Python XML.findall方法代码示例

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import findall [as 别名]
def mtgx2json(graph):
    zipfile = ZipFile(graph)
    graphs = filter(lambda x: x.endswith(".graphml"), zipfile.namelist())
    for f in graphs:
        multikeys = []
        xml = XML(zipfile.open(f).read())
        links = {}
        for edge in xml.findall(
            "{http://graphml.graphdrawing.org/xmlns}graph/" "{http://graphml.graphdrawing.org/xmlns}edge"
        ):
            src = edge.get("source")
            dst = edge.get("target")
            if src not in links:
                links[src] = dict(in_=[], out=[])
            if dst not in links:
                links[dst] = dict(in_=[], out=[])
            links[src]["out"].append(dst)
            links[dst]["in_"].append(src)

        for node in xml.findall(
            "{http://graphml.graphdrawing.org/xmlns}graph/" "{http://graphml.graphdrawing.org/xmlns}node"
        ):

            node_id = node.get("id")
            node = node.find(
                "{http://graphml.graphdrawing.org/xmlns}data/" "{http://maltego.paterva.com/xml/mtgx}MaltegoEntity"
            )

            record = OrderedDict({"NodeID": node_id, "EntityType": node.get("type").strip()})
            props = {"Data": {}}
            for prop in node.findall(
                "{http://maltego.paterva.com/xml/mtgx}Properties/" "{http://maltego.paterva.com/xml/mtgx}Property"
            ):
                value = prop.find("{http://maltego.paterva.com/xml/mtgx}Value").text or ""
                entity_prop = {prop.get("displayName"): value.strip()}
                props["Data"].update(entity_prop)
            record.update(props)
            s = " - ".join(["%s: %s" % (key, value) for (key, value) in record["Data"].items()])
            record.pop("Data")
            data = {"Data": s}
            record.update(data)
            link = {"Links": {}}
            i_link = {"Incoming": links.get(node_id, {}).get("in_", 0)}
            link["Links"].update(i_link)
            o_link = {"Outgoing": links.get(node_id, {}).get("out", 0)}
            link["Links"].update(o_link)
            record.update(link)
            multikeys.append(record)
        return multikeys

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import findall [as 别名]
def mtgx2csv(opts):

    zipfile = ZipFile(opts.graph)
    graphs = filter(lambda x: x.endswith(".graphml"), zipfile.namelist())

    for f in graphs:
        filename = "%s_%s" % (opts.graph.replace(".", "_", 1), os.path.basename(f).replace(".graphml", ".csv", 1))
        print "Writing data from %s/%s to %s..." % (opts.graph, f, filename)
        with open(filename, "wb") as csvfile:
            csv = writer(csvfile)
            xml = XML(zipfile.open(f).read())
            links = {}
            for edge in xml.findall(
                "{http://graphml.graphdrawing.org/xmlns}graph/" "{http://graphml.graphdrawing.org/xmlns}edge"
            ):
                src = edge.get("source")
                dst = edge.get("target")
                if src not in links:
                    links[src] = dict(in_=0, out=0)
                if dst not in links:
                    links[dst] = dict(in_=0, out=0)
                links[src]["out"] += 1
                links[dst]["in_"] += 1

            for node in xml.findall(
                "{http://graphml.graphdrawing.org/xmlns}graph/" "{http://graphml.graphdrawing.org/xmlns}node"
            ):

                node_id = node.get("id")
                node = node.find(
                    "{http://graphml.graphdrawing.org/xmlns}data/" "{http://maltego.paterva.com/xml/mtgx}MaltegoEntity"
                )

                row = [to_utf8(("Entity Type=%s" % node.get("type")).strip())]
                for prop in node.findall(
                    "{http://maltego.paterva.com/xml/mtgx}Properties/" "{http://maltego.paterva.com/xml/mtgx}Property"
                ):
                    value = prop.find("{http://maltego.paterva.com/xml/mtgx}Value").text or ""
                    row.append(to_utf8(("%s=%s" % (prop.get("displayName"), value)).strip()))
                row.append("Incoming Links=%s" % links.get(node_id, {}).get("in_", 0))
                row.append("Outgoing Links=%s" % links.get(node_id, {}).get("out", 0))
                csv.writerow(row)

