Python xml.dom.Node.TEXT_NODE Examples

The following are 30 code examples of xml.dom.Node.TEXT_NODE(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module xml.dom.Node , or try the search function .
Example #1
Source File: parser.py    From wechat-python-sdk with BSD 2-Clause "Simplified" License 6 votes vote down vote up 
def _element2dict(self, parent):
        """
        将单个节点转换为 dict
        """
        d = {}
        for node in parent.childNodes:
            if not isinstance(node, minidom.Element):
                continue
            if not node.hasChildNodes():
                continue

            if node.childNodes[0].nodeType == minidom.Node.ELEMENT_NODE:
                try:
                    d[node.tagName]
                except KeyError:
                    d[node.tagName] = []
                d[node.tagName].append(self._element2dict(node))
            elif len(node.childNodes) == 1 and node.childNodes[0].nodeType in [minidom.Node.CDATA_SECTION_NODE, minidom.Node.TEXT_NODE]:
                d[node.tagName] = node.childNodes[0].data
        return d
Example #2
Source File: expatbuilder.py    From oss-ftp with MIT License 6 votes vote down vote up 
def _handle_white_text_nodes(self, node, info):
        if (self._options.whitespace_in_element_content
            or not info.isElementContent()):
            return

        # We have element type information and should remove ignorable
        # whitespace; identify for text nodes which contain only
        # whitespace.
        L = []
        for child in node.childNodes:
            if child.nodeType == TEXT_NODE and not child.data.strip():
                L.append(child)

        # Remove ignorable whitespace from the tree.
        for child in L:
            node.removeChild(child)
Example #3
Source File: expatbuilder.py    From oss-ftp with MIT License 6 votes vote down vote up 
def character_data_handler_cdata(self, data):
        childNodes = self.curNode.childNodes
        if self._cdata:
            if (  self._cdata_continue
                  and childNodes[-1].nodeType == CDATA_SECTION_NODE):
                childNodes[-1].appendData(data)
                return
            node = self.document.createCDATASection(data)
            self._cdata_continue = True
        elif childNodes and childNodes[-1].nodeType == TEXT_NODE:
            node = childNodes[-1]
            value = node.data + data
            d = node.__dict__
            d['data'] = d['nodeValue'] = value
            return
        else:
            node = minidom.Text()
            d = node.__dict__
            d['data'] = d['nodeValue'] = data
            d['ownerDocument'] = self.document
        _append_child(self.curNode, node)
Example #4
Source File: dom.py    From nzb-subliminal with GNU General Public License v3.0 6 votes vote down vote up 
def getNodeDetails(self, node):
        if node.nodeType == Node.DOCUMENT_TYPE_NODE:
            return _base.DOCTYPE, node.name, node.publicId, node.systemId

        elif node.nodeType in (Node.TEXT_NODE, Node.CDATA_SECTION_NODE):
            return _base.TEXT, node.nodeValue

        elif node.nodeType == Node.ELEMENT_NODE:
            attrs = {}
            for attr in node.attributes.keys():
                attr = node.getAttributeNode(attr)
                attrs[(attr.namespaceURI,attr.localName)] = attr.value
            return (_base.ELEMENT, node.namespaceURI, node.nodeName, 
                    attrs, node.hasChildNodes())

        elif node.nodeType == Node.COMMENT_NODE:
            return _base.COMMENT, node.nodeValue

        elif node.nodeType in (Node.DOCUMENT_NODE, Node.DOCUMENT_FRAGMENT_NODE):
            return (_base.DOCUMENT,)

        else:
            return _base.UNKNOWN, node.nodeType
Example #5
Source File: expatbuilder.py    From Computable with MIT License 6 votes vote down vote up 
def _handle_white_text_nodes(self, node, info):
        if (self._options.whitespace_in_element_content
            or not info.isElementContent()):
            return

        # We have element type information and should remove ignorable
        # whitespace; identify for text nodes which contain only
        # whitespace.
        L = []
        for child in node.childNodes:
            if child.nodeType == TEXT_NODE and not child.data.strip():
                L.append(child)

