我们从Python开源项目中，提取了以下50个代码示例，用于说明如何使用xml.etree.ElementTree.parse()。
def pull_item(self, index): img_id = self.ids[index] target = ET.parse(self._annopath % img_id).getroot() img = cv2.imread(self._imgpath % img_id) height, width, channels = img.shape if self.target_transform is not None: target = self.target_transform(target, width, height) if self.transform is not None: target = np.array(target) img, boxes, labels = self.transform(img, target[:, :4], target[:, 4]) # to rgb img = img[:, :, (2, 1, 0)] # img = img.transpose(2, 0, 1) target = np.hstack((boxes, np.expand_dims(labels, axis=1))) return torch.from_numpy(img).permute(2, 0, 1), target, height, width # return torch.from_numpy(img), target, height, width
def read_preposition_senses(self): num_senses_per_prep = [] for filename in os.listdir(self.prep_senses_dir): if '.defs.xml' in filename: prep_str = filename.replace('.defs.xml', '') xml_root = ElementTree.parse("%s/%s" % (self.prep_senses_dir, filename)).getroot() senses = [] for child_el in xml_root.getchildren(): sense_id = child_el.findtext('senseid') if sense_id is not None: # This will add strings like 'into-1(1)' senses.append("%s-%s" % (prep_str, sense_id)) num_senses_per_prep.append(len(senses)) self.prep_senses[prep_str] = senses num_preps = len(self.prep_senses) print >>sys.stderr, "Read senses for %d prepositions." % num_preps print >>sys.stderr, "Senses per preposition: %f" % (float(sum(num_senses_per_prep))/num_preps) # TODO: Take a coarse-grained mapping file and implement the following function.
def find_service_manifest(xml_file): """Find the path to the first service manifest for an application""" root = ET.parse(xml_file).getroot() import_elem = root.find('fabric:ServiceManifestImport', XML_NS) if import_elem is None: raise ValueError('Could not find service manifest import section') ref_elem = import_elem.find('fabric:ServiceManifestRef', XML_NS) if ref_elem is None: raise ValueError('Could not find service manifest reference section') manifest_name = ref_elem.attrib.get('ServiceManifestName', None) if not manifest_name: raise ValueError('Could not find service manifest name') return os.path.join(os.path.dirname(xml_file), manifest_name, 'ServiceManifest.xml')
def parse_service_type(xml_file): """Determines the first avaliable service type and the associated type name""" root = ET.parse(xml_file).getroot() service_type = root.find('fabric:ServiceTypes', XML_NS) if service_type is None: raise ValueError('Could not find service types in service manifest') service_type_kind = None if 'StatelessServiceType' in service_type[0].tag: service_type_kind = 'stateless' else: # For now we only support stateless services for service creation raise ValueError('Unsupported service type') service_type_name = service_type[0].attrib.get('ServiceTypeName', None) if not service_type_name: raise ValueError('Could not find service type name') return (service_type_kind, service_type_name)
def parse_rec(filename): """ Parse a PASCAL VOC xml file """ tree = ET.parse(filename) objects = [] for obj in tree.findall('object'): obj_struct = {} obj_struct['name'] = obj.find('name').text obj_struct['pose'] = obj.find('pose').text obj_struct['truncated'] = int(obj.find('truncated').text) obj_struct['difficult'] = int(obj.find('difficult').text) bbox = obj.find('bndbox') obj_struct['bbox'] = [int(bbox.find('xmin').text), int(bbox.find('ymin').text), int(bbox.find('xmax').text), int(bbox.find('ymax').text)] objects.append(obj_struct) return objects