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import findall [as 别名]
 def listChildrenViaPropfind():
     data = yield self.simpleSend(
         "PROPFIND", "/", resultcode=responsecode.MULTI_STATUS,
         headers=[('Depth', '1')]
     )
     tree = XML(data)
     seq = [e.text for e in tree.findall("{DAV:}response/{DAV:}href")]
     shortest = min(seq, key=len)
     seq.remove(shortest)
     filtered = [elem[len(shortest):].rstrip("/") for elem in seq]
     returnValue(filtered)

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import findall [as 别名]
def parse_highlights(xml):

	soup = XML(xml)

	highlightList = []

	for series in soup.findall('series'):
		tempSeries = dict(series.items())
		tempSeries.update(xml_text_elements(series))
		highlightList.append(tempSeries)

	return highlightList

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import findall [as 别名]
        def listChildrenViaPropfind():
            request = SimpleStoreRequest(self, "PROPFIND", "/calendars/__uids__/user01/", authid="user01")
            request.headers.setHeader("depth", "1")
            response = yield self.send(request)
            response = IResponse(response)
            data = yield allDataFromStream(response.stream)

            tree = XML(data)
            seq = [e.text for e in tree.findall("{DAV:}response/{DAV:}href")]
            shortest = min(seq, key=len)
            seq.remove(shortest)
            filtered = [elem[len(shortest):].rstrip("/") for elem in seq]
            returnValue(filtered)

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import findall [as 别名]
def mtgx2csv(opts):

    zipfile = ZipFile(opts.graph)
    graphs = filter(lambda x: x.endswith('.graphml'), zipfile.namelist())

    for f in graphs:
        filename = '%s_%s' % (opts.graph.replace('.', '_', 1), os.path.basename(f).replace('.graphml', '.csv', 1))
        print 'Writing data from %s/%s to %s...' % (opts.graph, f, filename)
        with open(filename, 'wb') as csvfile:
            csv = writer(csvfile)
            xml = XML(zipfile.open(f).read())
            links = {}
            for edge in xml.findall('{http://graphml.graphdrawing.org/xmlns}graph/'
                                    '{http://graphml.graphdrawing.org/xmlns}edge'):
                src = edge.get('source')
                dst = edge.get('target')
                if src not in links:
                    links[src] = dict(in_=0, out=0)
                if dst not in links:
                    links[dst] = dict(in_=0, out=0)
                links[src]['out'] += 1
                links[dst]['in_'] += 1

            for node in xml.findall('{http://graphml.graphdrawing.org/xmlns}graph/'
                                    '{http://graphml.graphdrawing.org/xmlns}node'):

                node_id = node.get('id')
                node = node.find('{http://graphml.graphdrawing.org/xmlns}data/'
                                 '{http://maltego.paterva.com/xml/mtgx}MaltegoEntity')

                row = [to_utf8(('Entity Type=%s' % node.get('type')).strip())]
                for prop in node.findall('{http://maltego.paterva.com/xml/mtgx}Properties/'
                                         '{http://maltego.paterva.com/xml/mtgx}Property'):
                    value = prop.find('{http://maltego.paterva.com/xml/mtgx}Value').text or ''
                    row.append(to_utf8(('%s=%s' % (prop.get('displayName'), value)).strip()))
                row.append('Incoming Links=%s' % links.get(node_id, {}).get('in_', 0))
                row.append('Outgoing Links=%s' % links.get(node_id, {}).get('out', 0))
                csv.writerow(row)

