Python ElementTree.XMLParser方法代码示例

# 需要导入模块: from xml.etree import ElementTree [as 别名]
# 或者: from xml.etree.ElementTree import XMLParser [as 别名]
def parse(source, binaryfp=None):
    """Parse ArtsXML file from source.

    Args:
        source (str): Filename or file pointer.

    Returns:
        xml.etree.ElementTree: XML Tree of the ARTS data file.

    """
    arts_element = type('ARTSElementBinaryFP',
                        ARTSElement.__bases__,
                        dict(ARTSElement.__dict__))
    arts_element.binaryfp = binaryfp
    return ElementTree.parse(source,
                             parser=ElementTree.XMLParser(
                                 target=ElementTree.TreeBuilder(
                                     element_factory=arts_element))) 

# 需要导入模块: from xml.etree import ElementTree [as 别名]
# 或者: from xml.etree.ElementTree import XMLParser [as 别名]
def bug_200708_close():
    """

    Test default builder.
    >>> parser = ET.XMLParser() # default
    >>> parser.feed("<element>some text</element>")
    >>> summarize(parser.close())
    'element'

    Test custom builder.
    >>> class EchoTarget:
    ...     def close(self):
    ...         return ET.Element("element") # simulate root
    >>> parser = ET.XMLParser(EchoTarget())
    >>> parser.feed("<element>some text</element>")
    >>> summarize(parser.close())
    'element'

    """ 

# 需要导入模块: from xml.etree import ElementTree [as 别名]
# 或者: from xml.etree.ElementTree import XMLParser [as 别名]
def __init__(self, xml=None, rootnode=None):
        if xml is None and rootnode is None:
            xml = default_xml
        if rootnode is None:
            if sys.platform.startswith('win'):
                enc = 'ISO-8859-1'
            else:
                enc = 'UTF-8'
            self.dom = ElementTree.fromstring(xml, ElementTree.XMLParser(encoding=enc))
        else:
            self.dom = rootnode

        # determine OME namespaces
        self.ns = get_namespaces(self.dom)
        if __name__ == '__main__':
            if self.ns['ome'] is None:
                raise Exception("Error: String not in OME-XML format")

        # generate a uuid if there is none
        # < OME UUID = "urn:uuid:ef8af211-b6c1-44d4-97de-daca46f16346"
        omeElem = self.dom
        if not omeElem.get('UUID'):
            omeElem.set('UUID', 'urn:uuid:'+str(uuid.uuid4()))
        self.uuidStr = omeElem.get('UUID') 

# 需要导入模块: from xml.etree import ElementTree [as 别名]
# 或者: from xml.etree.ElementTree import XMLParser [as 别名]
def fetch_filtered_daily_feeds(self, day, filter_parm):
        """ Fetch the feed for +day+ and returns an ElementTree instance. """
        # import xml.etree.ElementTree as ET

        from xml.etree import ElementTree
        from htmlentitydefs import name2codepoint

        if self.FEED_PASSWORD is None:
            raise ValueError("%s.FEED_PASSWORD must be set." % self.__class__.__name__)

        r = requests.get(self.FEED_FILTER_URL % (day.strftime('%d-%m-%Y'), filter_parm),
                         auth=(self.FEED_USER, self.FEED_PASSWORD),
                         verify=False,
                         timeout=60)

        r.raise_for_status()

        parser = ElementTree.XMLParser()
        parser.parser.UseForeignDTD(True)
        parser.entity.update((x, unichr(i)) for x, i in name2codepoint.iteritems())
        etree = ElementTree

        return etree.fromstring(r.text.encode('utf-8'), parser=parser) 