def parse(inFileName): doc = parsexml_(inFileName) rootNode = doc.getroot() rootTag, rootClass = get_root_tag(rootNode) if rootClass is None: rootTag = 'softPkg' rootClass = softPkg rootObj = rootClass.factory() rootObj.build(rootNode) # Enable Python to collect the space used by the DOM. doc = None ## sys.stdout.write('<?xml version="1.0" ?>\n') ## rootObj.export(sys.stdout, 0, name_=rootTag, ## namespacedef_='', ## pretty_print=True) return rootObj
def parse(inFileName): doc = parsexml_(inFileName) rootNode = doc.getroot() rootTag, rootClass = get_root_tag(rootNode) if rootClass is None: rootTag = 'devicepkg' rootClass = devicepkg rootObj = rootClass.factory() rootObj.build(rootNode) # Enable Python to collect the space used by the DOM. doc = None ## sys.stdout.write('<?xml version="1.0" ?>\n') ## rootObj.export(sys.stdout, 0, name_=rootTag, ## namespacedef_='', ## pretty_print=True) return rootObj
def parse(inFileName): doc = parsexml_(inFileName) rootNode = doc.getroot() rootTag, rootClass = get_root_tag(rootNode) if rootClass is None: rootTag = 'deviceconfiguration' rootClass = deviceconfiguration rootObj = rootClass.factory() rootObj.build(rootNode) # Enable Python to collect the space used by the DOM. doc = None ## sys.stdout.write('<?xml version="1.0" ?>\n') ## rootObj.export(sys.stdout, 0, name_=rootTag, ## namespacedef_='', ## pretty_print=True) return rootObj
def parse(inFileName): doc = parsexml_(inFileName) rootNode = doc.getroot() rootTag, rootClass = get_root_tag(rootNode) if rootClass is None: rootTag = 'domainmanagerconfiguration' rootClass = domainmanagerconfiguration rootObj = rootClass.factory() rootObj.build(rootNode) # Enable Python to collect the space used by the DOM. doc = None ## sys.stdout.write('<?xml version="1.0" ?>\n') ## rootObj.export(sys.stdout, 0, name_=rootTag, ## namespacedef_='', ## pretty_print=True) return rootObj
def parse(inFileName): doc = parsexml_(inFileName) rootNode = doc.getroot() rootTag, rootClass = get_root_tag(rootNode) if rootClass is None: rootTag = 'profile' rootClass = profile rootObj = rootClass.factory() rootObj.build(rootNode) # Enable Python to collect the space used by the DOM. doc = None ## sys.stdout.write('<?xml version="1.0" ?>\n') ## rootObj.export(sys.stdout, 0, name_=rootTag, ## namespacedef_='', ## pretty_print=True) return rootObj
def parse(inFileName): doc = parsexml_(inFileName) rootNode = doc.getroot() rootTag, rootClass = get_root_tag(rootNode) if rootClass is None: rootTag = 'softwareassembly' rootClass = softwareassembly rootObj = rootClass.factory() rootObj.build(rootNode) # Enable Python to collect the space used by the DOM. doc = None ## sys.stdout.write('<?xml version="1.0" ?>\n') ## rootObj.export(sys.stdout, 0, name_=rootTag, ## namespacedef_='', ## pretty_print=True) return rootObj
def parse(inFileName): doc = parsexml_(inFileName) rootNode = doc.getroot() rootTag, rootClass = get_root_tag(rootNode) if rootClass is None: rootTag = 'softwarecomponent' rootClass = softwarecomponent rootObj = rootClass.factory() rootObj.build(rootNode) # Enable Python to collect the space used by the DOM. doc = None ## sys.stdout.write('<?xml version="1.0" ?>\n') ## rootObj.export(sys.stdout, 0, name_=rootTag, ## namespacedef_='', ## pretty_print=True) return rootObj
def parse(inFileName): doc = parsexml_(inFileName) rootNode = doc.getroot() rootTag, rootClass = get_root_tag(rootNode) if rootClass is None: rootTag = 'properties' rootClass = properties rootObj = rootClass.factory() rootObj.build(rootNode) # Enable Python to collect the space used by the DOM. doc = None ## sys.stdout.write('<?xml version="1.0" ?>\n') ## rootObj.export(sys.stdout, 0, name_=rootTag, ## namespacedef_='', ## pretty_print=True) return rootObj
