def parse_page_content(self,response):
item = CqspiderItem()
page_content = response.xpath('//tr[4]/td[2]//div[1]').extract()
page_content = page_content.pop()
page_content = re.sub('<[^>]+>',' ',page_content)
fil = FilterForHC(page_content)
item['project_name'] = fil.get_project_name()
item['bid_name'] = fil.get_bid_name()
item['bid_time'] = fil.get_bid_time()
item['bid_money'] = fil.get_bid_money()
return item
def parse_page_content(self, response):
item = CqspiderItem()
content = response.xpath('//*[@id="textflag"]').extract().pop()
content = re.sub('<[^>]*>', '', content)
fil = FilterForJJ(content)
item['project_name'] = fil.get_project_name()
item['bid_name'] = fil.get_bid_name()
item['bid_time'] = fil.get_bid_time()
item['bid_money'] = fil.get_bid_money()
return item
def parse_page_content(self, response):
item = CqspiderItem()
page_content = response.xpath(
'//*[@id="bulletinContent"]/tbody').extract().pop()
page_content = re.sub('<[^>]+>', ' ', page_content)
fil = FilterForCQS(page_content)
item['project_name'] = fil.get_project_name()
item['bid_name'] = fil.get_bid_name()
item['bid_time'] = fil.get_bid_time()
item['bid_money'] = fil.get_bid_money()
return item
def parse_page_content(self, response):
item = CqspiderItem()
page_content = response.xpath('//*[@id="tblInfo"]').extract()
if page_content:
page_content = page_content.pop()
page_content = re.sub('<[^>]+>', ' ', page_content)
fil = FilterForBB(page_content)
item['project_name'] = fil.get_project_name()
item['bid_name'] = fil.get_bid_name()
item['bid_time'] = fil.get_bid_time()
item['bid_money'] = fil.get_bid_money()
return item