diff options
| -rw-r--r-- | CHANGELOG | 3 | ||||
| -rw-r--r-- | beautifulsoup/element.py | 42 | ||||
| -rw-r--r-- | tests/test_tree.py | 84 |
3 files changed, 67 insertions, 62 deletions
@@ -1,5 +1,8 @@ = 4.0 = +Methods have been renamed for comply with PEP 8. findAll is now +find_all, and so on. Old names still work. + tag.string now operates recursively. If tag A contains a single tag B and nothing else, then A.string is the same as B.string. So: diff --git a/beautifulsoup/element.py b/beautifulsoup/element.py index b4981a7..869be4d 100644 --- a/beautifulsoup/element.py +++ b/beautifulsoup/element.py @@ -164,13 +164,13 @@ class PageElement: def findNext(self, name=None, attrs={}, text=None, **kwargs): """Returns the first item that matches the given criteria and appears after this Tag in the document.""" - return self._findOne(self.findAllNext, name, attrs, text, **kwargs) + return self._findOne(self.find_allNext, name, attrs, text, **kwargs) - def findAllNext(self, name=None, attrs={}, text=None, limit=None, + def find_allNext(self, name=None, attrs={}, text=None, limit=None, **kwargs): """Returns all items that match the given criteria and appear after this Tag in the document.""" - return self._findAll(name, attrs, text, limit, self.nextGenerator, + return self._find_all(name, attrs, text, limit, self.nextGenerator, **kwargs) def findNextSibling(self, name=None, attrs={}, text=None, **kwargs): @@ -183,22 +183,22 @@ class PageElement: **kwargs): """Returns the siblings of this Tag that match the given criteria and appear after this Tag in the document.""" - return self._findAll(name, attrs, text, limit, + return self._find_all(name, attrs, text, limit, self.nextSiblingGenerator, **kwargs) fetchNextSiblings = findNextSiblings # Compatibility with pre-3.x def findPrevious(self, name=None, attrs={}, text=None, **kwargs): """Returns the first item that matches the given criteria and appears before this Tag in the document.""" - return self._findOne(self.findAllPrevious, name, attrs, text, **kwargs) + return self._findOne(self.find_allPrevious, name, attrs, text, **kwargs) - def findAllPrevious(self, name=None, attrs={}, text=None, limit=None, + def find_allPrevious(self, name=None, attrs={}, text=None, limit=None, **kwargs): """Returns all items that match the given criteria and appear before this Tag in the document.""" - return self._findAll(name, attrs, text, limit, self.previousGenerator, + return self._find_all(name, attrs, text, limit, self.previousGenerator, **kwargs) - fetchPrevious = findAllPrevious # Compatibility with pre-3.x + fetchPrevious = find_allPrevious # Compatibility with pre-3.x def findPreviousSibling(self, name=None, attrs={}, text=None, **kwargs): """Returns the closest sibling to this Tag that matches the @@ -210,7 +210,7 @@ class PageElement: limit=None, **kwargs): """Returns the siblings of this Tag that match the given criteria and appear before this Tag in the document.""" - return self._findAll(name, attrs, text, limit, + return self._find_all(name, attrs, text, limit, self.previousSiblingGenerator, **kwargs) fetchPreviousSiblings = findPreviousSiblings # Compatibility with pre-3.x @@ -229,7 +229,7 @@ class PageElement: """Returns the parents of this Tag that match the given criteria.""" - return self._findAll(name, attrs, None, limit, self.parentGenerator, + return self._find_all(name, attrs, None, limit, self.parentGenerator, **kwargs) fetchParents = findParents # Compatibility with pre-3.x @@ -242,7 +242,7 @@ class PageElement: r = l[0] return r - def _findAll(self, name, attrs, text, limit, generator, **kwargs): + def _find_all(self, name, attrs, text, limit, generator, **kwargs): "Iterates over a generator looking for things that match." if isinstance(name, SoupStrainer): @@ -394,7 +394,7 @@ class Tag(PageElement, Entities): "Basic constructor." # We don't actually store the parser object: that lets extracted - # chunks be garbage-collected + # chunks be garbage-collected. self.parserClass = parser.