def parse(stream): """Parse a stream containing XML into an ``InputDefinition``. :param stream: stream containing XML to parse. :return: definition: an ``InputDefinition`` object. """ definition = InputDefinition() # parse XML from the stream, then get the root node root = ET.parse(stream).getroot() for node in root: if node.tag == "configuration": # get config for each stanza definition.inputs = parse_xml_data(node, "stanza") else: definition.metadata[node.tag] = node.text return definition
def get_pub_dic_xml(file_name = 'data/proton-beam-all.xml'): tree = ET.parse(file_name) root = tree.getroot()[0] # Create dic of : id -> text features pub_dic = {} for pub in root: rec_number = int (get_text (pub.find('rec-number'))) abstract = get_text (pub.find('abstract')) title = get_text (pub.find('titles')[0]) text = title + abstract for kw in pub.find('keywords'): text = text + kw.text + ' ' pub_dic[rec_number] = text return pub_dic
def youtube_channel(channel_id): import xml.etree.ElementTree as ET import urllib.request import datetime url = "https://www.youtube.com/feeds/videos.xml?max-results=50&channel_id=" + channel_id videos = [] with urllib.request.urlopen(url) as f: root = ET.parse(f).getroot() for entry in root.iter('{http://www.w3.org/2005/Atom}entry'): video = {} video['id'] = entry.find('{http://www.youtube.com/xml/schemas/2015}videoId').text video['date'] = datetime.datetime.strptime(entry.find('{http://www.w3.org/2005/Atom}published').text, '%Y-%m-%dT%H:%M:%S+00:00') video['title'] = entry.find('{http://www.w3.org/2005/Atom}title').text videos.append(video) return videos
def parse_file(self): if self.path.endswith("gz"): f = gzip.GzipFile(self.path) else: f = open(self.path) tree = ET.parse(f) f.close() root = tree.getroot() current_urbs = {} for child in root: p = USBPacket(child) urb_id = p["usb.urb_id"] urb_status = p["usb.urb_status"] urb_type = p["usb.urb_type"] if (urb_type == URB_TYPE_SUBMIT): current_urbs[urb_id] = p if (urb_type == URB_TYPE_COMPLETED): if (urb_id not in current_urbs): print("Urb id not present: {:x}".format(urb_id)) else: submit = current_urbs[urb_id] completed = p self.usb_transaction(submit, completed) del current_urbs[urb_id]
def parse_voc_rec(filename): """ parse pascal voc record into a dictionary :param filename: xml file path :return: list of dict """ import xml.etree.ElementTree as ET tree = ET.parse(filename) objects = [] for obj in tree.findall('object'): obj_dict = dict() obj_dict['name'] = obj.find('name').text obj_dict['difficult'] = int(obj.find('difficult').text) bbox = obj.find('bndbox') obj_dict['bbox'] = [int(bbox.find('xmin').text), int(bbox.find('ymin').text), int(bbox.find('xmax').text), int(bbox.find('ymax').text)] objects.append(obj_dict) return objects
def parseXML(self): assert self.filepath.endswith(XML_EXT), "Unsupport file format" parser = etree.XMLParser(encoding=ENCODE_METHOD) xmltree = ElementTree.parse(self.filepath, parser=parser).getroot() filename = xmltree.find('filename').text try: verified = xmltree.attrib['verified'] if verified == 'yes': self.verified = True except KeyError: self.verified = False for object_iter in xmltree.findall('object'): bndbox = object_iter.find("bndbox") label = object_iter.find('name').text # Add chris difficult = False if object_iter.find('difficult') is not None: difficult = bool(int(object_iter.find('difficult').text)) self.addShape(label, bndbox, difficult) return True
def parse_rec(filename): """ Parse a PASCAL VOC xml file """ tree = ET.parse(filename) objects = [] for obj in tree.findall('object'): obj_struct = {} obj_struct['name'] = obj.find('name').text obj_struct['pose'] = obj.find('pose').text obj_struct['truncated'] = int(obj.find('truncated').text) obj_struct['difficult'] = int(obj.find('difficult').text) bbox = obj.find('bndbox') obj_struct['bbox'] = [int(bbox.find('xmin').text) - 1, int(bbox.find('ymin').text) - 1, int(bbox.find('xmax').text) - 1, int(bbox.find('ymax').text) - 1] objects.append(obj_struct) return objects
