Move SitemapItem class into generator.spiders.sitemap_file
This will solve the following issue: ImportError: No module named sitemap.generator Change-Id: I449f0fb0c87613c36447cca94f4f5857f3d31afa
This commit is contained in:
parent
6b669e8778
commit
92a4fb6527
|
@ -1,21 +0,0 @@
|
||||||
# Licensed under the Apache License, Version 2.0 (the "License"); you may
|
|
||||||
# not use this file except in compliance with the License. You may obtain
|
|
||||||
# a copy of the License at
|
|
||||||
#
|
|
||||||
# http://www.apache.org/licenses/LICENSE-2.0
|
|
||||||
#
|
|
||||||
# Unless required by applicable law or agreed to in writing, software
|
|
||||||
# distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
|
|
||||||
# WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
|
|
||||||
# License for the specific language governing permissions and limitations
|
|
||||||
# under the License.
|
|
||||||
|
|
||||||
import scrapy
|
|
||||||
|
|
||||||
|
|
||||||
class SitemapItem(scrapy.item.Item):
|
|
||||||
'''Class to represent an item in the sitemap.'''
|
|
||||||
loc = scrapy.item.Field()
|
|
||||||
lastmod = scrapy.item.Field()
|
|
||||||
priority = scrapy.item.Field()
|
|
||||||
changefreq = scrapy.item.Field()
|
|
|
@ -13,9 +13,17 @@
|
||||||
import time
|
import time
|
||||||
import urlparse
|
import urlparse
|
||||||
|
|
||||||
|
from scrapy import item
|
||||||
from scrapy.linkextractors import LinkExtractor
|
from scrapy.linkextractors import LinkExtractor
|
||||||
from scrapy import spiders
|
from scrapy import spiders
|
||||||
from sitemap.generator import items
|
|
||||||
|
|
||||||
|
class SitemapItem(item.Item):
|
||||||
|
'''Class to represent an item in the sitemap.'''
|
||||||
|
loc = item.Field()
|
||||||
|
lastmod = item.Field()
|
||||||
|
priority = item.Field()
|
||||||
|
changefreq = item.Field()
|
||||||
|
|
||||||
|
|
||||||
class SitemapSpider(spiders.CrawlSpider):
|
class SitemapSpider(spiders.CrawlSpider):
|
||||||
|
@ -68,7 +76,7 @@ class SitemapSpider(spiders.CrawlSpider):
|
||||||
self.start_urls.append(url)
|
self.start_urls.append(url)
|
||||||
|
|
||||||
def parse_item(self, response):
|
def parse_item(self, response):
|
||||||
item = items.SitemapItem()
|
item = SitemapItem()
|
||||||
item['loc'] = response.url
|
item['loc'] = response.url
|
||||||
|
|
||||||
path = urlparse.urlsplit(response.url).path
|
path = urlparse.urlsplit(response.url).path
|
||||||
|
|
Loading…
Reference in New Issue