Esempio n. 1
0
def Crawl_Malitary_Title(response):
    _title = []
    _link = []
    item = DmozItem()
    hxs = HtmlXPathSelector(response)
    item['title'] = hxs.select("//div[@class='dd_bt']//a/text()").extract()
    item['link'] = hxs.select("//div[@class='dd_bt']//a/@href").extract()
    dataOptionGet = DataOptionGet()
    latest_link = dataOptionGet.get_Last_Link_MA()
    for i in range(len(item['title'])):
        if "http://www.chinanews.com"+str(item['link'][i]) == latest_link:
            break
        _title.append(item['title'][i])
        _link.append(item['link'][i])
    if len(_link) > 0:
        dataOptionSave = DataOptionSave()
        dataOptionSave.Mali_Title_Save(_link,_title)