def pull_anno(self, index): '''Returns the original annotation of image at index Note: not using self.__getitem__(), as any transformations passed in could mess up this functionality. Argument: index (int): index of img to get annotation of Return: list: [img_id, [(label, bbox coords),...]] eg: ('001718', [('dog', (96, 13, 438, 332))]) ''' img_id = self.ids[index] anno = ET.parse(self._annopath % img_id).getroot() gt = self.target_transform(anno, 1, 1) return img_id[1], gt
def clean(path): for f_xml in glob.iglob(os.path.join(path, '*.xml')): print(f_xml) f_txt = os.path.splitext(f_xml)[0] with io.open(f_txt, mode='w', encoding='utf-8') as fd_txt: root = ET.parse(f_xml).getroot()[0] for doc in root.findall('doc'): for e in doc.findall('seg'): fd_txt.write(e.text.strip() + '\n') xml_tags = ['<url', '<keywords', '<talkid', '<description', '<reviewer', '<translator', '<title', '<speaker'] for f_orig in glob.iglob(os.path.join(path, 'train.tags*')): print(f_orig) f_txt = f_orig.replace('.tags', '') with io.open(f_txt, mode='w', encoding='utf-8') as fd_txt, \ io.open(f_orig, mode='r', encoding='utf-8') as fd_orig: for l in fd_orig: if not any(tag in l for tag in xml_tags): fd_txt.write(l.strip() + '\n')
def test_to_dict_from_etree(self): vh_xml_tree = _ElementTree.parse('examples/vehicles/vehicles.xml') col_xml_tree = _ElementTree.parse('examples/collection/collection.xml') xml_dict = self.vh_schema.to_dict(vh_xml_tree) self.assertNotEqual(xml_dict, _VEHICLES_DICT) # XSI namespace unmapped xml_dict = self.vh_schema.to_dict(vh_xml_tree, namespaces=self.namespaces) self.assertEqual(xml_dict, _VEHICLES_DICT) xml_dict = xmlschema.to_dict(vh_xml_tree, self.vh_schema.url, namespaces=self.namespaces) self.assertEqual(xml_dict, _VEHICLES_DICT) xml_dict = self.col_schema.to_dict(col_xml_tree) self.assertNotEqual(xml_dict, _COLLECTION_DICT) xml_dict = self.col_schema.to_dict(col_xml_tree, namespaces=self.namespaces) self.assertEqual(xml_dict, _COLLECTION_DICT) xml_dict = xmlschema.to_dict(col_xml_tree, self.col_schema.url, namespaces=self.namespaces) self.assertEqual(xml_dict, _COLLECTION_DICT)
def _parse_annotation_xml(filepath): tree = et.parse(filepath) data = tree.getroot()[1] # <data> for sf in data: # <sourcefile> ... find first non-empty sourcefile node if len(list(sf)) != 0: break file = sf[0] # <file> objs = sf[1:] # <object> ... num_objs = len(objs) num_frames = int(file.find("./*[@name='NUMFRAMES']/*[@value]").attrib['value']) parsed_bbx = np.zeros([num_frames, num_objs, 4]) for i, obj in enumerate(objs): # iterate <object> nodes loc = obj.find("./*[@name='Location']") for bbx in loc: span = re.findall(r'\d+', bbx.attrib['framespan']) beg, end = int(span[0]), int(span[1]) h = int(bbx.attrib['height']) w = int(bbx.attrib['width']) x = int(bbx.attrib['x']) y = int(bbx.attrib['y']) parsed_bbx[beg-1:end, i] = [h, w, x, y] return parsed_bbx
def translate_to_text(results_file, text_file): f = open(text_file, 'w') import xml.etree.ElementTree as ET et = ET.parse (results_file) for test in et.findall('Test'): node_to_text (test, f) for example in et.findall('Example'): result = example.find('Result').text name = example.find('Name').text if not example.find('Time') is None: time_real = example.find('Time').get('real') else: time_real = '' output = "%s: Example \"%s\" (%s)\n" % (result, name, time_real) f.write(output) f.close() # # A simple example of writing an HTML file with a test result summary. It is # expected that this will eventually be made prettier as time progresses and # we have time to tweak it. This may end up being moved to a separate module # since it will probably grow over time. #
