diff options
| -rw-r--r-- | CHANGELOG | 1 | ||||
| -rw-r--r-- | TODO | 8 | ||||
| -rw-r--r-- | bs4/element.py | 64 | ||||
| -rw-r--r-- | tests/test_tree.py | 8 |
4 files changed, 35 insertions, 46 deletions
@@ -22,6 +22,7 @@ version of the API is in use, the module is now called 'bs4': Methods have been renamed to comply with PEP 8. The old names still work. Here are the renames: + * replaceWith -> replace_with * findAll -> find_all * findAllNext -> find_all_next * findAllPrevious -> find_all_previous @@ -1,3 +1,11 @@ +3.0.8 optimized findAll('tag-name') and findAll(True), bypassing the +soupstrainer process. + +define a setter for Tag.string which replaces the tag's contents with +a string. + +Tag.text: concatenate all strings and return them + Bare ampersands should be converted to HTML entities upon output. Add namespace support. diff --git a/bs4/element.py b/bs4/element.py index 315ee63..6fb6210 100644 --- a/bs4/element.py +++ b/bs4/element.py @@ -27,19 +27,20 @@ class PageElement(object): self.previousSibling = self.parent.contents[-1] self.previousSibling.nextSibling = self - def replaceWith(self, replaceWith): + def replace_with(self, replace_with): oldParent = self.parent myIndex = self.parent.contents.index(self) - if hasattr(replaceWith, 'parent') and replaceWith.parent == self.parent: + if hasattr(replace_with, 'parent') and replace_with.parent == self.parent: # We're replacing this element with one of its siblings. - index = self.parent.contents.index(replaceWith) + index = self.parent.contents.index(replace_with) if index and index < myIndex: # Furthermore, it comes before this element. That # means that when we extract it, the index of this # element will change. myIndex = myIndex - 1 self.extract() - oldParent.insert(myIndex, replaceWith) + oldParent.insert(myIndex, replace_with) + replaceWith = replace_with # BS4 def extract(self): """Destructively rips this element out of the tree.""" @@ -52,7 +53,7 @@ class PageElement(object): #Find the two elements that would be next to each other if #this element (and any children) hadn't been parsed. Connect #the two. - lastChild = self._lastRecursiveChild() + lastChild = self._last_recursive_child() nextElement = lastChild.next if self.previous: @@ -70,7 +71,7 @@ class PageElement(object): self.previousSibling = self.nextSibling = None return self - def _lastRecursiveChild(self): + def _last_recursive_child(self): "Finds the last element beneath this object to be parsed." lastChild = self while hasattr(lastChild, 'contents') and lastChild.contents: @@ -106,11 +107,11 @@ class PageElement(object): previousChild = self.contents[position-1] newChild.previousSibling = previousChild newChild.previousSibling.nextSibling = newChild - newChild.previous = previousChild._lastRecursiveChild() + newChild.previous = previousChild._last_recursive_child() if newChild.previous: newChild.previous.next = newChild - newChildsLastElement = newChild._lastRecursiveChild() + newChildsLastElement = newChild._last_recursive_child() if position >= len(self.contents): newChild.nextSibling = None @@ -144,7 +145,7 @@ class PageElement(object): def find_next(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.find_all_next, name, attrs, text, **kwargs) + return self._find_one(self.find_all_next, name, attrs, text, **kwargs) findNext = find_next # BS3 def find_all_next(self, name=None, attrs={}, text=None, limit=None, @@ -158,7 +159,7 @@ class PageElement(object): def find_next_sibling(self, name=None, attrs={}, text=None, **kwargs): """Returns the closest sibling to this Tag that matches the given criteria and appears after this Tag in the document.""" - return self._findOne(self.find_next_siblings, name, attrs, text, + return self._find_one(self.find_next_siblings, name, attrs, text, **kwargs) findNextSibling = find_next_sibling # BS3 @@ -174,7 +175,7 @@ class PageElement(object): def find_previous(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( + return self._find_one( self.find_all_previous, name, attrs, text, **kwargs) findPrevious = find_previous # BS3 @@ -190,7 +191,7 @@ class PageElement(object): def find_previous_sibling(self, name=None, attrs={}, text=None, **kwargs): """Returns the closest sibling to this Tag that matches the given criteria and appears before this Tag in the document.""" - return