        # Remove ignorable whitespace from the tree.
        for child in L:
            node.removeChild(child)
Example #6
Source File: expatbuilder.py    From pmatic with GNU General Public License v2.0 6 votes vote down vote up 
def _handle_white_text_nodes(self, node, info):
        if (self._options.whitespace_in_element_content
            or not info.isElementContent()):
            return

        # We have element type information and should remove ignorable
        # whitespace; identify for text nodes which contain only
        # whitespace.
        L = []
        for child in node.childNodes:
            if child.nodeType == TEXT_NODE and not child.data.strip():
                L.append(child)

        # Remove ignorable whitespace from the tree.
        for child in L:
            node.removeChild(child)
Example #7
Source File: expatbuilder.py    From Computable with MIT License 6 votes vote down vote up 
def character_data_handler_cdata(self, data):
        childNodes = self.curNode.childNodes
        if self._cdata:
            if (  self._cdata_continue
                  and childNodes[-1].nodeType == CDATA_SECTION_NODE):
                childNodes[-1].appendData(data)
                return
            node = self.document.createCDATASection(data)
            self._cdata_continue = True
        elif childNodes and childNodes[-1].nodeType == TEXT_NODE:
            node = childNodes[-1]
            value = node.data + data
            d = node.__dict__
            d['data'] = d['nodeValue'] = value
            return
        else:
            node = minidom.Text()
            d = node.__dict__
            d['data'] = d['nodeValue'] = data
            d['ownerDocument'] = self.document
        _append_child(self.curNode, node)
Example #8
Source File: expatbuilder.py    From BinderFilter with MIT License 6 votes vote down vote up 
def _handle_white_text_nodes(self, node, info):
        if (self._options.whitespace_in_element_content
            or not info.isElementContent()):
            return

        # We have element type information and should remove ignorable
        # whitespace; identify for text nodes which contain only
        # whitespace.
        L = []
        for child in node.childNodes:
            if child.nodeType == TEXT_NODE and not child.data.strip():
                L.append(child)

        # Remove ignorable whitespace from the tree.
        for child in L:
            node.removeChild(child)
Example #9
Source File: expatbuilder.py    From Imogen with MIT License 6 votes vote down vote up 
def _handle_white_text_nodes(self, node, info):
        if (self._options.whitespace_in_element_content
            or not info.isElementContent()):
            return

        # We have element type information and should remove ignorable
        # whitespace; identify for text nodes which contain only
        # whitespace.
        L = []
        for child in node.childNodes:
            if child.nodeType == TEXT_NODE and not child.data.strip():
                L.append(child)