def _le_xml(self, arquivo): if arquivo is None: return False if not isinstance(arquivo, basestring): arquivo = etree.tounicode(arquivo) if arquivo is not None: if isinstance(arquivo, basestring): if NAMESPACE_NFSE in arquivo: arquivo = por_acentos(arquivo) if u'<' in arquivo: self._xml = etree.fromstring(tira_abertura(arquivo)) else: arq = open(arquivo) txt = ''.join(arq.readlines()) txt = tira_abertura(txt) arq.close() self._xml = etree.fromstring(txt) else: self._xml = etree.parse(arquivo) return True return False
def validar(self): arquivo_esquema = self.caminho_esquema + self.arquivo_esquema # Aqui é importante remover a declaração do encoding # para evitar erros de conversão unicode para ascii xml = tira_abertura(self.xml).encode(u'utf-8') esquema = etree.XMLSchema(etree.parse(arquivo_esquema)) if not esquema.validate(etree.fromstring(xml)): for e in esquema.error_log: if e.level == 1: self.alertas.append(e.message.replace('{http://www.portalfiscal.inf.br/nfe}', '')) elif e.level == 2: self.erros.append(e.message.replace('{http://www.portalfiscal.inf.br/nfe}', '')) return esquema.error_log
def xml_start(xml): 'Stores $xml file in $dicc dictionary' def xml_parse(root, dicc, way=""): new_way = way + "/" + root.tag value = [] try: value = dicc[new_way] except: value = [] value.append(root.text) dicc.__setitem__(new_way, value) for new_root in root._children: xml_parse(new_root, dicc, new_way) tree = ET.parse(xml, parser=None) root = tree.getroot() dicc = {} xml_parse(root, dicc, way="") return dicc
def getByID(id): try: en_tree = ET.parse('lib/lang/en.xml') de_tree = ET.parse('lib/lang/de.xml') except FileNotFoundError: print(BOLD + RED + "ERROR: Didn't find en.xml or de.xml in lib/lang/\n" + " Please clone this project again from GitHub!" + ENDC) sys.exit(0) string = '''.//*[@id='%ID%']''' string = str(string).replace("%ID%", id) if language.__contains__("de"): return de_tree.findall(string)[0].text else: return en_tree.findall(string)[0].text
def append_result_files(self, dst_resultfile, kw_resultfile_list, dst_root='Testcase', childtag='Keyword'): """Append kw/system result files into a testcase result file""" try: finstring = '' for kw_file in kw_resultfile_list: if kw_file is not None and kw_file is not False: tree = self.xml_utils().get_tree_from_file(kw_file) self.root = tree.getroot() for child in self.root: if child.tag == childtag: finstring = finstring+self.xml_utils().convert_element_to_string(child) tc_string = ' ' if self.file_utils().fileExists(dst_resultfile): tc_tree = ET.parse(dst_resultfile) tc_root = tc_tree.getroot() for tc_child in tc_root: tc_string = tc_string+self.xml_utils().convert_element_to_string(tc_child) finalresult = '\n'.join(['<{0}>'.format(dst_root), tc_string + finstring, '</{0}>'.format(dst_root)]) with open(dst_resultfile, 'w') as resultfile: resultfile.write(finalresult) resultfile.flush() resultfile.close() except Exception, err: print_info('unexpected error: {0}'.format(str(err)))
def parse_tree(self, node): """ Method to parse ElementTree to ConfigurationElement Tree :param node: :return: """ for key in node.attrib: self.attributes[key] = node.attrib[key] self.attributes['xml_tag'] = node.tag # self.attributes['xml_element'] = node for child in node: try: if not child.attrib['name'] in self.children: child_config = ConfigurationElement(child.attrib['name']) child_config.parse_data(child, root=False) self.children[child.attrib['name']] = child_config else: self.children[child.attrib['name']].parse_tree(child) except KeyError: print_error("No name attribute for node " + child.tag + ". Tree with root " "at node " + child.tag + " not parsed.")
