小弟刚在学scrapy。参考了官方文档照着它写了一段抓取代码。可以抓取到内容，但在使用scrapy crawl dmoz -o items.json 命令将爬的东西保存成json时生成的文件却只有一些空的［］，这是什么原因，求大牛help!
import scrapy
from scrapy.selector import Selector
from tutorial.items import DmozItem
class DmozSpider(scrapy.spider.Spider):
name = "dmoz"
allowed_domains = ["dmoz.org"]
start_urls = [
"http://www.dmoz.org/Computers/Programming/Languages/Python/Books/",
"http://www.dmoz.org/Computers/Programming/Languages/Python/Resources/"
]
def parse(self, response):
sel = Selector(response)
sites = sel.xpath('//ul[@class="directory-url"]/li')
items = []
for sel in sites:
item = DmozItem()
item['title'] = sel.xpath('a/text()').extract()
item['link'] = sel.xpath('a/@href').extract()
item['desc'] = sel.xpath('text()').re('-\s[^\n]*\\r')
items.append(item)
return items
Select Language