def pmc_article_search():
id_list = []
search_string = '((neuron electrophysiology) OR (neurophysiology) OR ("input resistance") OR ("resting potential" OR "resting membrane potential") OR "LTP" OR "synaptic plasticity" OR "LTD")'
search_string_quoted = quote(search_string, safeChars)
#print search_string_quoted
retstart = 0
retmax = 20
link = esearch % (search_string_quoted, retstart, retmax)
req = Request(link)
handle = urlopen(req)
data = handle.read()
xml = XML(data)
num_found_articles = 20#int(xml.find('.//Count').text)
while retstart < num_found_articles:
link = esearch % (search_string_quoted, retstart, retmax)
req = Request(link)
handle = urlopen(req)
data = handle.read()
#print data
xml = XML(data)
id_list_temp = xml.findall(".//Id")
if len(id_list_temp) == 0:
id_list_temp = int(xml.findall(".//Id"))
for id_elem in id_list_temp:
id_list.append(int(id_elem.text))
retstart += retmax
return id_list
def protocolParser(protocol,game,conn):
print protocol
xmlelement=XML(protocol)
print xmlelement.tag
if(xmlelement.tag=="CLOGIN"):
a_lst = xmlelement.findall("username")
val=''
for node in a_lst:
val=node.attrib["usr"]
print val
threading.Thread(target=srvau(val,game,conn)).start()
elif(xmlelement.tag=="CPLAY"):
a_lst = xmlelement.findall("username")
print 'a_lst'
val=''
for node in a_lst:
val=node.attrib["usr"]
print val
threading.Thread(target=splay(val,game,conn)).start()
elif(xmlelement.tag=="CDICE"):
a_lst = xmlelement.findall("username")
val=''
for node in a_lst:
val=node.attrib["usr"]
print val
threading.Thread(target=sdice(val,game,conn)).start()
def analyze(self, url, text=None):
if text:
args = {'uri': url, 'appId': self.api_key, 'text': text}
else:
args = {'uri': url, 'appId': self.api_key}
args_enc = urllib.urlencode(args)
output = urllib.urlopen(self.url, args_enc).read()
results = []
if output:
dom = XML(output)
aliases = []
for alias in dom.findall('.//alias'):
aliases.append(alias.text)
for entity in dom.findall('.//entity'):
name = entity.find('name')
try:
if float(entity.attrib['score']) < self.relevance:
continue
except KeyError:
pass
if name != None:
if name.text in aliases:
continue
cname = entity.find('canonicalName')
if cname != None:
name = cname
if name == None:
continue
else:
if name.text in results:
continue
results.append(name.text)
return results
def _get_sys_info(self):
"""
Returns sysinfo of host system in the following format::
{'memory': [{'bank_locator': 'BANK 0',
'form_factor': 'SODIMM',
'locator': 'ChannelA-DIMM0',
'manufacturer': 'Samsung',
'part_number': 'M471B5273DH0-CK0',
'serial_number': '9760E90B',
'size': '4096 MB',
'speed': '1600 MHz',
'type': 'DDR3',
'type_detail': 'Synchronous'},
{'bank_locator': 'BANK 2',
'form_factor': 'SODIMM',
'locator': 'ChannelB-DIMM0',
'manufacturer': 'Micron',
'part_number': '16KTF51264HZ-1G6M1',
'serial_number': '3255C613',
'size': '4096 MB',
'speed': '1600 MHz',
'type': 'DDR3',
'type_detail': 'Synchronous'}],
'processor': {'external_clock': '100 MHz',
'family': 'Core i5',
'manufacturer': 'Intel(R) Corporation',
'max_speed': '2600 MHz',
'part_number': 'None',
'serial_number': 'None',
'signature': 'Type 0, Family 6, Model 58, Stepping 9',
'socket_destination': 'CPU Socket - U3E1',
'status': 'Populated, Enabled',
'type': 'Central Processor',
'version': 'Intel(R) Core(TM) i5-3320M CPU @ 2.60GHz'},
'system': {'family': 'ThinkPad T430',
'manufacturer': 'LENOVO',
'product': '234455G',
'serial': 'PBKVYA6',
'sku': 'LENOVO_MT_2344',
'uuid': 'D6A27701-51F5-11CB-963F-F8A34AA11505',
'version': 'ThinkPad T430'}}
"""
xml = XML(self.conn.getSysinfo(0))
sysinfo = {}
keys = ['system', 'processor']
for key in keys:
sysinfo[key] = {}
for element in xml.findall(key+'/entry'):
sysinfo[key][element.attrib['name']] = element.text
sysinfo['memory'] = []
for memorydevs in xml.findall('memory_device'):
x = {}
for entry in memorydevs.findall('entry'):
x[entry.attrib['name']] = entry.text
sysinfo['memory'].append(x)
return sysinfo
def pubmed_count_coauthored_papers(author_1, author_2):
"""
Count number of co-published papers between author_1 and author_2
co-published defined by number of papers in pubmed where author_1 is
first author and author_2 is last author
Args:
author_1 (str): String of first authors name; e.g., Tripathy S
author_2 (str): String of second authors name; e.g., Urban N
Returns:
match_count (int): count of numbers of matching pubmed articles
"""
advisee_author_str = author_1
adviser_author_str = author_2
esearchlink = 'http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?'+\
'db=pubmed&term=%s[Author] AND (%s[Author])'
efetch = 'http://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?'+\
'&db=pubmed&retmode=xml&id=%s'
advisee_last_name = advisee_author_str.split()[0]
#print advisee_last_name
adviser_last_name = adviser_author_str.split()[0]
match_count = 0
link = esearchlink % (advisee_author_str, adviser_author_str)
linkCoded = quote(link, ':=/&()?_')
req = Request(linkCoded)
handle = urlopen(req)
data = handle.read()
xml = XML(data)
matching_pmids = [xml_ob.text for xml_ob in xml.findall('.//Id')]
for pmid in matching_pmids:
link = efetch % (pmid)
req = Request(link)
handle = urlopen(req)
data = handle.read()
xml = XML(data)
authorList = xml.findall(".//Author[@ValidYN='Y']")
if len(authorList) == 0:
authorList = xml.findall(".//Author")
#print authorList
if len(authorList) > 1:
#print data
try:
first_author_last_name = authorList[0].find("./LastName").text
#print first_author_last_name
last_author_last_name = authorList[-1].find("./LastName").text
except Exception:
continue
if first_author_last_name == advisee_last_name and last_author_last_name == adviser_last_name:
match_count += 1
#print '%s, %s, matching pubs = %d' % \
# (advisee_author_str, adviser_author_str, match_count)
return match_count
def _list_alchemy_results(xml, relevance):
dom = XML(xml)
results = []
if dom.find("status").text == "OK":
for concept in dom.findall(".//concept"):
if float(concept.find("relevance").text) > relevance:
results.append(concept.find("text").text)
for kw in dom.findall(".//keyword"):
if float(kw.find("relevance").text) > relevance:
results.append(kw.find("text").text)
return results
def _list_alchemy_results(xml,relevance):
dom = XML(xml)
results = []
if dom.find('status').text == 'OK':
for concept in dom.findall('.//concept'):
if float(concept.find('relevance').text) > relevance:
results.append(concept.find('text').text)
for kw in dom.findall('.//keyword'):
if float(kw.find('relevance').text) > relevance:
results.append(kw.find('text').text)
return results
def test_myschema_xsd02(self):
"With Document"
body_map = {'user_id': 1, 'title': '',
'description': '', 'linked_folder': '', 'filedata': '',
}
backend = self._get_backend(DocumentFakeBackend, subject='create_doc',
body_map=body_map, model=Document
)
builder = self._get_builder(backend)
xsd = '{http://www.w3.org/2001/XMLSchema}'
content = builder._render_myschema_xsd(self.request)
xml = XML(content)
self.assertEqual(builder.namespace, xml.get('targetNamespace'))
self.assertEqual(builder.namespace,
re.search(r'xmlns:my="(?P<ns>[\w\d\-:/\.]*)"', content).groupdict()['ns']
) # Can't be got with ElementTree, because it's a namespace
ref_attrs = {node.get('ref')
for node in xml.findall('{xsd}element/{xsd}complexType/{xsd}sequence/{xsd}element'.format(xsd=xsd))
}
expected_ref_attrs = {'my:{}'.format(key) for key in body_map}
self.assertEqual(expected_ref_attrs, ref_attrs)
xsd_elements = {
'CremeCRMCrudity': {'name': 'CremeCRMCrudity'},
'user_id': {'name': 'user_id', 'type': 'xsd:integer'}, # <xsd:element name="user_id" type="xsd:integer"/>
'title': {'name': 'title', 'type': 'my:requiredString'}, # <xsd:element name="first_name" type="xsd:requiredString"/>
# <xsd:element name="description">
# <xsd:complexType mixed="true">
# <xsd:sequence>
# <xsd:any minOccurs="0" maxOccurs="unbounded"
# namespace="http://www.w3.org/1999/xhtml" processContents="lax"/>
# </xsd:sequence>
# </xsd:complexType>
# </xsd:element>
'description': {'name': 'description'},
'linked_folder': {'name': 'linked_folder', 'type': 'xsd:integer'},
'filedata': {'name': 'filedata', 'type': 'my:requiredBase64Binary'},
}
for element_node in xml.findall('{}element'.format(xsd)):
xsd_element_attrs = xsd_elements.get(element_node.get('name'))
if xsd_element_attrs is None:
self.fail('There is at least an extra node named: {}'.format(element_node.get('name')))
self.assertEqual(set(xsd_element_attrs.keys()), set(element_node.keys()))
for attr in element_node.keys():
self.assertEqual(xsd_element_attrs[attr], element_node.get(attr))
def parse(self,url):
ti = TextInventory()
logger.info("Parsing CTS service @ %s"%url)
try:
