31c25891c1
This script crawls all available sites on http://docs.openstack.org and extracts all URLs. Based on the URLs the script generates a sitemap for search engines according to the protocol described at http://www.sitemaps.org/protocol.html. Change-Id: Id7839d2048989da503d31e436455aea9bb4cdc1d
22 lines
788 B
Python
22 lines
788 B
Python
# 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()
|