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import findall [as 别名]
def run(args):
    opts = parse_args(args)

    zipfile = ZipFile(opts.graph)
    graphs = filter(lambda x: x.endswith('.graphml'), zipfile.namelist())

    for f in graphs:
        with open(f.split('/')[1].split('.')[0] + '.csv', 'wb') as csvfile:
            csv = writer(csvfile)
            xml = XML(zipfile.open(f).read())
            links = {}
            for edge in xml.findall('{http://graphml.graphdrawing.org/xmlns}graph/'
                                    '{http://graphml.graphdrawing.org/xmlns}edge'):
                src = edge.get('source')
                dst = edge.get('target')
                if src not in links:
                    links[src] = dict(in_=0, out=0)
                if dst not in links:
                    links[dst] = dict(in_=0, out=0)
                links[src]['out'] += 1
                links[dst]['in_'] += 1

            for node in xml.findall('{http://graphml.graphdrawing.org/xmlns}graph/'
                                    '{http://graphml.graphdrawing.org/xmlns}node'):

                node_id = node.get('id')
                node = node.find('{http://graphml.graphdrawing.org/xmlns}data/'
                                 '{http://maltego.paterva.com/xml/mtgx}MaltegoEntity')

                row = [to_utf8(('Entity Type=%s' % node.get('type')).strip())]
                for prop in node.findall('{http://maltego.paterva.com/xml/mtgx}Properties/'
                                         '{http://maltego.paterva.com/xml/mtgx}Property'):
                    value = prop.find('{http://maltego.paterva.com/xml/mtgx}Value').text or ''
                    row.append(to_utf8(('%s=%s' % (prop.get('displayName'), value)).strip()))
                row.append('Incoming Links=%s' % links[node_id]['in_'])
                row.append('Outgoing Links=%s' % links[node_id]['out'])
                csv.writerow(row)

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import findall [as 别名]
def run(args):

    opts = parse_args(args)

    zip = ZipFile(opts.graph)
    graphs = filter(lambda x: x.endswith('.graphml'), zip.namelist())

    for f in graphs:
        csv = open(f.split('/')[1].split('.')[0] + '.csv', 'w')
        xml = XML(zip.open(f).read())
        for e in xml.findall('{http://graphml.graphdrawing.org/xmlns}graph/{http://graphml.graphdrawing.org/xmlns}node/{http://graphml.graphdrawing.org/xmlns}data/{http://maltego.paterva.com/xml/mtgx}MaltegoEntity'):
            csv.write(('"Entity Type=%s",' % e.get('type')).strip())
            for prop in e.findall('{http://maltego.paterva.com/xml/mtgx}Properties/{http://maltego.paterva.com/xml/mtgx}Property'):
                value = prop.find('{http://maltego.paterva.com/xml/mtgx}Value').text or ''
                if '"' in value:
                    value.replace('"', '""')
                csv.write(('"%s=%s",' % (prop.get('displayName'), value)).strip())
            csv.write('\n')

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import findall [as 别名]
def run(args):
    opts = parse_args(args)

    if path.exists(opts.outfile) and not opts.append and not \
        parse_bool('%s already exists. Are you sure you want to overwrite it? [y/N]: ' % repr(opts.outfile),
                   default='n'):
        exit(-1)

    entity_source = None
    if opts.mtz_file is None:
        d = detect_settings_dir()
        if maltego_version(d) >= '3.4.0':
            print("""
=========================== ERROR: NOT SUPPORTED ===========================

 Starting from Maltego v3.4.0 the 'canari generate-entities' command can no
 longer generate entity definition files from the Maltego configuration
 directory. Entities can only be generated from export files (*.mtz). To
 export entities navigate to the 'Manage' tab in Maltego, then click on the
 'Export Entities' button and follow the prompts. Once the entities have
 been exported, run the following command:

 shell> canari generate-entities -m myentities.mtz

=========================== ERROR: NOT SUPPORTED ===========================
                """)
            exit(-1)
        entity_source = DirFile(
            path.join(d, 'config', 'Maltego', 'Entities')
        )
    else:
        entity_source = ZipFile(opts.mtz_file)

