def Crawl_China_Title(response):
_title = []
_link = []
item = DmozItem()
hxs = HtmlXPathSelector(response)
sites = hxs.select('//a')
dataOptionGet = DataOptionGet()
latest_link = dataOptionGet.get_Last_Link_CH()
for site in sites:
item['title'] = site.select("//a[@target='_blank' and @class='linkto']/text()").extract()
item['link'] = site.select("//a[@target='_blank' and @class='linkto']/@href").extract()
break
for i in range(len(item['title'])):
if "http://news.qq.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.Chnews_Title_Save(str(_link), str(_title))
