Merge pull request #363 from taikano/sitemap_alternate

also fetch alternate URLs from sitemaps, see #360

docs/topics/spiders.rst

@@ -560,6 +560,25 @@ SitemapSpider
 
         By default, all sitemaps are followed.
 
+    .. attribute:: sitemap_alternate_links
+
+        Specifies if alternate links for one ``url`` should be followed. These
+        are links for the same website in another language passed within
+        the same ``url`` block.
+        
+        For example::
+       
+            <url>
+                <loc>http://example.com/</loc>
+                <xhtml:link rel="alternate" hreflang="de" href="http://example.com/de"/>
+            </url>
+
+        With ``sitemap_alternate_links`` set, this would retrieve both URLs. With
+        ``sitemap_alternate_links`` disabled, only ``http://example.com/`` would be
+        retrieved.
+
+        Default is ``sitemap_alternate_links`` disabled.
+
 
 SitemapSpider examples
 ~~~~~~~~~~~~~~~~~~~~~~

scrapy/contrib/spiders/sitemap.py

@@ -11,6 +11,7 @@ class SitemapSpider(BaseSpider):
     sitemap_urls = ()
     sitemap_rules = [('', 'parse')]
     sitemap_follow = ['']
+    sitemap_alternate_links = False
 
     def __init__(self, *a, **kw):
         super(SitemapSpider, self).__init__(*a, **kw)
@@ -37,7 +38,7 @@ class SitemapSpider(BaseSpider):
 
             s = Sitemap(body)
             if s.type == 'sitemapindex':
-                for loc in iterloc(s):
+                for loc in iterloc(s, self.sitemap_alternate_links):
                     if any(x.search(loc) for x in self._follow):
                         yield Request(loc, callback=self._parse_sitemap)
             elif s.type == 'urlset':
@@ -65,6 +66,11 @@ def regex(x):
         return re.compile(x)
     return x
 
-def iterloc(it):
+def iterloc(it, alt=False):
     for d in it:
         yield d['loc']
+
+        # Also consider alternate URLs (xhtml:link rel="alternate")
+        if alt and 'alternate' in d:
+            for l in d['alternate']:
+                yield l

scrapy/tests/test_utils_sitemap.py

@@ -159,6 +159,42 @@ Disallow: /forum/active/
             {'lastmod': '2013-07-15', 'loc': 'http://www.example.com/sitemap3.xml'},
         ])
 
+    def test_comment(self):
+        s = Sitemap("""<?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/</loc>
+            <!-- this is a comment on which the parser might raise an exception if implemented incorrectly -->
+        </url>
+    </urlset>""")
+
+        self.assertEqual(list(s), [
+            {'loc': 'http://www.example.com/'}
+        ])
+
+    def test_alternate(self):
+        s = Sitemap("""<?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="en"
+                href="http://www.example.com/english/"/>
+            <xhtml:link rel="alternate" hreflang="en"/><!-- wrong tag without href -->
+        </url>
+    </urlset>""")
+        
+        self.assertEqual(list(s), [
+            {'loc': 'http://www.example.com/english/',
+             'alternate': ['http://www.example.com/deutsch/', 'http://www.example.com/schweiz-deutsch/', 'http://www.example.com/english/']
+            }
+        ])
+
 
 if __name__ == '__main__':
     unittest.main()

scrapy/utils/sitemap.py

@@ -12,7 +12,7 @@ class Sitemap(object):
     (type=sitemapindex) files"""
 
     def __init__(self, xmltext):
-        xmlp = lxml.etree.XMLParser(recover=True)
+        xmlp = lxml.etree.XMLParser(recover=True, remove_comments=True)
         self._root = lxml.etree.fromstring(xmltext, parser=xmlp)
         rt = self._root.tag
         self.type = self._root.tag.split('}', 1)[1] if '}' in rt else rt
@@ -23,7 +23,13 @@ class Sitemap(object):
             for el in elem.getchildren():
                 tag = el.tag
                 name = tag.split('}', 1)[1] if '}' in tag else tag
-                d[name] = el.text.strip() if el.text else ''
+
+                if name == 'link':
+                    if 'href' in el.attrib:
+                        d.setdefault('alternate', []).append(el.get('href'))
+                else:
+                    d[name] = el.text.strip() if el.text else ''
+
             if 'loc' in d:
                 yield d