Merge pull request #5450 from kinoute/master

fixed detection of extensions like ".tar.gz" in URL

scrapy/utils/url.py

@@ -5,7 +5,6 @@ library.
 Some of the functions that used to be imported from this module have been moved
 to the w3lib.url module. Always import those from there instead.
 """
-import posixpath
 import re
 from urllib.parse import ParseResult, urldefrag, urlparse, urlunparse
 
@@ -31,8 +30,9 @@ def url_is_from_spider(url, spider):
 
 
 def url_has_any_extension(url, extensions):
-    return posixpath.splitext(parse_url(url).path)[1].lower() in extensions
-
+    """Return True if the url ends with one of the extensions provided"""
+    lowercase_path = parse_url(url).path.lower()
+    return any(lowercase_path.endswith(ext) for ext in extensions)
 
 def parse_url(url, encoding=None):
     """Return urlparsed url from the given argument (which could be an already

tests/test_utils_url.py

@@ -1,6 +1,8 @@
 import unittest
 
+from scrapy.linkextractors import IGNORED_EXTENSIONS
 from scrapy.spiders import Spider
+from scrapy.utils.misc import arg_to_iter
 from scrapy.utils.url import (
     add_http_if_no_scheme,
     guess_scheme,
@@ -8,9 +10,9 @@ from scrapy.utils.url import (
     strip_url,
     url_is_from_any_domain,
     url_is_from_spider,
+    url_has_any_extension,
 )
 
-
 __doctests__ = ['scrapy.utils.url']
 
 
@@ -81,6 +83,15 @@ class UrlUtilsTest(unittest.TestCase):
         self.assertTrue(url_is_from_spider('http://www.example.net/some/page.html', MySpider))
         self.assertFalse(url_is_from_spider('http://www.example.us/some/page.html', MySpider))
 
+    def test_url_has_any_extension(self):
+        deny_extensions = {'.' + e for e in arg_to_iter(IGNORED_EXTENSIONS)}
+        self.assertTrue(url_has_any_extension("http://www.example.com/archive.tar.gz", deny_extensions))
+        self.assertTrue(url_has_any_extension("http://www.example.com/page.doc", deny_extensions))
+        self.assertTrue(url_has_any_extension("http://www.example.com/page.pdf", deny_extensions))
+        self.assertFalse(url_has_any_extension("http://www.example.com/page.htm", deny_extensions))
+        self.assertFalse(url_has_any_extension("http://www.example.com/", deny_extensions))
+        self.assertFalse(url_has_any_extension("http://www.example.com/page.doc.html", deny_extensions))
+
 
 class AddHttpIfNoScheme(unittest.TestCase):