        # Remove ignorable whitespace from the tree.
        for child in L:
            node.removeChild(child)
Example #10
Source File: expatbuilder.py    From BinderFilter with MIT License 6 votes vote down vote up 
def character_data_handler_cdata(self, data):
        childNodes = self.curNode.childNodes
        if self._cdata:
            if (  self._cdata_continue
                  and childNodes[-1].nodeType == CDATA_SECTION_NODE):
                childNodes[-1].appendData(data)
                return
            node = self.document.createCDATASection(data)
            self._cdata_continue = True
        elif childNodes and childNodes[-1].nodeType == TEXT_NODE:
            node = childNodes[-1]
            value = node.data + data
            d = node.__dict__
            d['data'] = d['nodeValue'] = value
            return
        else:
            node = minidom.Text()
            d = node.__dict__
            d['data'] = d['nodeValue'] = data
            d['ownerDocument'] = self.document
        _append_child(self.curNode, node)
Example #11
Source File: expatbuilder.py    From Fluid-Designer with GNU General Public License v3.0 6 votes vote down vote up 
def character_data_handler_cdata(self, data):
        childNodes = self.curNode.childNodes
        if self._cdata:
            if (  self._cdata_continue
                  and childNodes[-1].nodeType == CDATA_SECTION_NODE):
                childNodes[-1].appendData(data)
                return
            node = self.document.createCDATASection(data)
            self._cdata_continue = True
        elif childNodes and childNodes[-1].nodeType == TEXT_NODE:
            node = childNodes[-1]
            value = node.data + data
            node.data = value
            return
        else:
            node = minidom.Text()
            node.data = data
            node.ownerDocument = self.document
        _append_child(self.curNode, node)
Example #12
Source File: expatbuilder.py    From jawfish with MIT License 6 votes vote down vote up 
def character_data_handler_cdata(self, data):
        childNodes = self.curNode.childNodes
        if self._cdata:
            if (  self._cdata_continue
                  and childNodes[-1].nodeType == CDATA_SECTION_NODE):
                childNodes[-1].appendData(data)
                return
            node = self.document.createCDATASection(data)
            self._cdata_continue = True
        elif childNodes and childNodes[-1].nodeType == TEXT_NODE:
            node = childNodes[-1]
            value = node.data + data
            node.data = value
            return
        else:
            node = minidom.Text()
            node.data = data
            node.ownerDocument = self.document
        _append_child(self.curNode, node)
Example #13
Source File: expatbuilder.py    From Fluid-Designer with GNU General Public License v3.0 6 votes vote down vote up 
def _handle_white_text_nodes(self, node, info):
        if (self._options.whitespace_in_element_content
            or not info.isElementContent()):
            return

        # We have element type information and should remove ignorable
        # whitespace; identify for text nodes which contain only
        # whitespace.
        L = []
        for child in node.childNodes:
            if child.nodeType == TEXT_NODE and not child.data.strip():
                L.append(child)

        # Remove ignorable whitespace from the tree.
        for child in L:
            node.removeChild(child)
Example #14
Source File: expatbuilder.py    From ironpython2 with Apache License 2.0 6 votes vote down vote up 
def _handle_white_text_nodes(self, node, info):
        if (self._options.whitespace_in_element_content
            or not info.isElementContent()):
            return

        # We have element type information and should remove ignorable
        # whitespace; identify for text nodes which contain only
        # whitespace.
        L = []
        for child in node.childNodes:
            if child.nodeType == TEXT_NODE and not child.data.strip():
                L.append(child)