__class__ self.name = name self.isSelfClosing = builder.isSelfClosingTag(name) @@ -407,7 +407,6 @@ class Tag(PageElement, Entities): self.setup(parent, previous) self.hidden = False self.containsSubstitutions = False - self.escapeUnrecognizedEntities = parser.escapeUnrecognizedEntities if isinstance(attrs, types.DictType): self.attrs = [kv for kv in attrs.items()] @@ -487,9 +486,9 @@ class Tag(PageElement, Entities): def __call__(self, *args, **kwargs): """Calling a tag like a function is the same as calling its - findAll() method. Eg. tag('a') returns a list of all the A tags + find_all() method. Eg. tag('a') returns a list of all the A tags found within this tag.""" - return apply(self.findAll, args, kwargs) + return apply(self.find_all, args, kwargs) def __getattr__(self, tag): #print "Getattr %s.%s" % (self.__class__, tag) @@ -670,14 +669,14 @@ class Tag(PageElement, Entities): """Return only the first child of this Tag matching the given criteria.""" r = None - l = self.findAll(name, attrs, recursive, text, 1, **kwargs) + l = self.find_all(name, attrs, recursive, text, 1, **kwargs) if l: r = l[0] return r findChild = find - def findAll(self, name=None, attrs={}, recursive=True, text=None, - limit=None, **kwargs): + def find_all(self, name=None, attrs={}, recursive=True, text=None, + limit=None, **kwargs): """Extracts a list of Tag objects that match the given criteria. You can specify the name of the Tag and any attributes you want the Tag to have. @@ -690,8 +689,11 @@ class Tag(PageElement, Entities): generator = self.recursiveChildGenerator if not recursive: generator = self.childGenerator - return self._findAll(name, attrs, text, limit, generator, **kwargs) - findChildren = findAll + return self._find_all(name, attrs, text, limit, generator, **kwargs) + + # Old names for backwards compatibility. + find_all = find_all + findChildren = find_all #Private methods diff --git a/tests/test_tree.py b/tests/test_tree.py index 367489e..87bd154 100644 --- a/tests/test_tree.py +++ b/tests/test_tree.py @@ -40,7 +40,7 @@ class TreeTest(SoupTest): class TestFind(TreeTest): """Basic tests of the find() method. - find() just calls findAll() with limit=1, so it's not tested all + find() just calls find_all() with limit=1, so it's not tested all that thouroughly here. """ @@ -54,34 +54,34 @@ class TestFind(TreeTest): class TestFindAll(TreeTest): - """Basic tests of the findAll() method.""" + """Basic tests of the find_all() method.""" def test_find_all_text_nodes(self): """You can search the tree for text nodes.""" soup = self.soup("<html>Foo<b>bar</b>\xbb</html>") # Exact match. - self.assertEqual(soup.findAll(text="bar"), [u"bar"]) + self.assertEqual(soup.find_all(text="bar"), [u"bar"]) # Match any of a number of strings. self.assertEqual( - soup.findAll(text=["Foo", "bar"]), [u"Foo", u"bar"]) + soup.find_all(text=["Foo", "bar"]), [u"Foo", u"bar"]) # Match a regular expression. - self.assertEqual(soup.findAll(text=re.compile('.*')), + self.assertEqual(soup.find_all(text=re.compile('.*')), [u"Foo", u"bar", u'\xbb']) # Match anything. - self.assertEqual(soup.findAll(text=True), + self.assertEqual(soup.find_all(text=True), [u"Foo", u"bar", u'\xbb']) def test_find_all_limit(self): - """You can limit the number of items returned by findAll.""" + """You can limit the number of items returned by find_all.""" soup = self.soup("<a>1</a><a>2</a><a>3</a><a>4</a><a>5</a>") - self.assertSelects(soup.findAll('a', limit=3), ["1", "2", "3"]) - self.assertSelects(soup.findAll('a', limit=1), ["1"]) + self.assertSelects(soup.find_all('a', limit=3), ["1", "2", "3"]) + self.assertSelects(soup.find_all('a', limit=1), ["1"]) self.assertSelects( - soup.findAll('a', limit=10), ["1", "2", "3", "4", "5"]) + soup.find_all('a', limit=10), ["1", "2", "3", "4", "5"]) # A limit of 0 means no limit. self.assertSelects( - soup.findAll('a', limit=0), ["1", "2", "3", "4", "5"]) + soup.find_all('a', limit=0), ["1", "2", "3", "4", "5"]) class