def parse_item(self, response):
url = response.url
item = ItemLoader(item=MeizituItem(), response=response)
item.add_xpath('title', '//h2/a/text()')
item.add_xpath('image_urls', '//div[@id="picture"]//img/@src')
item.add_value('url', url)
return item.load_item()
def parse_item(self, response):
print('parse=========', response.url)
item = ItemLoader(item=MeizituItem(), response=response)
item.add_value('url', response.url)
item.add_value('page', response.url[len(self.host):].replace('/', '_'))
# item.add_xpath('tags', "//ul[@id='article']/li/h2/a/text()")
item.add_xpath('tags', "/html/body/div[2]/ul[@id='article']/li/h2/a/text()")
item.add_xpath('image_urls', "//div[@class='pic']/a/img/@src")
return item.load_item()
def parse_detail(self, response):
item = MeizituItem()
title = response.xpath('//h2/a/text()').get()
image_urls = response.xpath('//div[@id="picture"]//img/@src').extract()
url = response.url
item['title'] = title
item['image_urls'] = image_urls
item['url'] = url
yield item
def parse(self, response):
node_list = response.xpath("//ul[@id='pins']/li")
for node in node_list:
item = MeizituItem()
item['img_name'] = node.xpath('./span/a/text()').extract_first()
item['img_link'] = node.xpath('./span/a/@href').extract_first()
# print(item['img_link'])
yield scrapy.Request(url=item['img_link'],
callback=self.detail_page,
meta={"item": item})
def parse(self, response):
sel = scrapy.selector.Selector(response)
# list = response.xpath('//ol[@class="commentlist"]')
# for li in list:
item = MeizituItem()
item['image'] = sel.xpath('//div[@class="wrap2"]/div/div/dl/dt/a/img/@src').extract()
#item['image'] = response.xpath("./li//img/@src").extract()
yield item
def parse_detail(self, response):
# print("response.url===",response.url)
#好多的图片
images = response.xpath("//img/@src").extract()
title = response.xpath("//h5/text()").extract()[0]
for image in images:
item = MeizituItem()
item["image"] = image
item["title"] = title
item["url"] = response.url
yield item