    entity_files = filter(lambda x: x.endswith('.entity'), entity_source.namelist())

    namespaces = dict()

    excluded_entities = []
    if opts.append:
        existing_entities = get_existing_entities(opts.outfile)
        # excluded_entities.extend([e._type_ for e in existing_entities])
        for entity_class in existing_entities:
            excluded_entities.extend(entity_class._type_)
            if entity_class._type_.endswith('Entity'):
                namespaces[entity_class._namespace_] = entity_class.__name__

    print 'Generating %s...' % repr(opts.outfile)
    outfile = open(opts.outfile, 'ab' if opts.append else 'wb')

    if opts.append:
        outfile.write('\n\n')
    else:
        outfile.write('#!/usr/bin/env python\n\nfrom canari.maltego.entities import EntityField, Entity\n\n\n')

    for entity_file in entity_files:
        xml = XML(entity_source.open(entity_file).read())
        id_ = xml.get('id')

        if (opts.entity and id_ not in opts.entity) or id_ in excluded_entities:
            continue

        namespace_entity = id_.split('.')

        base_classname = None
        namespace = '.'.join(namespace_entity[:-1])
        name = namespace_entity[-1]
        classname = name

        if (opts.namespace and namespace not in opts.namespace) or namespace in opts.exclude_namespace:
            continue

        if namespace not in namespaces:
            base_classname = '%sEntity' % (''.join([n.title() for n in namespace_entity[:-1]]))
            namespaces[namespace] = base_classname

            outfile.write('class %s(Entity):\n    _namespace_ = %s\n\n' % (base_classname, repr(namespace)))
        else:
            base_classname = namespaces[namespace]

        for field in xml.findall('Properties/Fields/Field'):
            fields = [
                'name=%s' % repr(field.get('name')),
                'propname=%s' % repr(normalize_fn(field.get('name'))),
                'displayname=%s' % repr(field.get('displayName'))

            ]
            outfile.write('@EntityField(%s)\n' % ', '.join(fields))

        outfile.write('class %s(%s):\n    pass\n\n\n' % (classname, base_classname))

    outfile.close()
    print 'done.'

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import findall [as 别名]
 
for e in entities:
    xml = XML(zip.open(e).read())
    id_ = xml.get('id')
 
    ens = id_.split('.')
 
    base_classname = None
    namespace = '.'.join(ens[:-1])
    name = ens[-1]
    classname = name
 
    if namespace not in nses:
        base_classname = '%sEntity' % (''.join([ n.title() for n in ens[:-1] ]))
        nses[namespace] = base_classname
 
        print 'class %s(Entity):\n    namespace = %s\n\n' % (base_classname, repr(namespace))
    else:
        base_classname = nses[namespace]
 
 
    for f in xml.findall('Properties/Fields/Field'):
        fields = [
            'name=%s' % repr(f.get('name')),
            'propname=%s' % repr(normalize_fn(f.get('name'))),
            'displayname=%s' % repr(f.get('displayName'))
 
        ]
        print '@EntityField(%s)' % ', '.join(fields)
 
    print 'class %s(%s):\n    pass\n\n' % (classname, base_classname)

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import findall [as 别名]
class NmapReportParser(object):

    def __init__(self, output):
        self.output = output
        self.xml = XML(output)

    def os(self, address):
        host = self._host(address)
        if host is not None:
            r = {
                'osmatch': [osm.attrib for osm in host.findall('os/osmatch')],
                'osclass': [osm.attrib for osm in host.findall('os/osclass')],
                'portused': host.find('os/portused').attrib
            }
            return r
        return { 'osmatch' : [], 'osclass' : [], 'portused' : {} }

    @property
    def addresses(self):
        return [ a.get('addr') for a in self.xml.findall('host/address') if a.get('addrtype') == 'ipv4' ]