        # Remove ignorable whitespace from the tree.
        for child in L:
            node.removeChild(child)
Example #15
Source File: expatbuilder.py    From Imogen with MIT License 6 votes vote down vote up 
def character_data_handler_cdata(self, data):
        childNodes = self.curNode.childNodes
        if self._cdata:
            if (  self._cdata_continue
                  and childNodes[-1].nodeType == CDATA_SECTION_NODE):
                childNodes[-1].appendData(data)
                return
            node = self.document.createCDATASection(data)
            self._cdata_continue = True
        elif childNodes and childNodes[-1].nodeType == TEXT_NODE:
            node = childNodes[-1]
            value = node.data + data
            node.data = value
            return
        else:
            node = minidom.Text()
            node.data = data
            node.ownerDocument = self.document
        _append_child(self.curNode, node)
Example #16
Source File: expatbuilder.py    From ironpython2 with Apache License 2.0 6 votes vote down vote up 
def character_data_handler_cdata(self, data):
        childNodes = self.curNode.childNodes
        if self._cdata:
            if (  self._cdata_continue
                  and childNodes[-1].nodeType == CDATA_SECTION_NODE):
                childNodes[-1].appendData(data)
                return
            node = self.document.createCDATASection(data)
            self._cdata_continue = True
        elif childNodes and childNodes[-1].nodeType == TEXT_NODE:
            node = childNodes[-1]
            value = node.data + data
            d = node.__dict__
            d['data'] = d['nodeValue'] = value
            return
        else:
            node = minidom.Text()
            d = node.__dict__
            d['data'] = d['nodeValue'] = data
            d['ownerDocument'] = self.document
        _append_child(self.curNode, node)
Example #17
Source File: expatbuilder.py    From pmatic with GNU General Public License v2.0 6 votes vote down vote up 
def character_data_handler_cdata(self, data):
        childNodes = self.curNode.childNodes
        if self._cdata:
            if (  self._cdata_continue
                  and childNodes[-1].nodeType == CDATA_SECTION_NODE):
                childNodes[-1].appendData(data)
                return
            node = self.document.createCDATASection(data)
            self._cdata_continue = True
        elif childNodes and childNodes[-1].nodeType == TEXT_NODE:
            node = childNodes[-1]
            value = node.data + data
            d = node.__dict__
            d['data'] = d['nodeValue'] = value
            return
        else:
            node = minidom.Text()
            d = node.__dict__
            d['data'] = d['nodeValue'] = data
            d['ownerDocument'] = self.document
        _append_child(self.curNode, node)
Example #18
Source File: expatbuilder.py    From ironpython3 with Apache License 2.0 6 votes vote down vote up 
def character_data_handler_cdata(self, data):
        childNodes = self.curNode.childNodes
        if self._cdata:
            if (  self._cdata_continue
                  and childNodes[-1].nodeType == CDATA_SECTION_NODE):
                childNodes[-1].appendData(data)
                return
            node = self.document.createCDATASection(data)
            self._cdata_continue = True
        elif childNodes and childNodes[-1].nodeType == TEXT_NODE:
            node = childNodes[-1]
            value = node.data + data
            node.data = value
            return
        else:
            node = minidom.Text()
            node.data = data
            node.ownerDocument = self.document
        _append_child(self.curNode, node)
Example #19
Source File: expatbuilder.py    From ironpython3 with Apache License 2.0 6 votes vote down vote up 
def _handle_white_text_nodes(self, node, info):
        if (self._options.whitespace_in_element_content
            or not info.isElementContent()):
            return

        # We have element type information and should remove ignorable
        # whitespace; identify for text nodes which contain only
        # whitespace.
        L = []
        for child in node.childNodes:
            if child.nodeType == TEXT_NODE and not child.data.strip():
                L.append(child)

        # Remove ignorable whitespace from the tree.
        for child in L:
            node.removeChild(child)
Example #20
Source File: expatbuilder.py    From jawfish with MIT License 6 votes vote down vote up 
def _handle_white_text_nodes(self, node, info):
        if (self._options.whitespace_in_element_content
            or not info.isElementContent()):
            return

        # We have element type information and should remove ignorable
        # whitespace; identify for text nodes which contain only
        # whitespace.
        L = []
        for child in node.childNodes:
            if child.nodeType == TEXT_NODE and not child.data.strip():
                L.append(child)

        # Remove ignorable whitespace from the tree.
        for child in L:
            node.removeChild(child)
Example #21
Source File: parser.py    From wechat-python-sdk with BSD 2-Clause "Simplified" License 5 votes vote down vote up 
def _remove_whitespace_nodes(self, node, unlink=True):
        """
        删除空白无用节点
        """
        remove_list = []
        for child in node.childNodes:
            if child.nodeType == Node.TEXT_NODE and not child.data.strip():
                remove_list.append(child)
            elif child.hasChildNodes():
                self._remove_whitespace_nodes(child, unlink)
        for node in remove_list:
            node.parentNode.removeChild(node)
            if unlink:
                node.unlink()
Example #22
Source File: dom.py    From stopstalk-deployment with MIT License 5 votes vote down vote up 
def getNodeDetails(self, node):
        if node.nodeType == Node.DOCUMENT_TYPE_NODE:
            return base.DOCTYPE, node.name, node.publicId, node.systemId

        elif node.nodeType in (Node.TEXT_NODE, Node.CDATA_SECTION_NODE):
            return base.TEXT, node.nodeValue

        elif node.nodeType == Node.ELEMENT_NODE:
            attrs = {}
            for attr in list(node.attributes.keys()):
                attr = node.getAttributeNode(attr)
                if attr.namespaceURI:
                    attrs[(attr.namespaceURI, attr.localName)] = attr.value
                else:
                    attrs[(None, attr.name)] = attr.value
            return (base.ELEMENT, node.namespaceURI, node.nodeName,
                    attrs, node.hasChildNodes())