def evaluate_argument_value(xpath_or_tagname, datafile): """This function takes checks if the given xpath_or_tagname exists in the datafile and returns its value. Else returns None.""" tree = ET.parse(datafile) root = tree.getroot() if xpath_or_tagname.startswith(root.tag + "/"): xpath_or_tagname = xpath_or_tagname[len(root.tag + "/"):] try: xpath_or_tagname = root.find(xpath_or_tagname).text except Exception: print_error("Invalid xpath: {0}".format(root.tag + "/" + xpath_or_tagname)) xpath_or_tagname = None else: print_error("Invalid xpath: {0}".format(xpath_or_tagname)) xpath_or_tagname = None return xpath_or_tagname
def getChildTextbyParentAttribute (datafile, pnode, patt, pattval, cnode): """ Seraches XML file for the parent node with a specific value. Finds the child node and returns its text datafile = xml file searched pnode = parent node patt = parent node attribute patval = parent node attribute value cnode = child node """ tree = ElementTree.parse(datafile) root = tree.getroot() value = False for node in root.findall(pnode): attribute = node.get(patt) if attribute == pattval: cnode = node.find(cnode) if cnode is not None: value = cnode.text else: return None break return value
def getChildTextbyParentTag (datafile, pnode, cnode): """ Seraches XML file for the first parent. Finds the child node and returns its text datafile = xml file searched pnode = parent node cnode = child node """ value = False tree = ElementTree.parse(datafile) root = tree.getroot() node = root.find(pnode) if node is not None: child = node.find(cnode) if child is not None: value = child.text return value else: # print_info("could not find cnode under the given pnode") return value else: # print_info("could not find pnode in the provided file") return value
def getChildAttributebyParentTag (datafile, pnode, cnode, cattrib): """Find the attribute in child node by traversing through the parent node in the given file datafile = xml file searched pnode = parent node cnode = child node cattrob = child node attrib """ tree = ElementTree.parse(datafile) root = tree.getroot() node = root.find(pnode) if node is not None: child = node.find(cnode) if child is not None: value = child.get(cattrib) return value else: # print_info("could not find cnode under the given pnode") return False else: # print_info("could not find pnode in the provided file") return False
def verifyParentandChildrenMatch (datafile, pnode, cnode, cvalue, rnode, rvalue): """ Searches XML file for the parent node. Finds the 1st child node and checks its value if value is a match, then search for second child and check if its value matches datafile = xml file searched pnode = parent node cnode = child node cvalue = child node value rnode = reference node rvalue = refernce node value """ tree = ElementTree.parse(datafile) root = tree.getroot() status = False for node in root.findall(pnode): value = node.find(cnode).text if value == cvalue: if node.find(rnode) is not None: cnodev = node.find(rnode).text # print_debug("-D- cnodev: '%s', rvalue : '%s'" % (cnodev, rvalue)) if cnodev == rvalue: # print_debug("-D- BREAK END METHOD verifyParentandChildrenMatch_Status '%s'" % status) return True return status
def getElementsListWithTagAttribValueMatch(datafile, tag, attrib, value): """ This method takes an xml document as input and finds all the sub elements (parent/children) containing specified tag and an attribute with the specified value. Returns a list of matching elements. Arguments: datafile = input xml file to be parsed. tag = tag value of the sub-element(parent/child) to be searched for. attrib = attribute name for the sub-element with above given tag should have. value = attribute value that the sub-element with above given tag, attribute should have. """ element_list = [] root = ElementTree.parse(datafile).getroot() for element in root.iterfind(".//%s[@%s='%s']" % (tag, attrib, value)): element_list.append(element) return element_list