    @property
    def report(self):
        return self.output

    def mac(self, address):
        host = self._host(address)
        if host is not None:
            for addr in host.findall('address'):
                if addr.get('addrtype') == 'mac':
                    return addr.get('addr')
        return None

    def _host(self, address):
        for host in self.xml.findall('host'):
            for addr in host.findall('address'):
                if addr.get('addr') == address:
                    return host
        return None

    def ports(self, address):
        host = self._host(address)
        ports = []
        if host is not None:
            for p in host.findall('ports/port'):
                r = p.attrib
                map(lambda x: r.update(x.attrib), p.getchildren())
                ports.append(r)
        return ports

    @property
    def scaninfo(self):
        return self.xml.find('scaninfo').attrib

    @property
    def verbosity(self):
        return self.xml.find('verbose').get('level')

    @property
    def debugging(self):
        return self.xml.find('debugging').get('level')

    def hostnames(self, address):
        host = self._host(address)
        if host is not None:
            return [ hn.attrib for hn in host.findall('hostnames/hostname') ]
        return []

    def times(self, address):
        host = self._host(address)
        if host is not None:
            return host.find('times').attrib
        return {}

    @property
    def runstats(self):
        rs = {}
        map(lambda x: rs.update(x.attrib), self.xml.find('runstats').getchildren())
        return rs

    def scanstats(self, address):
        host = self._host(address)
        if host is not None:
            return host.attrib
        return {}

    def status(self, address):
        host = self._host(address)
        if host is not None:
            return host.find('status').attrib
        return {}

    @property
    def nmaprun(self):
        return self.xml.attrib

    def tobanner(self, port):
        banner = port.get('product', 'Unknown')
        version = port.get('version')
        if version is not None:
#.........这里部分代码省略.........

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import findall [as 别名]
def run(args):

    opts = parse_args(args)

    if path.exists(opts.outfile) and not opts.append and not \
       parse_bool('%s already exists. Are you sure you want to overwrite it? [y/N]: ' % repr(opts.outfile), default='n'):
        exit(-1)


    ar = DirFile(
        path.join(detect_settings_dir(), 'config', 'Maltego', 'Entities')
    ) if opts.mtz_file is None else ZipFile(opts.mtz_file)

    entities = filter(lambda x: x.endswith('.entity'), ar.namelist())

    nses = dict()

    el = []
    if opts.append:
        l = diff(opts.outfile)
        el.extend([i.type for i in l])
        for i in l:
            if i.type.endswith('Entity'):
                nses[i.namespace] = i.__class__.__name__

    print 'Generating %s...' % repr(opts.outfile)
    fd = open(opts.outfile, 'ab' if opts.append else 'wb')

    if opts.append:
        fd.write('\n\n')
    else:
        fd.write('#!/usr/bin/env python\n\nfrom canari.maltego.entities import EntityField, Entity\n\n\n')

    for e in entities:
        xml = XML(ar.open(e).read())
        id_ = xml.get('id')

        if (opts.entity and id_ not in opts.entity) or id_ in el:
            continue

        ens = id_.split('.')

        base_classname = None
        namespace = '.'.join(ens[:-1])
        name = ens[-1]
        classname = name

        if (opts.namespace and namespace not in opts.namespace) or namespace in opts.exclude_namespace:
            continue

        if namespace not in nses:
            base_classname = '%sEntity' % (''.join([ n.title() for n in ens[:-1] ]))
            nses[namespace] = base_classname

            fd.write('class %s(Entity):\n    namespace = %s\n\n' % (base_classname, repr(namespace)))
        else:
            base_classname = nses[namespace]


        for f in xml.findall('Properties/Fields/Field'):
            fields = [
                'name=%s' % repr(f.get('name')),
                'propname=%s' % repr(normalize_fn(f.get('name'))),
                'displayname=%s' % repr(f.get('displayName'))

            ]
            fd.write('@EntityField(%s)\n' % ', '.join(fields))

        fd.write('class %s(%s):\n    pass\n\n\n' % (classname, base_classname))

    fd.close()
    print 'done.'