# TODO: separate this line in order to raise separate errors!
xml_ti = XML(urllib2.urlopen(url+_get_capab_req).read())
# retrieve and store the TI version
for node in xml_ti.findall('.//%sTextInventory'%_cts_ns):
ti.set_version(node.attrib.get('tiversion'))
logger.info("TextInventory version: %s"%ti.get_version())
# retrieve and store the textgroups
for node in xml_ti.findall('.//%stextgroup'%_cts_ns):
tg = TextGroup(id=node.attrib.get('projid'))
tg.xml = ElementTree.tostring(node)
ti.add('tg',tg)
# retrieve and store the works
for child in node:
# parse groupname elem
if(child.tag=="%s%s"%(_cts_ns,"groupname")):
tg.set_name(child.attrib.get("%slang"%_xml_ns),re.sub(r'\s\s+',"",child.text))
logger.debug("Found TextGroup: \"%s\""%tg.get_name(child.attrib.get("%slang"%_xml_ns)))
#parse work elem
elif(child.tag=="%s%s"%(_cts_ns,"work")):
w = Work(id=child.attrib.get('projid'),tg=tg.id)
for title in child.findall('.//%stitle'%_cts_ns):
w.set_title(title.text)
ti.add('wk',w)
logger.debug("Found Work: %s"%w.id)
# parse edition elem
for node in child.findall('.//%sedition'%_cts_ns):
e = Edition(id=node.attrib.get('projid'),work=w.id)
for child in node:
if(child.tag=="%s%s"%(_cts_ns,"label")):
e.label=child.text
elif(child.tag=="%s%s"%(_cts_ns,"description")):
lang=child.attrib.get("%slang"%_xml_ns)
desc=child.text
e.add_desc(lang,desc)
elif(child.tag=="%s%s"%(_cts_ns,"online")):
pass
#
ti.add('ed',e)
except ExpatError as error:
logger.error("Parsing of %s failed with error \"%s\""%(url,str(error)))
return ti
def check_existing_license(netconf_handler, licensetype='essential'):
'''
This procedure takes in the netconf handler for the switch and configures 2-event classification on the given interface.
Procedure returns True if configuration successful, else returns False
'''
licenseVaildated = False
output = (str(
netconf_handler.get_config(source='running',
filter=('xpath', "/native/license"))))
netconf_reply = xml.dom.minidom.parseString(
str(
netconf_handler.get_config(source='running',
filter=('xpath', "/native/license"))))
config = XML(netconf_reply.toxml("utf-8"))
for data in config.findall(
'{urn:ietf:params:xml:ns:netconf:base:1.0}data'):
for native in data.findall(
'{http://cisco.com/ns/yang/Cisco-IOS-XE-native}native'):
for license in native.findall(
'{http://cisco.com/ns/yang/Cisco-IOS-XE-native}license'):
for boot in license.findall(
'{http://cisco.com/ns/yang/Cisco-IOS-XE-native}boot'):
for level in boot.findall(
'{http://cisco.com/ns/yang/Cisco-IOS-XE-native}level'
):
for lictype in level:
if licensetype in str(lictype.tag):
licenseVaildated = True
if licenseVaildated:
return_val = True
else:
print("license not validated. Output %s" % output)
return_val = False
return return_val
def parse_kml(kmlstring):
entries = []
kmldom = XML(kmlstring)
ns = kmldom.tag.strip('kml')
placemarks = kmldom.findall('.//%sPlacemark' % ns)
for placemark in placemarks:
entry = {
'title': '',
'summary': '',
'summary_detail': {
'type': 'text/html'
},
'link': '',
'tags': None
}
title = placemark.findall(ns + 'name')
if title:
entry['title'] = title[0].text
else:
entry['title'] = ''
summary = placemark.findall(ns + 'description')
entry['summary'] = sanitize_kml_description(summary)
links = placemark.findall('{http://www.w3.org/2005/Atom}link')
for link in links:
entry['link'] = link.attrib.get('href')
entries.append(entry)
return entries
def __init__(self, **kwargs):
self._issue_date_utc = None
self._expiration_date_utc = None
self.is_trial = "false"
if "xml_node" in kwargs:
xml_node = kwargs["xml_node"]
else:
xml_node = XML(kwargs["xml"])
xml_attrs = xml_node.attrib
attrs = {
"id": "licenseId",
"user_id": "userId",
"payment_plan_id": "paymentPlanId",
"issue_date_utc": "issueDateUTC",
"expiration_date_utc": "expirationDateUTC",
"is_trial": "is_trial",
}
for k, v in attrs.items():
if v in xml_attrs:
setattr(self, k, xml_attrs[v])
else:
setattr(self, k, None)
features = []
for node in xml_node.findall(".//feature"):
feature = Feature(xml_node=node)
features.append(feature)
self.features = features
super().__init__(**kwargs)
def _parseIssueFeed(self, value, rd):
try:
feed = XML(value)
except:
rd.errback()
return
data = []
for item in feed.findall('channel/item'):
timeStruct = time.strptime(item.find('updated').text, '%a, %d %b %Y %H:%M:%S +0000')
component = item.find('component')
if component is None:
component = 'n/a'
else:
component = component.text
data.append({
'key': item.find('key').text,
'link': item.find('link').text,
'summary': item.find('summary').text,
'type': item.find('type').text,
'status': item.find('status').text,
'component': component,
'updated': timeStruct,
})
rd.callback(data)
def verify_optics_configuration(netconf_handler, main_interface):
payload = '''
<filter>
<interfaces xmlns="http://cisco.com/ns/yang/Cisco-IOS-XE-interfaces-oper">
<interface>
<name>{itf}</name>
</interface>
</interfaces>
</filter>
'''
breakout_interface = main_interface + "/2"
netconf_reply = xml.dom.minidom.parseString(str(netconf_handler.get(payload.format(itf=breakout_interface))))
oper_data = XML(netconf_reply.toxml("utf-8"))
for data in oper_data.findall('{urn:ietf:params:xml:ns:netconf:base:1.0}data'):
for element in data.findall('{http://cisco.com/ns/yang/Cisco-IOS-XE-interfaces-oper}interfaces'):
for intf in element.findall('{http://cisco.com/ns/yang/Cisco-IOS-XE-interfaces-oper}interface'):
itf_name = intf.find('{http://cisco.com/ns/yang/Cisco-IOS-XE-interfaces-oper}name').text
print(itf_name)
try:
if itf_name == breakout_interface:
return_val = True
except:
return_val = False
return return_val
def load(text, match=None):
"""This function reads a string that contains the XML of an Atom Feed, then
returns the
data in a native Python structure (a ``dict`` or ``list``). If you also
provide a tag name or path to match, only the matching sub-elements are
loaded.
