bpo-21475: Support the Sitemap extension in robotparser (GH-6883)

2 files changed, 33 insertions, 0 deletions

diff --git a/Lib/test/test_robotparser.py b/Lib/test/test_robotparser.py
index bee8d23..84a267a 100644
--- a/Lib/test/test_robotparser.py
+++ b/Lib/test/test_robotparser.py
@@ -12,6 +12,7 @@ class BaseRobotTest:
     agent = 'test_robotparser'
     good = []
     bad = []
+    site_maps = None
 
     def setUp(self):
         lines = io.StringIO(self.robots_txt).readlines()
@@ -36,6 +37,9 @@ class BaseRobotTest:
             with self.subTest(url=url, agent=agent):
                 self.assertFalse(self.parser.can_fetch(agent, url))
 
+    def test_site_maps(self):
+        self.assertEqual(self.parser.site_maps(), self.site_maps)
+
 
 class UserAgentWildcardTest(BaseRobotTest, unittest.TestCase):
     robots_txt = """\
@@ -65,6 +69,23 @@ Disallow:
     bad = ['/cyberworld/map/index.html']
 
 
+class SitemapTest(BaseRobotTest, unittest.TestCase):
+    robots_txt = """\
+# robots.txt for http://www.example.com/
+
+User-agent: *
+Sitemap: http://www.gstatic.com/s2/sitemaps/profiles-sitemap.xml
+Sitemap: http://www.google.com/hostednews/sitemap_index.xml
+Request-rate: 3/15
+Disallow: /cyberworld/map/ # This is an infinite virtual URL space
+
+    """
+    good = ['/', '/test.html']
+    bad = ['/cyberworld/map/index.html']
+    site_maps = ['http://www.gstatic.com/s2/sitemaps/profiles-sitemap.xml',
+                 'http://www.google.com/hostednews/sitemap_index.xml']
+
+
 class RejectAllRobotsTest(BaseRobotTest, unittest.TestCase):
     robots_txt = """\
 # go away
diff --git a/Lib/urllib/robotparser.py b/Lib/urllib/robotparser.py
index 92e4efe..7089916 100644
--- a/Lib/urllib/robotparser.py
+++ b/Lib/urllib/robotparser.py
@@ -27,6 +27,7 @@ class RobotFileParser:
 
     def __init__(self, url=''):
         self.entries = []
+        self.sitemaps = []
         self.default_entry = None
         self.disallow_all = False
         self.allow_all = False
@@ -141,6 +142,12 @@ class RobotFileParser:
                             and numbers[1].strip().isdigit()):
                             entry.req_rate = RequestRate(int(numbers[0]), int(numbers[1]))
                         state = 2
+                elif line[0] == "sitemap":
+                    # According to http://www.sitemaps.org/protocol.html
+                    # "This directive is independent of the user-agent line,
+                    #  so it doesn't matter where you place it in your file."
+                    # Therefore we do not change the state of the parser.
+                    self.sitemaps.append(line[1])
         if state == 2:
             self._add_entry(entry)
 
@@ -189,6 +196,11 @@ class RobotFileParser:
                 return entry.req_rate
         return self.default_entry.req_rate
 
+    def site_maps(self):
+        if not self.sitemaps:
+            return None
+        return self.sitemaps
+
     def __str__(self):
         entries = self.entries
         if self.default_entry is not None: