrl = "http://news.qq.com/newssh/qiwen.shtml"
self.__postedSet = urlSet