:param text: The XML text to load.
:type text: ``string``
:param match: A tag name or path to match (optional).
:type match: ``string``
"""
if text is None: return None
text = text.strip()
if len(text) == 0: return None
nametable = {
'namespaces': [],
'names': {}
}
root = XML(text)
items = [root] if match is None else root.findall(match)
count = len(items)
if count == 0:
return None
elif count == 1:
return load_root(items[0], nametable)
else:
return [load_root(item, nametable) for item in items]
def updated(downloader, path, _):
if path is None:
logging.error('internet archive file list get fail')
# FIXME: report to user a failure to download
return
from xml.etree.ElementTree import XML
xml = XML(open(path, 'r').read())
os.remove(path)
table = {
'text pdf': u'application/pdf',
'grayscale luratech pdf': u'application/pdf-bw',
'image container pdf': u'application/pdf',
'djvu': u'image/x.djvu',
'epub': u'application/epub+zip',
}
chosen = None
for element in xml.findall('file'):
fmt = element.find('format').text.lower()
if fmt in table:
if table[fmt] == content_type:
chosen = element.get('name')
break
if chosen is None:
logging.error('internet archive file list omits content type')
# FIXME: report to user a failure to find matching content
return
url = os.path.join(url_base, chosen)
GObject.idle_add(download_cb, url)
def _parseIssueFeed(self, value, rd):
try:
feed = XML(value)
except:
rd.errback()
return
data = []
for item in feed.findall('channel/item'):
timeStruct = time.strptime(item.find('updated').text, '%a, %d %b %Y %H:%M:%S +0000')
component = item.find('component')
if component is None:
component = 'n/a'
else:
component = component.text
data.append({
'key': item.find('key').text,
'link': item.find('link').text,
'summary': item.find('summary').text,
'type': item.find('type').text,
'status': item.find('status').text,
'component': component,
'updated': timeStruct,
})
rd.callback(data)
def __init__(self, args):
self.args = args
url = opener.open(args.build+"api/xml")
try:
log.debug('Fetching xml from %s code:%d', url.url, url.code)
if url.code != 200:
log.error('Failed to get CI XML from %s (code %d)',
url.url, url.code)
raise Stop(20, 'Job lookup failed, is the job name correct?')
ci_xml = url.read()
finally:
url.close()
root = XML(ci_xml)
artifacts = root.findall("./artifact")
base_url = args.build+"artifact/"
if len(artifacts) <= 0:
raise AttributeError(
"No artifacts, please check build on the CI server.")
patterns = self.get_artifacts_list()
for artifact in artifacts:
filename = artifact.find("fileName").text
for key, value in patterns.iteritems():
if re.compile(value).match(filename):
rel_path = base_url + artifact.find("relativePath").text
setattr(self, key, rel_path)
pass
def gsversion(self):
'''obtain the version or just 2.2.x if < 2.3.x
Raises:
FailedRequestError: If the request fails.
'''
if self._version: return self._version
about_url = self.service_url + "/about/version.xml"
response, content = self.http.request(about_url, "GET")
version = None
if response.status == 200:
dom = XML(content)
resources = dom.findall("resource")
for resource in resources:
if resource.attrib["name"] == "GeoServer":
try:
version = resource.find("Version").text
break
except:
pass
#This will raise an exception if the catalog is not available
#If the catalog is available but could not return version information,
#it is an old version that does not support that
if version is None:
self.get_workspaces()
# just to inform that version < 2.3.x
version = "2.2.x"
self._version = version
return version
def test_manifest_xsf_02(self):
"Test Image fk field."
body_map = {'user_id': 1, 'image': ''}
backend = self._get_backend(
ContactFakeBackend,
subject='create_contact', body_map=body_map, model=Contact,
)
builder = self._get_builder(backend)
content = builder._render_manifest_xsf(self.request)
self.assertEqual(re.search(r'xmlns:my="(?P<ns>[\w\d\-:/\.]*)"', content)['ns'],
builder.get_namespace()
) # Can't be got with ElementTree, because it's a namespace
xsf = '{http://schemas.microsoft.com/office/infopath/2003/solutionDefinition}'
xml = XML(content)
xmlToEdit_node = xml.find(f'{xsf}views/{xsf}view/{xsf}editing/{xsf}xmlToEdit')
self.assertIsNotNone(xmlToEdit_node)
self.assertEqual('image', xmlToEdit_node.get('name'))
self.assertEqual('/my:CremeCRMCrudity/my:image', xmlToEdit_node.get('item'))
button_nodes = xml.findall(f'{xsf}views/{xsf}view/{xsf}menuArea/{xsf}button')
self.assertTrue(button_nodes)
self.assertSetEqual(
{'image'}, {button_node.get('xmlToEdit') for button_node in button_nodes}
)
def findSha1Artifacts(self, strFileName, strGroupID, strArtifactID):
atVersions = []
# Generate the SHA1 sum for the file.
strFileSha1 = self.generate_sha1_from_file(strFileName)
strPath = self.strUrlLuceneSearchSha1 % strFileSha1
aucContent = self.tRestDriver.get(self.tServerBaseUrl, strPath)
tSearchResult = XML(aucContent)
# The search result must be complete.
if tSearchResult.findtext('tooManyResults')!='false':
raise Exception("Received a truncated search result!")
