def parse_news(self, response, title_, date_): item = GenericItem() self.get_id(response, item) self.get_url(response, item) item['title'] = title_ item['date'] = date_ self.get_source(response, item) self.get_body(response, item) #!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!remenber to Retrun Item after parse if item['body']: return item
def parse_news(self,response): item = GenericItem() self.get_id(response,item) self.get_url(response,item) self.get_source(response, item) self.get_title(response, item) self.get_date(response, item) self.get_body(response, item) #!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!remenber to Retrun Item after parse if item['body']: return item
def parse_news(self,response): yesterday = datetime.date.today() - datetime.timedelta(days=1) reday = yesterday.strftime('%d') item = GenericItem() self.get_id(response,item) self.get_url(response,item) self.get_source(response,item) self.get_title(response,item) self.get_date(response,item) self.get_body(response,item) #!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!remenber to Retrun Item after parse if item['body'] and item['date'][6:8] == reday: return item
def parse(self, response): yesterday = datetime.date.today() yesterday = yesterday.strftime('%Y%m%d') for i in range(19): item = GenericItem() self.get_id(response, item) self.get_url(response, item, i) self.get_source(response, item) self.get_title(response, item, i) self.get_date(response, item, i, yesterday) self.get_body(response, item, i) #!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!remenber to Retrun Item after parse if item['url'] and item['date'] == str( yesterday) + '000000' and item['body']: yield item else: continue