RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add test for alternate links

This commit is contained in:
Paul Tremberth 2017-08-03 16:35:47 +02:00
parent 01ac883893
commit 0cb3085f84
1 changed files with 27 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
tests/test_spider.py
View File

@ -348,6 +348,33 @@ Sitemap: /sitemap-relative-url.xml
'http://example.com/sitemap-uppercase.xml',
'http://www.example.com/sitemap-relative-url.xml'])
def test_alternate_url_locs(self):
sitemap = b"""<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
xmlns:xhtml="http://www.w3.org/1999/xhtml">
<url>
<loc>http://www.example.com/english/</loc>
<xhtml:link rel="alternate" hreflang="de"
href="http://www.example.com/deutsch/"/>
<xhtml:link rel="alternate" hreflang="de-ch"
href="http://www.example.com/schweiz-deutsch/"/>
<xhtml:link rel="alternate" hreflang="it"
href="http://www.example.com/italiano/"/>
<xhtml:link rel="alternate" hreflang="it"/><!-- wrong tag without href -->
</url>
</urlset>"""
r = TextResponse(url="http://www.example.com/sitemap.xml", body=sitemap)
spider = self.spider_class("example.com")
self.assertEqual([req.url for req in spider._parse_sitemap(r)],
['http://www.example.com/english/'])
spider.sitemap_alternate_links = True
self.assertEqual([req.url for req in spider._parse_sitemap(r)],
['http://www.example.com/english/',
'http://www.example.com/deutsch/',
'http://www.example.com/schweiz-deutsch/',
'http://www.example.com/italiano/'])
class DeprecationTest(unittest.TestCase):