# Loop over all results.
for tNode in tSearchResult.findall('data/artifact'):
strG = tNode.findtext('groupId')
strA = tNode.findtext('artifactId')
strVersion = tNode.findtext('version')
if isinstance(strG, basestring)==True and isinstance(strA, basestring)==True and isinstance(strVersion, basestring)==True:
strG = strG.strip()
strA = strA.strip()
strVersion = strVersion.strip()
if strGroupID==strG and strArtifactID==strA:
if strVersion=='SNAPSHOT':
tVersion = deploy_version.version(0, 0, 0)
else:
tVersion = deploy_version.version(strVersion)
atVersions.append(tVersion)
atVersions.sort()
return atVersions
def get_pubmed_id_from_doi(doi):
searchLink = "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term=%s[aid]" % (doi)
handle = urlopen(searchLink)
data = handle.read()
xml = XML(data) # convert to an xml object so we can apply x-path search fxns to it
pmidList = [x.text for x in xml.findall(".//Id")] # find xml "Id" elements
return pmidList
def do_dg_wwn_map(self):
devs = []
with open(self.dgfile_local_name, "r") as filep:
for line in filep.readlines():
if "DEV" not in line:
continue
devs.append(line.split()[1])
cmd = [
"/usr/symcli/bin/symdev", "list", "-output", "xml_e", "-sid",
self.symid, "-devs", ",".join(devs), "-v"
]
ret, out, err = self.call(cmd)
if ret != 0:
raise ex.Error("Failed to run command %s" % ' '.join(cmd))
tree = XML(out)
mapping = []
for dev in tree.findall("Symmetrix/Device"):
try:
local = dev.find('Product/wwn').text
remote = dev.find('RDF/Remote/wwn').text
except Exception as exc:
self.log.warning(str(exc))
else:
mapping.append((local, remote))
with open(self.wwn_map_fpath, 'w') as filep:
json.dump(mapping, filep)
filep.write("\n")
def print_usa(url):
data = get_data(url)
dy = XML(data)
for cd in dy.findall("./CD"):
if cd.find("./YEAR").text == "1988":
print cd.find("./TITLE").text
def download(job, regex):
"""Grabs platform specific distribution targets from Hudson"""
url = urllib.urlopen("/".join([HUDSON_ROOT, job, HUDSON_XML_SUFFIX]))
hudson_xml = url.read()
hudson_xml = hudson_xml.replace('origin/', 'origin_')
url.close()
root = XML(hudson_xml)
building = root.findtext("./building")
if building == 'true':
print '%s build in progress, exiting...' % job
sys.exit(1)
revision = root.findtext("./changeSet/revision/revision")
artifacts = root.findall("./artifact")
print "Retrieving %s job artifacts from revision: %s" % (job, revision)
base_url = "/".join([HUDSON_ROOT, job, 'lastSuccessfulBuild/artifact'])
new_artifacts = list()
for artifact in artifacts:
filename = artifact.findtext("fileName")
if not regex.match(filename):
continue
artifact_url = "/".join([base_url, artifact.findtext("relativePath")])
print "Downloading %s from URL %s" % (filename, artifact_url)
urllib.urlretrieve(artifact_url , filename)
new_artifacts.append(filename)
return [revision, new_artifacts]
def updated(downloader, path, _):
if path is None:
logging.error('internet archive file list get fail')
# FIXME: report to user a failure to download
return
from xml.etree.ElementTree import XML
xml = XML(open(path, 'r').read())
os.remove(path)
table = {
'text pdf': u'application/pdf',
'grayscale luratech pdf': u'application/pdf-bw',
'image container pdf': u'application/pdf',
'djvu': u'image/x.djvu',
'epub': u'application/epub+zip',
}
chosen = None
for element in xml.findall('file'):
fmt = element.find('format').text.lower()
if fmt in table:
if table[fmt] == content_type:
chosen = element.get('name')
break
if chosen is None:
logging.error('internet archive file list omits content type')
# FIXME: report to user a failure to find matching content
return
url = os.path.join(url_base, chosen)
GObject.idle_add(download_cb, url)
def get_version(self):
'''obtain the version or just 2.2.x if < 2.3.x
Raises:
FailedRequestError: If the request fails.
'''
if self._version:
return self._version
url = "{}/about/version.xml".format(self.service_url)
resp = self.http_request(url)
version = None
if resp.status_code == 200:
dom = XML(resp.content)
resources = dom.findall("resource")
for resource in resources:
if resource.attrib["name"] == "GeoServer":
try:
version = resource.find("Version").text
break
except AttributeError:
pass
# This will raise an exception if the catalog is not available
# If the catalog is available but could not return version information,
# it is an old version that does not support that
if version is None:
# just to inform that version < 2.3.x
version = "2.2.x"
self._version = version
return version
def _process_tokenizer(self, tokenizer):
# tokenizer_tokens = [token for token in tokenizer]
# no_marks = map(lambda s: s.strip('\'').strip(), tokenizer_tokens)
no_marks = map(lambda s: s.strip("'").strip(), tokenizer)
token_tree = XML(''.join(no_marks))
token_iter = token_tree.findall('.//')
return (token for token in token_iter)
def gsversion(self):
'''obtain the version or just 2.2.x if < 2.3.x
Raises:
FailedRequestError: If the request fails.
