Issue #25400: RobotFileParser now correctly returns default values for crawl_delay and request_rate
Initial patch by Peter Wirtz.
diff --git a/Lib/test/test_robotparser.py b/Lib/test/test_robotparser.py
index 51b48ce..0f64ba8 100644
--- a/Lib/test/test_robotparser.py
+++ b/Lib/test/test_robotparser.py
@@ -79,7 +79,28 @@
bad = ['/cyberworld/map/index.html', '/', '/tmp/']
-class CrawlDelayAndRequestRateTest(BaseRobotTest, unittest.TestCase):
+class BaseRequestRateTest(BaseRobotTest):
+
+ def test_request_rate(self):
+ for url in self.good + self.bad:
+ agent, url = self.get_agent_and_url(url)
+ with self.subTest(url=url, agent=agent):
+ if self.crawl_delay:
+ self.assertEqual(
+ self.parser.crawl_delay(agent), self.crawl_delay
+ )
+ if self.request_rate:
+ self.assertEqual(
+ self.parser.request_rate(agent).requests,
+ self.request_rate.requests
+ )
+ self.assertEqual(
+ self.parser.request_rate(agent).seconds,
+ self.request_rate.seconds
+ )
+
+
+class CrawlDelayAndRequestRateTest(BaseRequestRateTest, unittest.TestCase):
robots_txt = """\
User-agent: figtree
Crawl-delay: 3
@@ -96,24 +117,6 @@
bad = ['/tmp', '/tmp.html', '/tmp/a.html', '/a%3cd.html', '/a%3Cd.html',
'/a%2fb.html', '/~joe/index.html']
- def test_request_rate(self):
- for url in self.good:
- agent, url = self.get_agent_and_url(url)
- with self.subTest(url=url, agent=agent):
- if self.crawl_delay:
- self.assertEqual(
- self.parser.crawl_delay(agent), self.crawl_delay
- )
- if self.request_rate and self.parser.request_rate(agent):
- self.assertEqual(
- self.parser.request_rate(agent).requests,
- self.request_rate.requests
- )
- self.assertEqual(
- self.parser.request_rate(agent).seconds,
- self.request_rate.seconds
- )
-
class DifferentAgentTest(CrawlDelayAndRequestRateTest):
agent = 'FigTree Robot libwww-perl/5.04'
@@ -230,6 +233,19 @@
bad = ['/another/path?']
+class DefaultEntryTest(BaseRequestRateTest, unittest.TestCase):
+ robots_txt = """\
+User-agent: *
+Crawl-delay: 1
+Request-rate: 3/15
+Disallow: /cyberworld/map/
+ """
+ request_rate = namedtuple('req_rate', 'requests seconds')(3, 15)
+ crawl_delay = 1
+ good = ['/', '/test.html']
+ bad = ['/cyberworld/map/index.html']
+
+
class RobotHandler(BaseHTTPRequestHandler):
def do_GET(self):
@@ -309,6 +325,8 @@
self.assertTrue(parser.allow_all)
self.assertFalse(parser.disallow_all)
self.assertEqual(parser.mtime(), 0)
+ self.assertIsNone(parser.crawl_delay('*'))
+ self.assertIsNone(parser.request_rate('*'))
if __name__=='__main__':
unittest.main()
diff --git a/Lib/urllib/robotparser.py b/Lib/urllib/robotparser.py
index 85add16..9dab4c1 100644
--- a/Lib/urllib/robotparser.py
+++ b/Lib/urllib/robotparser.py
@@ -175,16 +175,20 @@
return True
def crawl_delay(self, useragent):
+ if not self.mtime():
+ return None
for entry in self.entries:
if entry.applies_to(useragent):
return entry.delay
- return None
+ return self.default_entry.delay
def request_rate(self, useragent):
+ if not self.mtime():
+ return None
for entry in self.entries:
if entry.applies_to(useragent):
return entry.req_rate
- return None
+ return self.default_entry.req_rate
def __str__(self):
return ''.join([str(entry) + "\n" for entry in self.entries])