TestFindAllByName(TreeTest): """Test ways of finding tags by tag name.""" @@ -95,33 +95,33 @@ class TestFindAllByName(TreeTest): def test_find_all_by_tag_name(self): # Find all the <a> tags. self.assertSelects( - self.tree.findAll('a'), ['First tag.', 'Nested tag.']) + self.tree.find_all('a'), ['First tag.', 'Nested tag.']) def test_find_all_on_non_root_element(self): # You can call find_all on any node, not just the root. - self.assertSelects(self.tree.c.findAll('a'), ['Nested tag.']) + self.assertSelects(self.tree.c.find_all('a'), ['Nested tag.']) def test_calling_element_invokes_find_all(self): self.assertSelects(self.tree('a'), ['First tag.', 'Nested tag.']) def test_find_all_by_tag_strainer(self): self.assertSelects( - self.tree.findAll(SoupStrainer('a')), + self.tree.find_all(SoupStrainer('a')), ['First tag.', 'Nested tag.']) def test_find_all_by_tag_names(self): self.assertSelects( - self.tree.findAll(['a', 'b']), + self.tree.find_all(['a', 'b']), ['First tag.', 'Second tag.', 'Nested tag.']) def test_find_all_by_tag_dict(self): self.assertSelects( - self.tree.findAll({'a' : True, 'b' : True}), + self.tree.find_all({'a' : True, 'b' : True}), ['First tag.', 'Second tag.', 'Nested tag.']) def test_find_all_by_tag_re(self): self.assertSelects( - self.tree.findAll(re.compile('^[ab]$')), + self.tree.find_all(re.compile('^[ab]$')), ['First tag.', 'Second tag.', 'Nested tag.']) def test_find_all_with_tags_matching_method(self): @@ -135,26 +135,26 @@ class TestFindAllByName(TreeTest): <b id="b">Match 2.</a>""") self.assertSelects( - tree.findAll(id_matches_name), ["Match 1.", "Match 2."]) + tree.find_all(id_matches_name), ["Match 1.", "Match 2."]) class TestFindAllByAttribute(TreeTest): def test_find_all_by_attribute_name(self): - # You can pass in keyword arguments to findAll to search by + # You can pass in keyword arguments to find_all to search by # attribute. tree = self.soup(""" <a id="first">Matching a.</a> <a id="second"> Non-matching <b id="first">Matching b.</b>a. </a>""") - self.assertSelects(tree.findAll(id='first'), + self.assertSelects(tree.find_all(id='first'), ["Matching a.", "Matching b."]) def test_find_all_by_attribute_dict(self): # You can pass in a dictionary as the argument 'attrs'. This # lets you search for attributes like 'name' (a fixed argument - # to findAll) and 'class' (a reserved word in Python.) + # to find_all) and 'class' (a reserved word in Python.) tree = self.soup(""" <a name="name1" class="class1">Name match.</a> <a name="name2" class="class2">Class match.</a> @@ -163,14 +163,14 @@ class TestFindAllByAttribute(TreeTest): """) # This doesn't do what you want. - self.assertSelects(tree.findAll(name='name1'), + self.assertSelects(tree.find_all(name='name1'), ["A tag called 'name1'."]) # This does what you want. - self.assertSelects(tree.findAll(attrs={'name' : 'name1'}), + self.assertSelects(tree.find_all(attrs={'name' : 'name1'}), ["Name match."]) # Passing class='class2' would cause a syntax error. - self.assertSelects(tree.findAll(attrs={'class' : 'class2'}), + self.assertSelects(tree.find_all(attrs={'class' : 'class2'}), ["Class match."]) def test_find_all_by_class(self): @@ -180,8 +180,8 @@ class TestFindAllByAttribute(TreeTest): <a class="2">Class 2.</a> <b class="1">Class 1.</a> """) - self.assertSelects(tree.findAll('a', '1'), ['Class 1.']) - self.assertSelects(tree.findAll(attrs='1'), ['Class 1.', 'Class 1.']) + self.assertSelects(tree.find_all('a', '1'), ['Class 1.']) + self.assertSelects(tree.find_all(attrs='1'), ['Class 1.', 'Class 1.']) def test_find_all_by_attribute_soupstrainer(self): tree = self.soup(""" @@ -189,24 +189,24 @@ class TestFindAllByAttribute(TreeTest): <a id="second">Non-match.</a>""") strainer = SoupStrainer(attrs={'id' : 'first'}) - self.assertSelects(tree.findAll(strainer), ['Match.']) + self.assertSelects(tree.find_all(strainer), ['Match.']) def test_find_all_with_missing_atribute(self): - # You can pass in None as the value of an attribute to findAll. + # You can pass in None as the value of an attribute to find_all. # This will match tags that do not have that attribute set. tree = self.soup("""<a id="1">ID present.