'''
if self._version: return self._version
about_url = self.service_url + "/about/version.xml"
response, content = self.http.request(about_url, "GET")
version = None
if response.status == 200:
dom = XML(content)
resources = dom.findall("resource")
for resource in resources:
if resource.attrib["name"] == "GeoServer":
try:
version = resource.find("Version").text
break
except:
pass
#This will raise an exception if the catalog is not available
#If the catalog is available but could not return version information,
#it is an old version that does not support that
if version is None:
self.get_workspaces()
# just to inform that version < 2.3.x
version = "2.2.x"
self._version = version
return version
def getAllArtifactVersions(self, strGroupID, strArtifactID):
atVersions = []
strPath = self.strUrlLuceneSearchGA % (strGroupID, strArtifactID)
aucContent = self.tRestDriver.get(self.tServerBaseUrl, strPath)
tSearchResult = XML(aucContent)
# The search result must be complete.
if tSearchResult.findtext('tooManyResults') != 'false':
raise Exception("Received a truncated search result!")
# Loop over all results.
for tNode in tSearchResult.findall('data/artifact'):
strVersion = tNode.findtext('version')
if isinstance(strVersion, basestring) == True:
strVersion = strVersion.strip()
if strVersion == 'SNAPSHOT':
tVersion = deploy_version.version(0, 0, 0)
else:
tVersion = deploy_version.version(strVersion)
atVersions.append(tVersion)
# Sort the versions.
atVersions.sort()
return atVersions
def identify(self, geosGeometry, geometryFieldName, layers, url, username, password):
"""
Assuming :
Url like http://localhost:8080/geoserver/wfs
layers like geonode:capa
geosGeometry is in Lambert72
"""
#TODO input checking
gmlString = geosGeometry.ogr.gml
payload = self._buildWfsIntersectRequest(gmlString, layers, geometryFieldName)
#Verify False to avoid certificate not trusted problems
r = requests.post(url, data = payload, auth=(username, password), verify=False)
tree = XML(r.text)
if tree.tag == "{http://www.opengis.net/ogc}ServiceExceptionReport":
#We Got OGC Error. Find the root cause and throw a proper Exception
se = tree.find('{http://www.opengis.net/ogc}ServiceException')
raise Exception(str(se.text).strip())
else:
clean_results = []
features = tree.findall('{http://www.opengis.net/gml}featureMember')
for feature in features:
attributes = {}
for child in feature:
for child_elem in child:
tag_name = child_elem.tag.split('}')[-1] #Get rid of namespace
if child_elem.text is not None:
attributes[tag_name] = child_elem.text
else:
attributes[tag_name] = ""
clean_results.append(attributes)
return clean_results
def getAllArtifactVersions(self, strGroupID, strArtifactID):
atVersions = []
strPath = self.strUrlLuceneSearchGA % (strGroupID, strArtifactID)
aucContent = self.tRestDriver.get(self.tServerBaseUrl, strPath)
tSearchResult = XML(aucContent)
# The search result must be complete.
if tSearchResult.findtext('tooManyResults')!='false':
raise Exception("Received a truncated search result!")
# Loop over all results.
for tNode in tSearchResult.findall('data/artifact'):
strVersion = tNode.findtext('version')
if isinstance(strVersion, basestring)==True:
strVersion = strVersion.strip()
if strVersion=='SNAPSHOT':
tVersion = deploy_version.version(0, 0, 0)
else:
tVersion = deploy_version.version(strVersion)
atVersions.append(tVersion)
# Sort the versions.
atVersions.sort()
return atVersions
def print_usa_cds(url):
data = get_data(url)
dx = XML(data)
for cd in dx.findall("./CD"):
if cd.find("./COUNTRY").text == "USA":
print(cd.find("./TITLE").text)
def verify_app_status(netconf_connection, appplication_name, status="deployed"):
'''
This procedure verifies the application status as deployed state. In order to change CPU and memory resources, Application need to be in deployed state.
'''
oper_payload = '''
<filter>
<virtual-services xmlns="http://cisco.com/ns/yang/Cisco-IOS-XE-virtual-service-oper">
<virtual-service>
<name>{application}</name>
<details>
<state/>
</details>
</virtual-service>
</virtual-services>
</filter>
'''
netconf_reply = xml.dom.minidom.parseString(str(netconf_connection.get(oper_payload.format(application=appplication_name))))
print(netconf_reply.toprettyxml( indent = " " ))
if "<ok/>" not in (netconf_reply.toprettyxml(indent = " ")):
return False
oper_data = XML(netconf_reply.toxml("utf-8"))
for data in oper_data.findall('{urn:ietf:params:xml:ns:netconf:base:1.0}data'):
for element in data.findall('{http://cisco.com/ns/yang/Cisco-IOS-XE-virtual-service-oper}virtual-services'):
for service in element.findall('{http://cisco.com/ns/yang/Cisco-IOS-XE-virtual-service-oper}virtual-service'):
app_name = service.find('{http://cisco.com/ns/yang/Cisco-IOS-XE-virtual-service-oper}name').text
for detail in service.findall('{http://cisco.com/ns/yang/Cisco-IOS-XE-virtual-service-oper}details'):
app_status = detail.find('{http://cisco.com/ns/yang/Cisco-IOS-XE-virtual-service-oper}state').text
if app_status.upper() == status.upper()
return_val = True
else:
return_val = False
return return_val
def get_version(self):
'''obtain the version or just 2.2.x if < 2.3.x
Raises:
FailedRequestError: If the request fails.
