10 examples of 'how to extract data from xml file using python' in Python

81
def test_xml_extraction(self):
82
    xml = '''
83
    
84
    
85
        <ul>
86
            <li>a</li>
87
            b
88
        </ul>
89
    
90
    '''
91
92
    namespaces = {'a': 'http://test.com/', 'b': 'http://www.w3.org/2001/XMLSchema-instance'}
93
    # xpath
94
    self.assertEqual(len(MockParser(xpath='//a:ul', namespaces=namespaces).parse(xml)), 1)
95
    self.assertEqual(len(MockParser(xpath='a:ul', namespaces=namespaces).parse(xml)), 1)
96
    self.assertEqual(len(MockParser(xpath='/a:ul', namespaces=namespaces).parse(xml)), 0)
97
98
    self.assertEqual(len(MockParser(xpath='//a:li', namespaces=namespaces).parse(xml)), 1)
99
    self.assertEqual(len(MockParser(xpath='a:li', namespaces=namespaces).parse(xml)), 0)
100
    self.assertEqual(len(MockParser(xpath='/a:li', namespaces=namespaces).parse(xml)), 0)
101
102
    self.assertEqual(len(MockParser(xpath='//b:li', namespaces=namespaces).parse(xml)), 1)
103
    self.assertEqual(len(MockParser(xpath='b:li', namespaces=namespaces).parse(xml)), 0)
104
    self.assertEqual(len(MockParser(xpath='/b:li', namespaces=namespaces).parse(xml)), 0)

17
def readXml(input_file):
18
	with open(input_file,"rb") as f:
19
		xmlr = XmlUnpacker()
20
		return xmlr.read(f)

28
def parseXML(xmlFile):
29
    """
30
    Parse the xml
31
    """
32
    f = open(xmlFile)
33
    xml = f.read()
34
    f.close()
35
36
    tree = etl.parse(StringIO(xml))
37
    context = etl.iterparse(StringIO(xml))
38
    for action, elem in context:
39
        if not elem.text:
40
            text = "None"
41
        else:
42
            text = elem.text
43
        print elem.tag + " => " + text

6
def parse(filename='example.html'):
7
  xml=loadpage(filename)
8
  cells=getcells(xml)
9
  row=makerow(cells)
10
  print row

19
def parse_xml(content, transport, base_url=None):
20
    parser = etree.XMLParser(remove_comments=True, resolve_entities=False)
21
    parser.resolvers.add(ImportResolver(transport))
22
    try:
23
        return fromstring(content, parser=parser, base_url=base_url)
24
    except etree.XMLSyntaxError as exc:
25
        raise XMLSyntaxError("Invalid XML content received (%s)" % exc.message)

284
def parseEtree(inFileName):
285
    doc = parsexml_(inFileName)
286
    rootNode = doc.getroot()
287
    rootTag, rootClass = get_root_tag(rootNode)
288
    if rootClass is None:
289
        rootTag = 'Device'
290
        rootClass = DeviceObjectType
291
    rootObj = rootClass.factory()
292
    rootObj.build(rootNode)
293
    # Enable Python to collect the space used by the DOM.
294
    doc = None
295
    rootElement = rootObj.to_etree(None, name_=rootTag)
296
    content = etree_.tostring(rootElement, pretty_print=True,
297
        xml_declaration=True, encoding="utf-8")
298
    sys.stdout.write(content)
299
    sys.stdout.write('\n')
300
    return rootObj, rootElement

406
def parseEtree(inFileName):
407
    doc = parsexml_(inFileName)
408
    rootNode = doc.getroot()
409
    rootTag, rootClass = get_root_tag(rootNode)
410
    if rootClass is None:
411
        rootTag = 'Network_Route_Object'
412
        rootClass = NetRouteObjectType
413
    rootObj = rootClass.factory()
414
    rootObj.build(rootNode)
415
    # Enable Python to collect the space used by the DOM.
416
    doc = None
417
    rootElement = rootObj.to_etree(None, name_=rootTag)
418
    content = etree_.tostring(rootElement, pretty_print=True,
419
        xml_declaration=True, encoding="utf-8")
420
    sys.stdout.write(content)
421
    sys.stdout.write('\n')
422
    return rootObj, rootElement

385
def parseEtree(inFileName):
386
    doc = parsexml_(inFileName)
387
    rootNode = doc.getroot()
388
    rootTag, rootClass = get_root_tag(rootNode)
389
    if rootClass is None:
390
        rootTag = 'Windows_Network_Route_Entry'
391
        rootClass = WindowsNetworkRouteEntryObjectType
392
    rootObj = rootClass.factory()
393
    rootObj.build(rootNode)
394
    # Enable Python to collect the space used by the DOM.
395
    doc = None
396
    rootElement = rootObj.to_etree(None, name_=rootTag)
397
    content = etree_.tostring(rootElement, pretty_print=True,
398
        xml_declaration=True, encoding="utf-8")
399
    sys.stdout.write(content)
400
    sys.stdout.write('\n')
401
    return rootObj, rootElement

267
def parseEtree(inFileName):
268
    doc = parsexml_(inFileName)
269
    rootNode = doc.getroot()
270
    rootTag, rootClass = get_root_tag(rootNode)
271
    if rootClass is None:
272
        rootTag = 'Unix_Network_Route_Entry'
273
        rootClass = UnixNetworkRouteEntryObjectType
274
    rootObj = rootClass.factory()
275
    rootObj.build(rootNode)
276
    # Enable Python to collect the space used by the DOM.
277
    doc = None
278
    rootElement = rootObj.to_etree(None, name_=rootTag)
279
    content = etree_.tostring(rootElement, pretty_print=True,
280
        xml_declaration=True, encoding="utf-8")
281
    sys.stdout.write(content)
282
    sys.stdout.write('\n')
283
    return rootObj, rootElement

295
def parseEtree(inFileName):
296
    doc = parsexml_(inFileName)
297
    rootNode = doc.getroot()
298
    rootTag, rootClass = get_root_tag(rootNode)
299
    if rootClass is None:
300
        rootTag = 'Port'
301
        rootClass = PortObjectType
302
    rootObj = rootClass.factory()
303
    rootObj.build(rootNode)
304
    # Enable Python to collect the space used by the DOM.
305
    doc = None
306
    rootElement = rootObj.to_etree(None, name_=rootTag)
307
    content = etree_.tostring(rootElement, pretty_print=True,
308
        xml_declaration=True, encoding="utf-8")
309
    sys.stdout.write(content)
310
    sys.stdout.write('\n')
311
    return rootObj, rootElement