MrJattParser.py 文件源码

def list_of_all_href(self,html):
        '''
        It will return all hyper links found in the mr-jatt page for download
        ''' 
        soup=BeautifulSoup(html)
        links=[]
        a_list=soup.findAll('a','touch')
        for x in xrange(len(a_list)-1):
            link = a_list[x].get('href')
            name = a_list[x]
            name = str(name)
            name=re.sub(r'<a.*/>|<span.*">|</span>|</a>|<a.*html">|<font.*">|</font>','',name)
            name=re.sub(r'^[0-9]+\.','',name)
            links.append([link,name])

        #quit()
        return links