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

reverted previous changed as it broke tests

This commit is contained in:
Pablo Hoffman 2013-02-11 11:43:25 -02:00
parent 2df010a972
commit d9043ffa6e
2 changed files with 1 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
scrapy/tests/test_utils_url.py
View File

@ -158,13 +158,6 @@ class UrlUtilsTest(unittest.TestCase):
self.assertEqual(canonicalize_url("http://foo.com/AC%2FDC/"),
"http://foo.com/AC%2FDC/")
def test_url_has_any_extension(self):
self.assertTrue(url_has_any_extension("http://www.example.com/page.doc", IGNORED_EXTENSIONS))
self.assertTrue(url_has_any_extension("http://www.example.com/page.pdf", IGNORED_EXTENSIONS))
self.assertFalse(url_has_any_extension("http://www.example.com/page.htm", IGNORED_EXTENSIONS))
self.assertFalse(url_has_any_extension("http://www.example.com/", IGNORED_EXTENSIONS))
self.assertFalse(url_has_any_extension("http://www.example.com/page.doc.html", IGNORED_EXTENSIONS))
if __name__ == "__main__":
unittest.main()

2
scrapy/utils/url.py
View File

@ -28,7 +28,7 @@ def url_is_from_spider(url, spider):
getattr(spider, 'allowed_domains', []))
def url_has_any_extension(url, extensions):
return posixpath.splitext(parse_url(url).path)[1].replace('.', '').lower() in extensions
return posixpath.splitext(parse_url(url).path)[1].lower() in extensions
def canonicalize_url(url, keep_blank_values=True, keep_fragments=False, \
encoding=None):