meps_ie.py 文件源码

def get_name(self, tree):
        name = tree.xpath('//li[@class="mep_name"]')[0]
        name = self.rm_a.clean_html(name)
        name = html.tostring(name).decode('utf-8')
        name = re.sub(r'[\t\n]', r'', name)
        name = name.split('<br>')
        name = [html.fromstring(x).text_content() for x in name]
        name = ' '.join(name)
        return name