Added support for CSS selector values that contain quoted spaces,

  such as tag[style="display: foo"]. [bug=1540588]

3 files changed, 17 insertions, 8 deletions

diff --git a/NEWS.txt b/NEWS.txt
index 1fe2159..9e27d51 100644
--- a/NEWS.txt
+++ b/NEWS.txt
@@ -7,6 +7,9 @@
   reparented into a tag that contained an identical whitespace
   element. [bug=1505351]
 
+* Added support for CSS selector values that contain quoted spaces,
+  such as tag[style="display: foo"]. [bug=1540588]
+
 * Corrected handling of XML processing instructions. [bug=1504393]
 
 * The contents of <textarea> tags will no longer be modified when the
diff --git a/bs4/element.py b/bs4/element.py
index 7a3aa52..ad13533 100644
--- a/bs4/element.py
+++ b/bs4/element.py
@@ -4,6 +4,7 @@ __license__ = "MIT"
 
 import collections
 import re
+import shlex
 import sys
 import warnings
 from bs4.dammit import EntitySubstitution
@@ -1319,6 +1320,7 @@ class Tag(PageElement):
 
     _selector_combinators = ['>', '+', '~']
     _select_debug = False
+    quoted_colon = re.compile('"[^"]*:[^"]*"')
     def select_one(self, selector):
         """Perform a CSS selection operation on the current element."""
         value = self.select(selector, limit=1)
@@ -1344,8 +1346,7 @@ class Tag(PageElement):
                 if limit and len(context) >= limit:
                     break
             return context
-
-        tokens = selector.split()
+        tokens = shlex.split(selector)
         current_context = [self]
 
         if tokens[-1] in self._selector_combinators:
@@ -1397,7 +1398,7 @@ class Tag(PageElement):
                     return classes.issubset(candidate.get('class', []))
                 checker = classes_match
 
-            elif ':' in token:
+            elif ':' in token and not self.quoted_colon.search(token):
                 # Pseudo-class
                 tag_name, pseudo = token.split(':', 1)
                 if tag_name == '':
@@ -1428,11 +1429,8 @@ class Tag(PageElement):
                             self.count += 1
                             if self.count == self.destination:
                                 return True
-                            if self.count > self.destination:
-                                # Stop the generator that's sending us
-                                # these things.
-                                raise StopIteration()
-                            return False
+                            else:
+                                return False
                     checker = Counter(pseudo_value).nth_child_of_type
                 else:
                     raise NotImplementedError(
diff --git a/bs4/tests/test_tree.py b/bs4/tests/test_tree.py
index 8a05990..fc19046 100644
--- a/bs4/tests/test_tree.py
+++ b/bs4/tests/test_tree.py
@@ -1909,6 +1909,14 @@ class TestSoupSelector(TreeTest):
             ('div[data-tag]', ['data1'])
         )
 
+    def test_quoted_space_in_selector_name(self):
+        html = """<div style="display: wrong">nope</div>
+        <div style="display: right">yes</div>
+        """
+        soup = BeautifulSoup(html, 'html.parser')
+        [chosen] = soup.select('div[style="display: right"]')
+        self.assertEqual("yes", chosen.string)
+
     def test_unsupported_pseudoclass(self):
         self.assertRaises(
             NotImplementedError, self.soup.select, "a:no-such-pseudoclass")