Node and all of its subclasses provide you with access to the page's DOM. Instantiating the classes themselves won't do you much good.
+
+
Partial application of parameters. This is used internally but is also very useful with
Browser.load as it allows you to pass data to other functions.
(Provide Example).
-
+
Utility function to search for and get the full path of a file in $PATH.
Check whether a process of the given name is running.
=== modified file 'examples/dynamicdom.py'
--- examples/dynamicdom.py 2007-02-12 23:13:40 +0000
+++ examples/dynamicdom.py 2007-03-05 16:00:30 +0000
@@ -34,13 +34,11 @@
data = browser.document.serialized
if data != previousData:
print "DOM changed!"
- print "New text: %s", repr(browser.document.getElementById("mydiv").text)
- print len(pykhtml.application.children())
+ print "New text:", repr(browser.document.getElementById("mydiv").text)
pykhtml.stopEventLoop()
else:
print "DOM not changed. Checking in 1 second..."
- pykhtml.timer(1, pykhtml.curry(checkForDomChanges, browser, data))
- print len(pykhtml.application.children())
+ pykhtml.timer(1, pykhtml.partial(checkForDomChanges, browser, data))
def main():
browser = pykhtml.Browser()
@@ -48,9 +46,9 @@
browser.setHtml(page)
# to see if the DOM has changed we poll and access
# browser.document.serialized and compare its to
- # the previous calling. Note the use of pykhtml.curry
+ # the previous calling. Note the use of pykhtml.partial
# to bind the serialised data to the function
- pykhtml.timer(1, pykhtml.curry(checkForDomChanges, browser, browser.document.serialized))
+ pykhtml.timer(1, pykhtml.partial(checkForDomChanges, browser, browser.document.serialized))
pykhtml.startEventLoop()
if __name__ == "__main__":
=== modified file 'pykhtml/__init__.py'
--- pykhtml/__init__.py 2007-02-12 23:13:40 +0000
+++ pykhtml/__init__.py 2007-03-05 16:00:30 +0000
@@ -20,7 +20,7 @@
-class curry:
+class partial:
""" Partial application of parameters. This is used internally but is also very useful with [[Browser.load]] as it allows you to pass data to other functions.
(Provide Example). """
def __init__(self, fun, *args, **kwargs):
@@ -187,6 +187,13 @@
self.connect(self.part, qt.SIGNAL("docCreated()"), self._slotDocCreated)
self.location = uri
+ def _setOnLoadHandler(self, callback):
+ """ If a function is going to be called that changes the URL and we want a callback to be called when the page is loaded, this is the method for you. Does kinda what load does, without loading the page """
+ if self.loadFunction:
+ self.disconnect(self.part, qt.SIGNAL("docCreated()"). self._slotDocCreated)
+ self.loadFunction = callback
+ self.connect(self.part, qt.SIGNAL("docCreated()"), self._slotDocCreated)
+
def _slotDocCreated(self):
self.part.executeScript(DOM.Node(), "window.alert = function() {}")
self.disconnect(self.part, qt.SIGNAL("docCreated()"), self._slotDocCreated)
@@ -196,10 +203,10 @@
self.loadFunction = None
# If _passReferenceToCallbacks, bind this browser to the function
if self._passReferenceToCallbacks:
- func = curry(func, self)
+ func = partial(func, self)
# do this so the DOM loads fully. Cast to an Element -- not strictly correct, but we just want to get to addEvent.
# XX why not just put addEvent in Node and make Document inherit from Node? Document IS meant to be a Node, after all.
- docElement = dom.Element(self.document._d).addEvent("load", func)
+ dom.Element(self.document._d, self).addEvent("load", func)
def setHtml(self, source, url=None):
""" Set the HTML of the browser. Parses the HTML and generates the DOM tree so you can navigate it as usual. As well as the `source` parameter, a `url` parameter allows you to specify a URL with which this source code is linked so that e.g any scripts/images referenced in the HTML will be found. """
=== modified file 'pykhtml/dom.py'
--- pykhtml/dom.py 2007-02-11 15:16:45 +0000
+++ pykhtml/dom.py 2007-03-05 16:00:30 +0000
@@ -5,11 +5,11 @@
_nodeTypeToClass = {}
-def nodeToClass(n):
- return _nodeTypeToClass.get(n.nodeType(), Node)
+def nodeCast(n, browser):
+ return _nodeTypeToClass.get(n.nodeType(), Node)(n, browser)
_elementNameToClassMap = {}
-def elementToObject(e):
- e = _elementNameToClassMap.get(str(e.nodeName().string()).upper(), Element)(e)
+def elementCast(e, browser):
+ e = _elementNameToClassMap.get(str(e.nodeName().string()).upper(), Element)(e, browser)
return e
def registerNode(nodeType, klass):
@@ -20,9 +20,10 @@
class Node(object):
- """ Node and all of its subclasses provide you with read-only access to the page's DOM. Instantiating the classes themselves won't do you much good. """
- def __init__(self, cNode):
+ """ Node and all of its subclasses provide you with access to the page's DOM. Instantiating the classes themselves won't do you much good. """
+ def __init__(self, cNode, browser):
self._ = cNode
+ self.browser = browser
object.__init__(self)
self.__children = None
@@ -39,7 +40,7 @@
elements = self._.childNodes()
for i in xrange(elements.length()):
n = elements.item(i)
- l.append(nodeToClass(n)(n))
+ l.append(nodeCast(n, self.browser))
return self.__children
def childNodes(self):
@@ -49,8 +50,8 @@
class Text(Node):
""" A text node lets you access the text in it using the [[Text.value]] attribute or by converting to a string with str() """
- def __init__(self, cTextNode):