        elif node.nodeType == Node.COMMENT_NODE:
            return base.COMMENT, node.nodeValue

        elif node.nodeType in (Node.DOCUMENT_NODE, Node.DOCUMENT_FRAGMENT_NODE):
            return (base.DOCUMENT,)

        else:
            return base.UNKNOWN, node.nodeType
Example #23
Source File: prettyprint.py    From NoobSec-Toolkit with GNU General Public License v2.0 5 votes vote down vote up 
def _collapse(node):
        for child in node.childNodes:
                if child.nodeType == Node.TEXT_NODE and len(child.data.strip()) == 0:
                        child.data = ''
                else:
                        _collapse(child)
Example #24
Source File: dom.py    From learn_python3_spider with MIT License 5 votes vote down vote up 
def getNodeDetails(self, node):
        if node.nodeType == Node.DOCUMENT_TYPE_NODE:
            return base.DOCTYPE, node.name, node.publicId, node.systemId

        elif node.nodeType in (Node.TEXT_NODE, Node.CDATA_SECTION_NODE):
            return base.TEXT, node.nodeValue

        elif node.nodeType == Node.ELEMENT_NODE:
            attrs = {}
            for attr in list(node.attributes.keys()):
                attr = node.getAttributeNode(attr)
                if attr.namespaceURI:
                    attrs[(attr.namespaceURI, attr.localName)] = attr.value
                else:
                    attrs[(None, attr.name)] = attr.value
            return (base.ELEMENT, node.namespaceURI, node.nodeName,
                    attrs, node.hasChildNodes())

        elif node.nodeType == Node.COMMENT_NODE:
            return base.COMMENT, node.nodeValue

        elif node.nodeType in (Node.DOCUMENT_NODE, Node.DOCUMENT_FRAGMENT_NODE):
            return (base.DOCUMENT,)

        else:
            return base.UNKNOWN, node.nodeType
Example #25
Source File: dom.py    From scylla with Apache License 2.0 5 votes vote down vote up 
def getNodeDetails(self, node):
        if node.nodeType == Node.DOCUMENT_TYPE_NODE:
            return base.DOCTYPE, node.name, node.publicId, node.systemId

        elif node.nodeType in (Node.TEXT_NODE, Node.CDATA_SECTION_NODE):
            return base.TEXT, node.nodeValue

        elif node.nodeType == Node.ELEMENT_NODE:
            attrs = {}
            for attr in list(node.attributes.keys()):
                attr = node.getAttributeNode(attr)
                if attr.namespaceURI:
                    attrs[(attr.namespaceURI, attr.localName)] = attr.value
                else:
                    attrs[(None, attr.name)] = attr.value
            return (base.ELEMENT, node.namespaceURI, node.nodeName,
                    attrs, node.hasChildNodes())

        elif node.nodeType == Node.COMMENT_NODE:
            return base.COMMENT, node.nodeValue

        elif node.nodeType in (Node.DOCUMENT_NODE, Node.DOCUMENT_FRAGMENT_NODE):
            return (base.DOCUMENT,)

        else:
            return base.UNKNOWN, node.nodeType
Example #26
Source File: expatbuilder.py    From Imogen with MIT License 5 votes vote down vote up 
def character_data_handler(self, data):
        childNodes = self.curNode.childNodes
        if childNodes and childNodes[-1].nodeType == TEXT_NODE:
            node = childNodes[-1]
            node.data = node.data + data
            return
        node = minidom.Text()
        node.data = node.data + data
        node.ownerDocument = self.document
        _append_child(self.curNode, node)
Example #27
Source File: dom.py    From Building-Recommendation-Systems-with-Python with MIT License 5 votes vote down vote up 
def getNodeDetails(self, node):
        if node.nodeType == Node.DOCUMENT_TYPE_NODE:
            return base.DOCTYPE, node.name, node.publicId, node.systemId

