diff options
| author | Leonard Richardson <leonardr@segfault.org> | 2013-05-31 09:17:11 -0400 |
|---|---|---|
| committer | Leonard Richardson <leonardr@segfault.org> | 2013-05-31 09:17:11 -0400 |
| commit | 19f05a586c79b86be8ebe06a3728ab9a94162bee (patch) | |
| tree | 295326e49419a40a8942dc3b0552e51f97e18abb /bs4/testing.py | |
| parent | 342da7818966498e1fc2100c0b920cbc242c9831 (diff) | |
Create a new lxml parser object for every new parsing strategy.
Diffstat (limited to 'bs4/testing.py')
| -rw-r--r-- | bs4/testing.py | 13 |
1 files changed, 13 insertions, 0 deletions
diff --git a/bs4/testing.py b/bs4/testing.py index d8ff6b7..c363a89 100644 --- a/bs4/testing.py +++ b/bs4/testing.py @@ -279,6 +279,14 @@ class HTMLTreeBuilderSmokeTest(object): # to detect any differences between them. # + def test_can_parse_unicode_document(self): + # A seemingly innocuous document... but it's in Unicode! And + # it contains characters that can't be represented in the + # encoding found in the declaration! The horror! + markup = u'<html><head><meta encoding="euc-jp"></head><body>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</body>' + soup = self.soup(markup) + self.assertEqual(u'Sacr\xe9 bleu!', soup.body.string) + def test_soupstrainer(self): """Parsers should be able to work with SoupStrainers.""" strainer = SoupStrainer("b") @@ -482,6 +490,11 @@ class XMLTreeBuilderSmokeTest(object): encoded = soup.encode() self.assertTrue(b"< < hey > >" in encoded) + def test_can_parse_unicode_document(self): + markup = u'<?xml version="1.0" encoding="euc-jp"><root>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</root>' + soup = self.soup(markup) + self.assertEqual(u'Sacr\xe9 bleu!', soup.root.string) + def test_popping_namespaced_tag(self): markup = '<rss xmlns:dc="foo"><dc:creator>b</dc:creator><dc:date>2012-07-02T20:33:42Z</dc:date><dc:rights>c</dc:rights><image>d</image></rss>' soup = self.soup(markup) |