'''
if self._version:
return self._version
url = "{}/about/version.xml".format(self.service_url)
resp = self.http_request(url)
version = None
if resp.status_code == 200:
content = resp.content
if isinstance(content, bytes):
content = content.decode('UTF-8')
dom = XML(content)
resources = dom.findall("resource")
for resource in resources:
if resource.attrib["name"] == "GeoServer":
try:
version = resource.find("Version").text
break
except AttributeError:
pass
# This will raise an exception if the catalog is not available
# If the catalog is available but could not return version information,
# it is an old version that does not support that
if version is None:
# just to inform that version < 2.3.x
version = "2.2.x"
self._version = version
return version
def get_used_subid(netconf_handler):
'''
This procedure takes in the netconf handler for the switch and configures 2-event classification on the given interface.
Procedure returns True if configuration successful, else returns False
'''
netconf_reply = xml.dom.minidom.parseString(
str(
netconf_handler.get_config(source='running',
filter=('xpath', "/mdt-config-data"))))
config = XML(netconf_reply.toxml("utf-8"))
subscription_id = 1
for data in config.findall(
'{urn:ietf:params:xml:ns:netconf:base:1.0}data'):
for configdata in data.findall(
'{http://cisco.com/ns/yang/Cisco-IOS-XE-mdt-cfg}mdt-config-data'
):
for subscriptions in configdata.findall(
'{http://cisco.com/ns/yang/Cisco-IOS-XE-mdt-cfg}mdt-subscription'
):
subscription_id = int(
subscriptions.find(
'{http://cisco.com/ns/yang/Cisco-IOS-XE-mdt-cfg}subscription-id'
).text)
return subscription_id
def fetch_snp_records(ids):
# 2010-07-12 11:57 Reece Hart <*****@*****.**> Most (all other?)
# Entrez facilities use DTDs. dbSNP uses XSD (with namespaces), which
# isn't supported by Entrez.read. Use xml.elementtree instead.
xml = Entrez.efetch(db='snp',id=','.join(ids), retmode='xml').read()
d = XML(xml)
return map(_remap_dict_keys, map( _rs_elem_as_dict,
d.findall('{http://www.ncbi.nlm.nih.gov/SNP/docsum}Rs')))
def sanitize_kml(kmlstring):
kmldom = XML(kmlstring)
ns = kmldom.tag.strip('kml')
placemarks = kmldom.findall('.//%sPlacemark' % ns)
for placemark in placemarks:
summary = placemark.findall('%sdescription' % ns)
summary[0].text = sanitize_kml_description(summary)
return tostring(kmldom, 'utf-8')
def sanitize_kml(kmlstring):
kmldom = XML(kmlstring)
ns = kmldom.tag.strip('kml')
placemarks = kmldom.findall('.//%sPlacemark' % ns)
for placemark in placemarks:
summary = placemark.findall('%sdescription' % ns)
summary[0].text = sanitize_kml_description(summary)
return tostring(kmldom, 'utf-8')
def get_pubmed_id_from_title(titleEncoded):
queryStrQuoted = quote("(%s)" % titleEncoded, '()')
searchLink = 'http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term=%s' % (queryStrQuoted)
handle = urlopen(searchLink)
data = handle.read()
xml = XML(data) # convert to an xml object so we can apply x-path search fxns to it
pmidList = [x.text for x in xml.findall('.//Id')] # find xml "Id" elements
return pmidList
def verify_sw_version(netconf_handler,
min_major_release=16,
min_minor_release=9,
min_version=1):
'''
This procedure verifies whether the software version of the switch with <netconf_handler>is greater than or equal to given <min_sw_version>
Return True if condition satisfied, else return False
'''
payload = '''
<filter>
<device-hardware-data xmlns="http://cisco.com/ns/yang/Cisco-IOS-XE-device-hardware-oper">
<device-hardware>
<device-system-data>
<boot-time/>
<software-version/>
</device-system-data>
</device-hardware>
</device-hardware-data>
</filter>
'''
netconf_reply = xml.dom.minidom.parseString(
str(netconf_handler.get(payload)))
oper_data = XML(netconf_reply.toxml("utf-8"))
print(netconf_reply.toprettyxml(indent=" "))
for data in oper_data.findall(
'{urn:ietf:params:xml:ns:netconf:base:1.0}data'):
for element in data.findall(
'{http://cisco.com/ns/yang/Cisco-IOS-XE-device-hardware-oper}device-hardware-data'
):
for device in element.findall(
'{http://cisco.com/ns/yang/Cisco-IOS-XE-device-hardware-oper}device-hardware'
):
for sysdata in device.findall(
'{http://cisco.com/ns/yang/Cisco-IOS-XE-device-hardware-oper}device-system-data'
):
sw_version = sysdata.find(
'{http://cisco.com/ns/yang/Cisco-IOS-XE-device-hardware-oper}software-version'
).text
print(sw_version)
release = re.findall(r'^.*Version (\d+)\.(\d+)\.(\d+)', sw_version,
re.MULTILINE)
if (int(release[0][0]) >= int(min_major_release)) and (int(
release[0][1]) >= int(min_minor_release)) and (int(
release[0][2]) >= int(min_version)):
return_val = True
else:
print(
"Sofware version currently running: %s minimum expected release %s.%s.%s"
% (release, min_major_release, min_minor_release, min_version))
return_val = False
return return_val
def get_licenses(self, feature_ids = [], payment_plan_ids = []):
licenses = []
res = Base.api.do_request('GET', self.build_url('/licenses'), { 'featureIds': feature_ids, 'paymentPlanIds': payment_plan_ids })
xml = str(res['body'],'utf-8').replace("\n","")
doc = XML(xml)
for lnode in doc.findall('.//licenseCertificate'):
license = License(xml_node = lnode)
licenses.append(license)
return licenses
def getLastCommiter(file):
cmd = 'svn log --xml -l 1 %s'
output = os.popen(cmd % file)
content = output.read()
output.close()
root = XML(content)
for item in root.findall('logentry'):
return item.find('author').text, item.find('msg').text, item.find(
'date').text
def parse_cmml(cmml):
data = []
root = XML(cmml)
for clip in root.findall('clip'):
timestamp = _npt_to_timestamp(clip.attrib['start'])
url = '' # TODO: this
text = clip.attrib['title']
data.append({'timestamp': timestamp, 'url': url, 'text': text})
return data
def __init__(self, build=BUILD):
self.server = None
self.win = list()
self.mac = list()
self.linux = list()
url = urllib.urlopen(build + "api/xml")
hudson_xml = url.read()
url.close()
root = XML(hudson_xml)
artifacts = root.findall("./artifact")
base_url = build + "artifact/"
if len(artifacts) <= 0:
raise AttributeError("No artifacts, please check build on Hudson.")
