Hello I am trying out Scrapy. But for one domain, ShoeScribe, the
parse_item is not called for. With same code, it works fine with other
domain. Totally no idea why. Any help will be really appreciated!
import scrapy
from scrapy import log
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors import LinkExtractor
from lsspider.items import *
class ShoeScribeSpider(CrawlSpider):
name = "shoescribe"
merchant_name = "shoescribe.com"
allowed_domains = ["www.shoescribe.com"]
start_urls = [
"http://www.shoescribe.com/us/women/ankle-boots_cod44709699mx.html";,
]
rules = (
Rule(LinkExtractor(allow=('http://www.shoescribe.com/us/women/ankle-boots_cod44709699mx.html')),
callback='parse_item', follow=True),
)
def parse_item(self, response):
print 'parse_item'
item = Item()
item['url'] = response.url.split('?')[0]
print item['url']
return item
--
You received this message because you are subscribed to the Google Groups
"scrapy-users" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To post to this group, send email to [email protected].
Visit this group at http://groups.google.com/group/scrapy-users.
For more options, visit https://groups.google.com/d/optout.
