detail.py 文件源码

def parseOptional(url):
    '''
    ??url???????????url
    :param url: http://www.vipmro.com/search/?&categoryId=501110
    :return:['http://www.vipmro.com/search/?categoryId=501110&attrValueIds=509801,512680,509807,509823']
    '''
    # ??html
    home_page = getHtmlFromJs(url)['content'].encode('utf-8')
    html = HtmlResponse(url=url,body=str(home_page))
    # ????
    xi_lie = html.selector.xpath('/html/body/div[5]/div[6]/ul/li/a/@href').re(r'ValueIds=(\d+)')
    # ????????
    fen_duan = html.selector.xpath('/html/body/div[5]/div[10]/ul/li/a/@href').re(r'ValueIds=(\d+)')
    # ?????
    tuo_kou_qi = html.selector.xpath('/html/body/div[5]/div[14]/ul/li/a/@href').re(r'ValueIds=(\d+)')
    # ????
    an_zhuang = html.selector.xpath('/html/body/div[5]/div[12]/ul/li/a/@href').re(r'ValueIds=(\d+)')
    # ????????
    all_group = list(itertools.product(xi_lie,fen_duan,tuo_kou_qi,an_zhuang))
    _url = url + '&attrValueIds='
    url_list = map(lambda x:_url+','.join(list(x)),all_group)

    return url_list