# 需要导入模块: from xml.etree import ElementTree [as 别名]
# 或者: from xml.etree.ElementTree import XMLParser [as 别名]
def fetch_daily_feeds(self, day):
        """ Fetch the feed for +day+ and returns an ElementTree instance. """
        # import xml.etree.ElementTree as ET

        from xml.etree import ElementTree
        from htmlentitydefs import name2codepoint

        if self.FEED_PASSWORD is None:
            raise ValueError("%s.FEED_PASSWORD must be set." % self.__class__.__name__)

        r = requests.get(self.FEED_URL % day.strftime('%d-%m-%Y'),
                         auth=(self.FEED_USER, self.FEED_PASSWORD),
                         verify=False,
                         timeout=60)

        r.raise_for_status()

        parser = ElementTree.XMLParser()
        parser.parser.UseForeignDTD(True)
        parser.entity.update((x, unichr(i)) for x, i in name2codepoint.iteritems())
        etree = ElementTree

        return etree.fromstring(r.text.encode('utf-8'), parser=parser) 

# 需要导入模块: from xml.etree import ElementTree [as 别名]
# 或者: from xml.etree.ElementTree import XMLParser [as 别名]
def read(self):
        parser = ET.XMLParser()
        tree = ET.parse(self.filename, parser)
        root = tree.getroot()

        if root.tag != "Xdmf":
            raise ReadError()

        version = root.get("Version")

        if version.split(".")[0] == "2":
            return self.read_xdmf2(root)

        if version.split(".")[0] != "3":
            raise ReadError("Unknown XDMF version {}.".format(version))

        return self.read_xdmf3(root) 

# 需要导入模块: from xml.etree import ElementTree [as 别名]
# 或者: from xml.etree.ElementTree import XMLParser [as 别名]
def parse_impl(self):
        """
        Parses the HTML content as a stream. This is far less memory
        intensive than loading the entire HTML file into memory, like
        BeautifulSoup does.
        """

        # Cast to str to ensure not unicode under Python 2, as the parser
        # doesn't like that.
        parser = XMLParser(encoding=str('UTF-8'))
        element_iter = ET.iterparse(self.handle, events=("start", "end"), parser=parser)
        for pos, element in element_iter:
            tag, class_attr = _tag_and_class_attr(element)
            if tag == "h1" and pos == "end":
                if not self.user:
                    self.user = element.text.strip()
            elif tag == "div" and "thread" in class_attr and pos == "start":
                participants = self.parse_participants(element)
                thread = self.parse_thread(participants, element_iter, True)
                self.save_thread(thread) 

# 需要导入模块: from xml.etree import ElementTree [as 别名]
# 或者: from xml.etree.ElementTree import XMLParser [as 别名]
def entity():
    """
    Test entity handling.

    1) good entities

    >>> e = ET.XML("<document title='&#x8230;'>test</document>")
    >>> serialize(e)
    '<document title="&#33328;">test</document>'

    2) bad entities

    >>> ET.XML("<document>&entity;</document>")
    Traceback (most recent call last):
    ParseError: undefined entity: line 1, column 10

    >>> ET.XML(ENTITY_XML)
    Traceback (most recent call last):
    ParseError: undefined entity &entity;: line 5, column 10

    3) custom entity

    >>> parser = ET.XMLParser()
    >>> parser.entity["entity"] = "text"
    >>> parser.feed(ENTITY_XML)
    >>> root = parser.close()
    >>> serialize(root)
    '<document>text</document>'
    """ 

# 需要导入模块: from xml.etree import ElementTree [as 别名]
# 或者: from xml.etree.ElementTree import XMLParser [as 别名]
def load_xml(file_name):  # Load an XML file
    try:
        parser = ET.XMLParser(encoding="utf-8")
        return ET.parse(base_dir() + file_name, parser=parser)
    except IOError as ex:
        if ex.errno == 2:
            raise e.FileNotFound
        else:
            raise e.LoadFileException(str(ex)+'\nUnable to load XML ' + base_dir() + file_name) 

# 需要导入模块: from xml.etree import ElementTree [as 别名]
# 或者: from xml.etree.ElementTree import XMLParser [as 别名]
def extract_needs_from_html(html):
    # Replace entities, which elementTree can not handle
    html = html.replace('©', '')
    html = html.replace('&', '')

    if sys.version_info >= (3, 0):
        source = StringIO(html)
        parser = ElementTree.XMLParser(encoding="utf-8")
    else:  # Python 2.x
        source = StringIO(html.encode("utf-8"))
        parser = ElementTree.XMLParser(encoding="utf-8")