- Node.__init__(self, cTextNode)
+ def __init__(self, cTextNode, browser):
+ Node.__init__(self, cTextNode, browser)
def __str__(self):
return self.value
@@ -67,8 +68,8 @@
class Element(Node):
""" An HTML element. Instances of it provide methods for doing things with the element -- traversing it, adding events, etc. """
- def __init__(self, cElement):
- Node.__init__(self, cElement)
+ def __init__(self, cElement, browser):
+ Node.__init__(self, cElement, browser)
@property
def text(self):
@@ -83,21 +84,21 @@
def getElementById(self, id):
""" Get a reference to an element in the page by its id attribute """
n = self._.getElementById(DOMString(id))
- return nodeToClass(n)(n)
+ return nodeCast(n, self.browser)
def getElementsByTagName(self, name):
""" Get elements by tag name. Returns a generator that you can loop over or flatten into a list with list() """
elements = self._.getElementsByTagName(DOMString(name))
for i in xrange(elements.length()):
node = elements.item(i)
- yield nodeToClass(node)(node)
+ yield nodeCast(node, self.browser)
def getElementsByTagNameNS(self, ns, name):
""" Get elements by tag name given a certain namespace """
elements = self._.getElementsByTagNameNS(DOMString(ns), DOMString(name))
for i in xrange(elements.length()):
node = elements.item(i)
- yield nodeToClass(node)(node)
+ yield nodeCast(node, self.browser)
# convenience
def getElementsByClass(self, className, tagName="*"):
@@ -105,7 +106,7 @@
for element in self.getElementsByTagName(tagName):
if className in str(element.getAttribute(DOMString("class")).string()).split(" "):
e = elements.item(i)
- yield nodeToClass(e)(e)
+ yield nodeCast(e, self.browser)
@property
def tagName(self):
@@ -127,13 +128,13 @@
self._.removeEventListener(DOMString(eventName), _CallbackEventListener.getCallbackInstance(eventName, func), capture)
_CallbackEventListener.remove(eventName, func)
# -- important, we hook to the method not Element base class
-registerNode(1, elementToObject)
+registerNode(1, elementCast)
class Anchor(Element):
""" Anchor elements with an [[Anchor.href]] property """
- def __init__(self, cAnchor):
- Element.__init__(self, cAnchor)
+ def __init__(self, cAnchor, browser):
+ Element.__init__(self, cAnchor, browser)
self._ = sip.cast(self._, _DOM.HTMLAnchorElement)
@property
@@ -143,6 +144,49 @@
registerElement("A", Anchor)
+class Form(Element):
+ """ Form elements contain input elements. You can submit a form with [[Form.submit]] """
+ def __init__(self, cForm, browser):
+ Element.__init__(self, cForm, browser)
+ self._ = sip.cast(self._, _DOM.HTMLFormElement)
+
+ def _getAction(self):
+ return str(self._.action().string())
+ def _setAction(self, action):
+ self._.setAction(DOMString(action))
+ action = property(_getAction, _setAction, None, "The action for this form (the page to which data is to be submited)")
+
+ def _getMethod(self):
+ return str(self._.method().string())
+ def _setMethod(self, method):
+ self._.setMethod(DOMString(method))
+ action = property(_getMethod, _setMethod, None, "The method with which this form is to be submitted (GET, POST, etc)")
+
+ def submit(self, callback):
+ """ Submit the form to the page specified in the action. The callback given is like one you would pass to [[pykthml.Browser.load]] """
+ # load the callback
+ self.browser._setOnLoadHandler(callback)
+ # submit
+ self._.submit()
+
+ def submit(self):
+ """ Submit the form to the page specified in the action """
+ self._.submit()
+registerElement("FORM", Form)
+
+
+class Input(Element):
+ """ Input elements that you can set the value/name of """
+ def __init__(self, cInput, browser):
+ Element.__init__(self, cInput, browser)
+ self._ = sip.cast(self._, _DOM.HTMLInputElement)
+
+ @property
+ def form(self):
+ """ Get the form element this input resides in """
+ return Form(self._.form())
+registerElement("INPUT", Input)
+
#class Title(Element):
#def __init__(self, cTitle):
#Node.__init__(self, cTitle)
@@ -165,21 +209,21 @@
def getElementById(self, id):
""" Get a reference to an element in the page by its id attribute """
n = self._d.getElementById(DOMString(id))
- return nodeToClass(n)(n)
+ return nodeCast(n, self.browser)
def getElementsByTagName(self, name):
""" Get elements by tag name. Returns a generator that you can loop over or flatten into a list with list() """
elements = self._d.getElementsByTagName(DOMString(name))
for i in xrange(elements.length()):
node = elements.item(i)
- yield nodeToClass(node)(node)
+ yield nodeCast(node, self.browser)
def getElementsByTagNameNS(self, ns, name):
""" Get elements by tag name given a certain namespace """
elements = self._d.getElementsByTagNameNS(DOMString(ns), DOMString(name))
for i in xrange(elements.length()):
node = elements.item(i)
- yield nodeToClass(node)(node)
+ yield nodeCast(node, self.browser)
# convenience
def getElementsByClass(self, className, tagName="*"):
@@ -187,7 +231,7 @@
for element in self.getElementsByTagName(tagName):
if className in str(element.getAttribute(DOMString("class")).string()).split(" "):
e = elements.item(i)
- yield nodeToClass(e)(e)
+ yield nodeCast(e, self.browser)
def visit(self, text=None, callback=None, attributes=None, stripSpace=True):
""" Visit a page pointed to by a certain link. This function searches for all links in the document that either: