**items.py文件**
import scrapy
from scrapy.item import Item, Field
class TutorialItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
pass
class DmozItem(Item):
title = Field()
link = Field()
desc = Field()
**dmoz_spider.py文件**
from scrapy.spiders import Spider
from scrapy.selector import Selector
from tutorial.items import DmozItem
import sys
sys.path.append("..")
class DmozSpider(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 site in sites:
item = DmozItem()
item['title'] = site.xpath('a/text()').extract()
item['link'] = site.xpath('a/@href').extract()
item['desc'] = site.xpath('text()').extract()
items.append(item)
return items
**错误代码**
Traceback (most recent call last):
File "F:\tutorial\tutorial\spiders\dmoz_spider.py", line 3, in <module>
from tutorial.items import DmozItem
ImportError: No module named tutorial.items
[Finished in 0.6s with exit code 1