def text_parse_content(self, response):
for site in response.xpath('//div[@class="text"]'):
item = GifItem()
item['item_type'] = '3'
try:
item['name'] = site.xpath('./..//h3/a/b/text()').extract()[0]
item['content'] = site.xpath('./p/a/text()').extract()[0]
except Exception, ex:
pass
print item['name'], item['content']
yield item
def image_parse_content(self, response):
for site in response.xpath('//div[@class="text"]'):
item = GifItem()
item['item_type'] = '2'
item['content'] = ' '
item['path'] = ' '
try:
item['link_url'] = site.xpath('./..//h3/a/@href').extract()[0]
item['name'] = site.xpath('./..//h3/a/b/text()').extract()[0]
item['src_url'] = site.xpath('./p/img/@src').extract()[0]
except Exception, ex:
item['name'] = ' '
item['src_url'] = ' '
pass
# print item['name'],item['src_url']
yield item