def parse(self,response):
item = biquItem()
item['bookname'] = response.xpath('//*[@class="bottem1"]/a[3]/text()').extract()[0]
item['chaptername'] = response.xpath('//*[@class="bookname"]/h1/text()').extract()[0]
item['content'] = response.xpath('//*[@id="content"]/text()').extract()
return item
def parse(self, response):
item = biquItem()
#item['bookname'] = response.xpath('//h1[@id="chaptertitle"]/text()').extract()
item['bookname'] = response.xpath(
'//meta[@name="keywords"]/@content').extract()[0].split(',')[0]
#print(str(response.body).encode('utf-8').decode('gbk'))
item['chaptername'] = response.xpath(
'//meta[@name="keywords"]/@content')[0].extract().split(',')[1]
item['content'] = response.xpath(
'//div[@id="nr1"]/text()').extract()[0]
return item
def parse(self, response):
item = biquItem()
#item['bookname'] = response.xpath('//h1[@id="chaptertitle"]/text()').extract()
item['bookname'] = response.xpath(
'//meta[@name="keywords"]/@content').extract()[0].split(',')[0]
#print(str(response.body).encode('utf-8').decode('gbk'))
item['chaptername'] = response.xpath(
'//meta[@name="keywords"]/@content')[0].extract().split(',')[1]
item['booktype'] = response.xpath(
'//meta[@name="description"]/@content').extract()[0].split(
'提供了')[1].split('创作的')[1].split('小说')[0]
#item['booktype'] = re.findall(r'/w*',item['booktype'])
item['content'] = response.xpath(
'//div[@id="novelcontent"]/p/text()').extract()[0]
print(item['booktype'])
return item