class NovelSpider1(NovelSpiderBase): # name = "NovelXinShuBao" name = SpiderTypes.getTypeName_XinShuBao() def __init__(self): super().__init__() def getXpathMainInfo(self, response): return response.xpath( '//div[@class="box_con"]/div[@id="maininfo"]/div[@id="info"]') def getStrMainInfo_Name(self, info): return info.xpath('./h1/text()').extract()[0] def getStrMainInfo_Author(self, info): return info.xpath('./p/text()').extract()[0] def getXpathList(self, response): return response.xpath('//div[@id="btycz"]/div[@id="list"]/ul/li') def getStrItem_Link(self, item): link = item.xpath('./a/@href').extract()[0] return link def getStrItem_Idex(self, item): return item.xpath('./a/text()').extract()[0] def getXpathItem_Main(self, response): return response.xpath( '//div[@class="content_read"]/div[@class="box_con"]') def getStrItem_Title(self, xpath_main): return xpath_main.xpath('./div[@class="bookname"]/h1/text()').extract()[0]\ .strip()\ .replace(' ','')\ .replace('\r', '')\ .replace('\n', '')\ .replace('\t', '') def getStrItem_Content(self, xpath_main): return xpath_main.xpath('./div[@id="content"]/text()').extract()
def getScrapyType(self): return SpiderTypes.getTypeName_XinShuBao()