self._findOne(self.find_previous_siblings, name, attrs, text, + return self._find_one(self.find_previous_siblings, name, attrs, text, **kwargs) findPreviousSibling = find_previous_sibling # BS3 @@ -206,7 +207,7 @@ class PageElement(object): def find_parent(self, name=None, attrs={}, **kwargs): """Returns the closest parent of this Tag that matches the given criteria.""" - # NOTE: We can't use _findOne because findParents takes a different + # NOTE: We can't use _find_one because findParents takes a different # set of arguments. r = None l = self.find_parents(name, attrs, 1) @@ -226,7 +227,7 @@ class PageElement(object): #These methods do the real heavy lifting. - def _findOne(self, method, name, attrs, text, **kwargs): + def _find_one(self, method, name, attrs, text, **kwargs): r = None l = method(name, attrs, text, 1, **kwargs) if l: @@ -310,27 +311,10 @@ class PageElement(object): return self.parents # Utility methods - def substituteEncoding(self, str, encoding=None): + def substitute_encoding(self, str, encoding=None): encoding = encoding or "utf-8" return str.replace("%SOUP-ENCODING%", encoding) - def toEncoding(self, s, encoding=None): - """Encodes an object to a string in some encoding, or to Unicode. - .""" - if isinstance(s, unicode): - if encoding: - s = s.encode(encoding) - elif isinstance(s, str): - if encoding: - s = s.encode(encoding) - else: - s = unicode(s) - else: - if encoding: - s = self.toEncoding(str(s), encoding) - else: - s = unicode(s) - return s class NavigableString(unicode, PageElement): @@ -386,6 +370,7 @@ class Comment(NavigableString): PREFIX = u'<!--' SUFFIX = u'-->' + class Declaration(NavigableString): PREFIX = u'<!' SUFFIX = u'!>' @@ -524,10 +509,7 @@ class Tag(PageElement): def __eq__(self, other): """Returns true iff this tag has the same name, the same attributes, - and the same contents (recursively) as the given tag. - - XXX: right now this will return false if two tags have the - same attributes in a different order. Should this be fixed?""" + and the same contents (recursively) as the given tag.""" if not hasattr(other, 'name') or not hasattr(other, 'attrs') or not hasattr(other, 'contents') or self.name != other.name or self.attrs != other.attrs or len(self) != len(other): return False for i in range(0, len(self.contents)): @@ -578,7 +560,7 @@ class Tag(PageElement): if (self.contains_substitutions and eventual_encoding is not None and '%SOUP-ENCODING%' in val): - val = self.substituteEncoding(val, eventual_encoding) + val = self.substitute_encoding(val, eventual_encoding) decoded = (key + '=' + EntitySubstitution.substitute_xml(val, True)) @@ -702,15 +684,13 @@ class Tag(PageElement): #Generator methods @property def children(self): - for i in range(0, len(self.contents)): - yield self.contents[i] - raise StopIteration + return iter(self.contents) # XXX This seems to be untested. @property def recursive_children(self): if not len(self.contents): - raise StopIteration - stopNode = self._lastRecursiveChild().next + raise StopIteration # XXX return instead? + stopNode = self._last_recursive_child().next current = self.contents[0] while current is not stopNode: yield current diff --git a/tests/test_tree.py b/tests/test_tree.py index c61b326..f2989fe 100644 --- a/tests/test_tree.py +++ b/tests/test_tree.py @@ -557,12 +557,12 @@ class TestTreeModification(SoupTest): text = "<a><b></b><c>Foo<d></d></c></a><a><e></e></a>" soup = self.soup(text) c = soup.c - soup.c.replaceWith(c) + soup.c.replace_with(c) self.assertEquals(soup.decode(), self.document_for(text)) def test_replace_final_node(self): soup = self.soup("<b>Argh!</b>") - soup.find(text="Argh!").replaceWith("Hooray!") + soup.find(text="Argh!").replace_with("Hooray!") new_text = soup.find(text="Hooray!") b = soup.b self.assertEqual(new_text.previous, b) @@ -635,7 +635,7 @@ class TestTreeModification(SoupTest): soup = self.soup( "<p>There's <b>no</b> business like <b>show</b> business</p>") no, show = soup.find_all('b') - show.replaceWith(no) + show.replace_with(no) self.assertEquals( soup.decode(), self.document_for( @@ -654,7 +654,7 @@ class TestTreeModification(SoupTest): # right") with the <f> tag ("refuse"). remove_tag = soup.b move_tag = soup.f - remove_tag.replaceWith(move_tag) + remove_tag.replace_with(move_tag) self.assertEqual( soup.decode(), self.document_for( |