    # XML knows not nbsp definition, which comes from HTML.
    # So we need to add it
    parser.entity["nbsp"] = ' '

    etree = ElementTree.ElementTree()
    document = etree.parse(source, parser=parser)
    tables = document.findall(".//html:table", NS)

    # Sphinx <3.0 start html-code with:
    #    <html xmlns="http://www.w3.org/1999/xhtml">
    # Sphinx >= 3.0 starts it with:
    #    <html>
    # So above search will not work for Sphinx >= 3.0 and we try a new one
    if len(tables) == 0:
        tables = document.findall(".//html:table", {'html': ''})

    return [HtmlNeed(table) for table in tables if 'need' in table.get('class', '')] 

# 需要导入模块: from xml.etree import ElementTree [as 别名]
# 或者: from xml.etree.ElementTree import XMLParser [as 别名]
def __init__(self):
        self.tree_builder = _TerminationDetectingTreeBuilder()
        self.xml_tree_builder = et.XMLParser(target=self.tree_builder) 

# 需要导入模块: from xml.etree import ElementTree [as 别名]
# 或者: from xml.etree.ElementTree import XMLParser [as 别名]
def read_xml():
    if not xbmcvfs.exists(FILENAME):
        return ET.Element(ROOT_TAG)

    parser = ET.XMLParser(target=CommentedTreeBuilder())
    with closing(xbmcvfs.File(FILENAME)) as as_xml:
        try:
            return ET.parse(as_xml, parser).getroot()
        except ET.ParseError:
            log("Can't parse advancedsettings.xml", xbmc.LOGWARNING) 

# 需要导入模块: from xml.etree import ElementTree [as 别名]
# 或者: from xml.etree.ElementTree import XMLParser [as 别名]
def parseMeta(self, schid, clid):
        (error, meta) = ts3.getClientVariable(schid, clid, ts3defines.ClientProperties.CLIENT_META_DATA)
        # print(re.search('(<{0}.*>.*</{0}>)'.format(self.tag), meta))
        try: meta = re.search('<{0}>(.*)</{0}>'.format(self.tag), meta).group(0)
        except AttributeError: return False
        # print('meta_strip: %s'%meta.strip())
        # print('xml: %s'%xml.fromstring(meta.strip(), parser = xml.XMLParser(encoding="utf-8")))
        # print('xml_sub: %s'%xml.fromstring(meta.strip(), parser = xml.XMLParser(encoding="utf-8")).getchildren())
        # print('xml_sub[0]: %s'%xml.fromstring(meta.strip(), parser = xml.XMLParser(encoding="utf-8")).getchildren()[0])
        return xml.fromstring(meta.strip(), parser = xml.XMLParser(encoding="utf-8")).getchildren()[0] 

# 需要导入模块: from xml.etree import ElementTree [as 别名]
# 或者: from xml.etree.ElementTree import XMLParser [as 别名]
def getresponse(self,input):
        lines=input.split(b"<?xml")
        content = {}
        for line in lines:
            if line==b'':
                continue
            line=b"<?xml"+line
            parser = ET.XMLParser(encoding="utf-8")
            tree = ET.fromstring(line, parser=parser)
            e = ET.ElementTree(tree).getroot()
            for atype in e.findall('response'):
                for field in atype.attrib:
                    content[field]=atype.attrib[field]
        return content 

# 需要导入模块: from xml.etree import ElementTree [as 别名]
# 或者: from xml.etree.ElementTree import XMLParser [as 别名]
def getlog(self,input):
        lines=input.split(b"<?xml")
        data = []
        for line in lines:
            if line==b'':
                continue
            line=b"<?xml"+line
            parser = ET.XMLParser(encoding="utf-8")
            tree = ET.fromstring(line, parser=parser)
            e = ET.ElementTree(tree).getroot()
            for atype in e.findall('log'):
                if 'value' in atype.attrib:
                    data.append(atype.attrib['value'])
        return data