import re
from scrapy.item import Item, Field
from scrapy.contrib.loader.processor import MapCompose
class StelsItem(Item):
name = Field()
price = Field()
coll = Field()
==========================================
import re
from stels.items import StelsItem
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.contrib.loader import XPathItemLoader
from scrapy.contrib.loader.processor import Compose
from scrapy.contrib.loader.processor import MapCompose
from scrapy.contrib.loader.processor import TakeFirst
from scrapy.contrib.spiders import CrawlSpider
from scrapy.contrib.spiders import Rule
from scrapy.selector import HtmlXPathSelector
class StelsLoader(XPathItemLoader):
default_input_processor = MapCompose(lambda s: re.sub('\s+', ‘ ’, s.strip()))
default_output_processor = TakeFirst()
class StelsSpider(CrawlSpider):
name = “stels”
allowed_domains =
start_urls =
rules = (
Rule(SgmlLinkExtractor(allow
'sort\.aspx\?.+')), follow=True),Rule(SgmlLinkExtractor(allow
'item\.aspx\?.+')), callback='parse_item'),)
def parse_item(self, response):
hxs = HtmlXPathSelector(response)
l = AiteaLoader(AiteaItem(), hxs)
l.add_xpath('name', '//h1/span/text()')
l.add_xpath('price', '//span/text()')
l.add_xpath('coll', '//span/text()')
return l.load_item()
.