        elif node.nodeType in (Node.TEXT_NODE, Node.CDATA_SECTION_NODE):
            return base.TEXT, node.nodeValue

        elif node.nodeType == Node.ELEMENT_NODE:
            attrs = {}
            for attr in list(node.attributes.keys()):
                attr = node.getAttributeNode(attr)
                if attr.namespaceURI:
                    attrs[(attr.namespaceURI, attr.localName)] = attr.value
                else:
                    attrs[(None, attr.name)] = attr.value
            return (base.ELEMENT, node.namespaceURI, node.nodeName,
                    attrs, node.hasChildNodes())

        elif node.nodeType == Node.COMMENT_NODE:
            return base.COMMENT, node.nodeValue

        elif node.nodeType in (Node.DOCUMENT_NODE, Node.DOCUMENT_FRAGMENT_NODE):
            return (base.DOCUMENT,)

        else:
            return base.UNKNOWN, node.nodeType
Example #28
Source File: dom.py    From Building-Recommendation-Systems-with-Python with MIT License 5 votes vote down vote up 
def getNodeDetails(self, node):
        if node.nodeType == Node.DOCUMENT_TYPE_NODE:
            return base.DOCTYPE, node.name, node.publicId, node.systemId

        elif node.nodeType in (Node.TEXT_NODE, Node.CDATA_SECTION_NODE):
            return base.TEXT, node.nodeValue

        elif node.nodeType == Node.ELEMENT_NODE:
            attrs = {}
            for attr in list(node.attributes.keys()):
                attr = node.getAttributeNode(attr)
                if attr.namespaceURI:
                    attrs[(attr.namespaceURI, attr.localName)] = attr.value
                else:
                    attrs[(None, attr.name)] = attr.value
            return (base.ELEMENT, node.namespaceURI, node.nodeName,
                    attrs, node.hasChildNodes())

        elif node.nodeType == Node.COMMENT_NODE:
            return base.COMMENT, node.nodeValue

        elif node.nodeType in (Node.DOCUMENT_NODE, Node.DOCUMENT_FRAGMENT_NODE):
            return (base.DOCUMENT,)

        else:
            return base.UNKNOWN, node.nodeType
Example #29
Source File: prettyprint.py    From NoobSec-Toolkit with GNU General Public License v2.0 5 votes vote down vote up 
def _writexml_element(self, writer, indent="", addindent="", newl=""):
        # indent = current indentation
        # addindent = indentation to add to higher levels
        # newl = newline string
        writer.write(indent+"<" + self.tagName)

        attrs = self._get_attributes()
        a_names = attrs.keys()
        a_names.sort()

        for a_name in a_names:
                writer.write(" %s=\"" % a_name)
                minidom._write_data(writer, attrs[a_name].value)
                writer.write("\"")
        if self.childNodes:
                if self.childNodes[0].nodeType == Node.TEXT_NODE and len(self.childNodes[0].data) > 0:
                        writer.write(">")
                else:
                        writer.write(">%s"%(newl))
                for node in self.childNodes:
                        node.writexml(writer,indent+addindent,addindent,newl)
                if self.childNodes[-1].nodeType == Node.TEXT_NODE and len(self.childNodes[0].data) > 0:
                        writer.write("</%s>%s" % (self.tagName,newl))
                else:
                        writer.write("%s</%s>%s" % (indent,self.tagName,newl))
        else:
                writer.write("/>%s"%(newl))
Example #30
Source File: expatbuilder.py    From Fluid-Designer with GNU General Public License v3.0 5 votes vote down vote up 
def character_data_handler(self, data):
        childNodes = self.curNode.childNodes
        if childNodes and childNodes[-1].nodeType == TEXT_NODE:
            node = childNodes[-1]
            node.data = node.data + data
            return
        node = minidom.Text()
        node.data = node.data + data
        node.ownerDocument = self.document
        _append_child(self.curNode, node)