Python etree._ElementUnicodeResult方法代码示例

# 需要导入模块: from lxml import etree [as 别名]
# 或者: from lxml.etree import _ElementUnicodeResult [as 别名]
def extract_value(self, html, is_source=False):
        """
        Use css_select or re_select to extract a field value
        :return:
        """
        value = ''
        if self.css_select:
            value = html.cssselect(self.css_select)
        elif self.xpath_select:
            value = html.xpath(self.xpath_select)
        else:
            raise ValueError('%s field: css_select or xpath_select is expected' % self.__class__.__name__)
        if is_source:
            return value
        if isinstance(value, list) and len(value) == 1:
            if isinstance(value[0], etree._Element):
                text = ''
                for node in value[0].itertext():
                    text += node.strip()
                value = text
            if isinstance(value[0], str) or isinstance(value[0], etree._ElementUnicodeResult):
                value = ''.join(value)
        if self.default is not None:
            value = value if value else self.default
        return value 

# 需要导入模块: from lxml import etree [as 别名]
# 或者: from lxml.etree import _ElementUnicodeResult [as 别名]
def get_value(self, element):
        if self.elements:
            value = {}
            for child in self.elements:
                value[child.name] = child.read_value(element)
            return value
        elif type(element) == etree._ElementStringResult:
            value = str(element)
        elif type(element) == etree._ElementUnicodeResult:
            value = unicode(element)
        else:
            value = self.element_tostring(element)
        return value 

# 需要导入模块: from lxml import etree [as 别名]
# 或者: from lxml.etree import _ElementUnicodeResult [as 别名]
def _parse_element(self, element):
        # Extract text appropriately based on it's type
        if isinstance(element, etree._ElementUnicodeResult):
            strings = [node for node in element]
        else:
            strings = [node for node in element.itertext()]

        string = "".join(strings)
        return string if string else self.default 

# 需要导入模块: from lxml import etree [as 别名]
# 或者: from lxml.etree import _ElementUnicodeResult [as 别名]
def xpath(self, selector: str, *, first: bool = False, _encoding: str = None) -> _XPath:
        """Given an XPath selector, returns a list of
        :class:`Element <Element>` objects or a single one.

        :param selector: XPath Selector to use.
        :param first: Whether or not to return just the first result.
        :param _encoding: The encoding format.

        If a sub-selector is specified (e.g. ``//a/@href``), a simple
        list of results is returned.

        See W3School's `XPath Examples
        <https://www.w3schools.com/xml/xpath_examples.asp>`_
        for more details.

        If ``first`` is ``True``, only returns the first
        :class:`Element <Element>` found.
        """
        selected = self.lxml.xpath(selector)

        elements = [
            Element(element=selection, default_encoding=_encoding or self.encoding)
            if not isinstance(selection, etree._ElementUnicodeResult) else str(selection)
            for selection in selected
        ]

        return _get_first_or_list(elements, first) 

# 需要导入模块: from lxml import etree [as 别名]
# 或者: from lxml.etree import _ElementUnicodeResult [as 别名]
def is_attribute(tree, xpath, namespaces):
    """ Test if a given xpath matches and that match is an attribute

    An xpath attribute search will only match one item"""
    if xpath_matches(tree, xpath, namespaces):
        match = tree.xpath(xpath, namespaces=namespaces)
        if isinstance(match[0], etree._ElementStringResult):
            return True
        elif isinstance(match[0], etree._ElementUnicodeResult):
            return True
    return False 

# 需要导入模块: from lxml import etree [as 别名]
# 或者: from lxml.etree import _ElementUnicodeResult [as 别名]
def _get_username_from_saml_etree(self, signed_xml):
        xpath_with_namespaces = self._make_xpath_builder()

        xpath_fun = xpath_with_namespaces(self.xpath_username_location)
        xpath_result = xpath_fun(signed_xml)

        if isinstance(xpath_result, etree._ElementUnicodeResult):
            return xpath_result
        if type(xpath_result) is list and len(xpath_result) > 0:
            return xpath_result[0]

        self.log.warning('Could not find name from name XPath')
        return None 

# 需要导入模块: from lxml import etree [as 别名]
# 或者: from lxml.etree import _ElementUnicodeResult [as 别名]
def xpath(self, selector: str, *, clean: bool = False, first: bool = False, _encoding: str = None) -> _XPath:
        """Given an XPath selector, returns a list of
        :class:`Element <Element>` objects or a single one.

        :param selector: XPath Selector to use.
        :param clean: Whether or not to sanitize the found HTML of ``<script>`` and ``<style>`` tags.
        :param first: Whether or not to return just the first result.
        :param _encoding: The encoding format.

        If a sub-selector is specified (e.g. ``//a/@href``), a simple
        list of results is returned.

        See W3School's `XPath Examples
        <https://www.w3schools.com/xml/xpath_examples.asp>`_
        for more details.

        If ``first`` is ``True``, only returns the first
        :class:`Element <Element>` found.
        """
        selected = self.lxml.xpath(selector)

        elements = [
            Element(element=selection, url=self.url, default_encoding=_encoding or self.encoding)
            if not isinstance(selection, etree._ElementUnicodeResult) else str(selection)
            for selection in selected
        ]

        # Sanitize the found HTML.
        if clean:
            elements_copy = elements.copy()
            elements = []

            for element in elements_copy:
                element.raw_html = lxml_html_tostring(cleaner.clean_html(element.lxml))
                elements.append(element)

        return _get_first_or_list(elements, first)