</a> <a>No ID present.</a> <a id="">ID is empty.</a>""") - self.assertSelects(tree.findAll('a', id=None), ["No ID present."]) + self.assertSelects(tree.find_all('a', id=None), ["No ID present."]) def test_find_all_with_defined_attribute(self): - # You can pass in None as the value of an attribute to findAll. + # You can pass in None as the value of an attribute to find_all. # This will match tags that have that attribute set to any value. tree = self.soup("""<a id="1">ID present.</a> <a>No ID present.</a> <a id="">ID is empty.</a>""") self.assertSelects( - tree.findAll(id=True), ["ID present.", "ID is empty."]) + tree.find_all(id=True), ["ID present.", "ID is empty."]) def test_find_all_with_numeric_attribute(self): # If you search for a number, it's treated as a string. @@ -214,8 +214,8 @@ class TestFindAllByAttribute(TreeTest): <a id="1">Quoted attribute.</a>""") expected = ["Unquoted attribute.", "Quoted attribute."] - self.assertSelects(tree.findAll(id=1), expected) - self.assertSelects(tree.findAll(id="1"), expected) + self.assertSelects(tree.find_all(id=1), expected) + self.assertSelects(tree.find_all(id="1"), expected) def test_find_all_with_list_attribute_values(self): # You can pass a list of attribute values instead of just one, @@ -224,7 +224,7 @@ class TestFindAllByAttribute(TreeTest): <a id="2">2</a> <a id="3">3</a> <a>No ID.</a>""") - self.assertSelects(tree.findAll(id=["1", "3", "4"]), + self.assertSelects(tree.find_all(id=["1", "3", "4"]), ["1", "3"]) def test_find_all_with_regular_expression_attribute_value(self): @@ -237,7 +237,7 @@ class TestFindAllByAttribute(TreeTest): <a id="b">One b.</a> <a>No ID.</a>""") - self.assertSelects(tree.findAll(id=re.compile("^a+$")), + self.assertSelects(tree.find_all(id=re.compile("^a+$")), ["One a.", "Two as."]) @@ -318,8 +318,8 @@ class TestNextOperations(ProximityTest): self.assertEquals(self.tree.next, None) def test_find_all_next(self): - self.assertSelects(self.start.findAllNext('b'), ["Two", "Three"]) - self.assertSelects(self.start.findAllNext(id=3), ["Three"]) + self.assertSelects(self.start.find_allNext('b'), ["Two", "Three"]) + self.assertSelects(self.start.find_allNext(id=3), ["Three"]) def test_find_next(self): self.assertEquals(self.start.findNext('b')['id'], '2') @@ -328,7 +328,7 @@ class TestNextOperations(ProximityTest): def test_find_next_for_text_element(self): text = self.tree.find(text="One") self.assertEquals(text.findNext("b").string, "Two") - self.assertSelects(text.findAllNext("b"), ["Two", "Three"]) + self.assertSelects(text.find_allNext("b"), ["Two", "Three"]) def test_next_generator(self): start = self.tree.find(text="Two") @@ -369,8 +369,8 @@ class TestPreviousOperations(ProximityTest): # of the "Three" node itself, which is why "Three" shows up # here. self.assertSelects( - self.end.findAllPrevious('b'), ["Three", "Two", "One"]) - self.assertSelects(self.end.findAllPrevious(id=1), ["One"]) + self.end.find_allPrevious('b'), ["Three", "Two", "One"]) + self.assertSelects(self.end.find_allPrevious(id=1), ["One"]) def test_find_previous(self): self.assertEquals(self.end.findPrevious('b')['id'], '3') @@ -380,7 +380,7 @@ class TestPreviousOperations(ProximityTest): text = self.tree.find(text="Three") self.assertEquals(text.findPrevious("b").string, "Three") self.assertSelects( - text.findAllPrevious("b"), ["Three", "Two", "One"]) + text.find_allPrevious("b"), ["Three", "Two", "One"]) def test_previous_generator(self): start = self.tree.find(text="One") @@ -623,7 +623,7 @@ class TestTreeModification(SoupTest): def test_replace_with(self): soup = self.soup( "<p>There's <b>no</b> business like <b>show</b> business</p>") - no, show = soup.findAll('b') + no, show = soup.find_all('b') show.replaceWith(no) self.assertEquals( soup.decode(), |