def city_list(url):

    '''

    获取58站点的所有城市链接入口的 url 和 城市名称

    :param url:

    :return:

    '''

    try:

        pattern = r'.//dl[@id="clist"]'

        root = utils.get_root(url)

        data = root.xpath(pattern)

        if len(data) > 0:

            r_data = etree.tostring(data[0], encoding='utf-8')

            pattern = re.compile(r'\s*<a href="(\S+?)"[\s\S]*?>(\S+?)</a>\s*', re.S) # 表示多行匹配.将这个字符串作为一个整体，在整体中进行匹配。

            l_data = re.findall(pattern, r_data)

            if l_data is not None:

                l_data = list(set(l_data))

                return l_data

    except Exception, e:

        raise e

def get_root(url):

    '''

    获取url的root节点

    :param url:

    :return:

    '''

    try:

        if url is not None:

            request = urllib2.Request(url)

            response = urllib2.urlopen(request)

            html = response.read()

            root = etree.HTML(html)

            return root

    except Exception, e:

        raise e