def getElementWithTagAttribValueMatch(start, tag, attrib, value): """ When start is an xml datafile, it finds the root and first element with: tag, attrib, value. Or when it's an xml element, it finds the first child element with: tag, attrib, value. If there is not a match, it returns False. """ node = False if isinstance(start, (file, str)): # check if file exist here if file_Utils.fileExists(start): node = ElementTree.parse(start).getroot() else: print_warning('The file={0} is not found.'.format(start)) elif isinstance(start, ElementTree.Element): node = start if node is not False and node is not None: elementName = ".//%s[@%s='%s']" % (tag, attrib, value) element = node.find(elementName) else: element = node return element
def getConfigElementTextWithSpecificXpath(datafile, xpath): """ This method takes an xml document as input and finds the first sub element (parent/children) containing specified xpath which should be a filepath to a netconf config file Returns the element text attribute Arguments: parent = parent element xpath = a valid xml path value as supported by python, refer https://docs.python.org/2/library/xml.etree.elementtree.html """ root = ElementTree.parse(datafile).getroot() elem1 = root.find(xpath).text elem2_root = ElementTree.parse(elem1) elem2 = elem2_root.find('config') elem2_string = ElementTree.tostring(elem2) return elem2_string
def getChildElementWithSpecificXpath(start, xpath): """ This method takes a xml file or parent element as input and finds the first child containing specified xpath Returns the child element. Arguments: start = xml file or parent element xpath = a valid xml path value as supported by python, refer https://docs.python.org/2/library/xml.etree.elementtree.html """ node = False if isinstance(start, (file, str)): # check if file exist here if file_Utils.fileExists(start): node = ElementTree.parse(start).getroot() else: print_warning('The file={0} is not found.'.format(start)) elif isinstance(start, ElementTree.Element): node = start if node is not False or node is not None: element = node.find(xpath) else: element = False return element
def del_tags_from_xml(xml, tag_list=[]): """ It deletes the tags either by their names or xpath Arguments: 1.xml: It takes xml file path or xml string as input 2.tag_list: It contains list of tags which needs to be removed Returns: It returns xml string """ if os.path.exists(xml): tree = ElementTree.parse(xml) root = tree.getroot() else: root = ElementTree.fromstring(xml) for tag in tag_list: if 'xpath=' in tag: tag = tag.strip('xpath=') req_tags = getChildElementsListWithSpecificXpath(root, tag) else: req_tags = getChildElementsListWithSpecificXpath(root, ".//{0}".format(tag)) recursive_delete_among_children(root, req_tags) xml_string = ElementTree.tostring(root, encoding='utf-8', method='xml') return xml_string
def convert_xml_to_list_of_dict(file_name): """ Takes xml file path as input and converts to list of dictionaries Arguments: file_name : It takes xml file path as input Returns: list_of_dict: list of dictionaries where keys are tag names and values are respective text of the tag. """ tree = ElementTree.parse(file_name) root = tree.getroot() list_of_dict = [] for child in root: subchild_dict = OrderedDict() for subchild in child: subchild_dict[subchild.tag] = subchild.text list_of_dict.append(subchild_dict) return list_of_dict #2016/06/22 ymizugaki add begin
def get_node(filename, node_name): """ Searches for the specified node in the xml tree. return type: xml.etree.ElementTree.Element :Arguments: 1. node_name (str) = Name of the node to be searched 2. filename (str) = path of the .xml that has to be searched. :Returns: node = xml.etree.ElementTree.Element/boolean False """ root = ElementTree.parse(filename).getroot() node = root.find(node_name) if node is not None: return node else: return False
