def parse_item_forum(self,response): hxs = HtmlXPathSelector(response) item = ScrapedItem() item.title = cn(hxs.x('//h2/text()').extract()[0]) item.body = cn(hxs.x('//div[@class="t_msgfont"]').extract()[0]) item.url = response.url item.savedate = str(date.today()) item.uuid = str(abs(hash(response.url))) self.save_to_tt(item)
def __init__(self): ScrapedItem.__init__(self) self.url = ''