def parse_book(self, response):
sel = Selector(response)
items = []
item = doubanBookItem()
item['title'] = sel.xpath(
'//*[@id="wrapper"]/h1/span/text()').extract()
item['author'] = sel.xpath(
'//*[@id="info"]/span[1]/a/text()').extract()
item['intro_content'] = sel.xpath(
'//*[@id="link-report"]/div[1]/div/p[1]/text()').extract()
item['intro_author'] = sel.xpath(
'//*[@id="content"]/div/div[1]/div[3]/div[3]/div/div/p[1]/text()').extract()
item['image_urls'] = sel.xpath(
'//*[@id="mainpic"]/a/img/@src').extract()
items.append(item)
print('success add one pagecontent')
if len(items) > 30:
raise CloseSpider('enough')
yield item
def parse_book(self, response):
sel = Selector(response)
sel = sel.xpath('//')
for sel in sels:
item = doubanBookItem()
item['title'] = sel.xpath('//*[@id="wrapper"]/h1/span/text()').extract()
item['author'] = sel.xpath('//*[@id="info"]/span[1]/a').extract()
item['intro_content'] = sel.xpath('//*[@id="link-report"]/div[1]/div/p[1]/text()').extract()
item['intro_author'] = sel.xpath('//*[@id="content"]/div/div[1]/div[3]/div[3]/div/div/p[1]').extract()
items.append(item)
print('success add one pagecontent')
if len(items) > 30:
raise CloseSpider('enough')
return items
def parse_book(self, response):
sel = Selector(response)
sel = sel.xpath('//')
for sel in sels:
item = doubanBookItem()
item['title'] = sel.xpath(
'//*[@id="wrapper"]/h1/span/text()').extract()
item['author'] = sel.xpath('//*[@id="info"]/span[1]/a').extract()
item['intro_content'] = sel.xpath(
'//*[@id="link-report"]/div[1]/div/p[1]/text()').extract()
item['intro_author'] = sel.xpath(
'//*[@id="content"]/div/div[1]/div[3]/div[3]/div/div/p[1]'
).extract()
items.append(item)
print('success add one pagecontent')
if len(items) > 30:
raise CloseSpider('enough')
return items
