ElongService.py 文件源码

def __parseUrls(self,page_source):
        response = HtmlResponse(url="My HTML String",body=page_source,encoding="utf-8")
        hotel_list = response.xpath("//div[@class='h_list']/div[@class='h_item']")
        for hotel in hotel_list:
            url = hotel.xpath(".//p[@class='h_info_b1']/a/@href").extract()[0]
            name = hotel.xpath(".//p[@class='h_info_b1']/a/@title").extract()[0]
            address = hotel.xpath(".//p[@class='h_info_b2']/text()").extract()[1]
            commnum = hotel.xpath(".//div[@class='h_info_comt']/a/span[@class='c555 block mt5']/b/text()").extract()
            if len(commnum)==0:
                commnum = 0
            else:commnum = commnum[0]
            self.listPageInfo.append({
                "guid": uuid.uuid1(),
                "url": url,
                "hotel_name": name,
                "OTA": self.__ota_info,
                "comm_num": commnum,
                "address": address
            })
            pass