detail.py 文件源码

python
阅读 30 收藏 0 点赞 0 评论 0

项目:PyCrawler 作者: KillersDeath 项目源码 文件源码
def goodsUrlList(home_url):
    '''
    ?????????????????url
    :param home_url: http://www.vipmro.com/search/?&categoryId=501110
    :return:url??
    '''
    # ????????
    all_group_list = parseOptional(home_url)
    # ????goods????url
    url_list = []
    for url in all_group_list:
        # url = 'http://www.vipmro.com/search/?ram=0.9551325197768372&categoryId=501110&attrValueIds=509805,509801,509806,509807'
        # ??html
        home_page = getHtmlFromJs(url)['content'].encode('utf-8')
        html = HtmlResponse(url=url,body=str(home_page))
        urls = html.selector.xpath('/html/body/div[7]/div[1]/ul/li/div[2]/a/@href').extract()
        url_list.extend(urls)
    #     print(len(urls))
    #     print(urls)
    #     exit()
    # print(len(url_list))
    # print(url_list)
    return url_list
评论列表
文章目录


问题


面经


文章

微信
公众号

扫码关注公众号