for artifact in artifacts:
filename = artifact.find("fileName").text
if filename.startswith("OMERO.server"):
self.server = base_url + artifact.find("relativePath").text
elif filename.startswith('OMERO.source'):
self.source = base_url + artifact.find("relativePath").text
elif filename.startswith('OMERO.imagej') or\
filename.startswith('OMERO.java') or\
filename.startswith('OMERO.matlab') or\
filename.startswith('OMERO.py') or\
filename.startswith('OMERO.server'):
pass
elif filename.startswith("OMERO.importer"):
regex = re.compile(r'.*win.zip')
regex2 = re.compile(r'.*mac.zip')
if not regex.match(filename) and not regex2.match(filename):
self.linux.append(base_url +
artifact.find("relativePath").text)
else:
regex = re.compile(r'.*win.zip')
if regex.match(filename):
self.win.append(base_url +
artifact.find("relativePath").text)
regex = re.compile(r'.*OSX.zip')
if regex.match(filename):
self.mac.append(base_url +
artifact.find("relativePath").text)
regex = re.compile(r'.*mac.zip')
if regex.match(filename):
self.mac.append(base_url +
artifact.find("relativePath").text)
regex = re.compile(r'.*b\d+.zip')
if regex.match(filename):
self.linux.append(base_url +
artifact.find("relativePath").text)
def __parse_xml(self, xml):
self.__name_map.clear()
tree = XML(xml)
# <node key="N" id="Name"> ... </node>
list = tree.findall(".//node")
for itr in list:
self.__name_map[int(itr.get("key"))] = itr.get("id")
self.__xml = xml
def parse_name_map(xml_node_list):
name_map = {}
tree = XML(xml_node_list)
# <node key="N" id="Name"> ... </node>
list = tree.findall(".//node")
for itr in list:
name_map[int(itr.get("key"))] = itr.get("id")
return name_map
def get_profile_name(p):
"""
Takes a path object to the config xml
"""
xml = XML(p.text())
props = xml.findall("./properties")
for x in props:
id = x.attrib["id"]
if id == "__ACTIVE__":
for y in x.getchildren():
if y.attrib["name"] == "omero.config.profile":
return y.attrib["value"]
def get_pmid_from_str(in_str):
search_str = quote_plus(in_str)
searchLink = 'http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term=%s' % (search_str)
try:
handle = urlopen(searchLink)
data = handle.read()
xml = XML(data) # convert to an xml object so we can apply x-path search fxns to it
pmidList = [x.text for x in xml.findall('.//Id')] # find xml "Id" elements
if len(pmidList) > 1:
pmidList = [pmidList[0]]
except Exception, e:
pmidList = []
def get_profile_name(p):
"""
Takes a path object to the config xml
"""
xml = XML(p.text())
props = xml.findall("./properties")
for x in props:
id = x.attrib["id"]
if id == "__ACTIVE__":
for y in x.getchildren():
if y.attrib["name"] == "omero.config.profile":
return y.attrib["value"]
def __init__(self, build=BUILD):
self.server = None
self.win = list()
self.mac = list()
self.linux = list()
url = urllib.urlopen(build + "api/xml")
hudson_xml = url.read()
url.close()
root = XML(hudson_xml)
artifacts = root.findall("./artifact")
base_url = build + "artifact/"
if len(artifacts) <= 0:
raise AttributeError("No artifacts, please check build on Hudson.")
for artifact in artifacts:
filename = artifact.find("fileName").text
if filename.startswith("OMERO.server"):
self.server = base_url + artifact.find("relativePath").text
elif filename.startswith("OMERO.source"):
self.source = base_url + artifact.find("relativePath").text
elif (
filename.startswith("OMERO.imagej")
or filename.startswith("OMERO.java")
or filename.startswith("OMERO.matlab")
or filename.startswith("OMERO.py")
or filename.startswith("OMERO.server")
):
pass
elif filename.startswith("OMERO.importer"):
regex = re.compile(r".*win.zip")
regex2 = re.compile(r".*mac.zip")
if not regex.match(filename) and not regex2.match(filename):
self.linux.append(base_url + artifact.find("relativePath").text)
else:
regex = re.compile(r".*win.zip")
if regex.match(filename):
self.win.append(base_url + artifact.find("relativePath").text)
regex = re.compile(r".*OSX.zip")
if regex.match(filename):
self.mac.append(base_url + artifact.find("relativePath").text)
regex = re.compile(r".*mac.zip")
if regex.match(filename):
self.mac.append(base_url + artifact.find("relativePath").text)
regex = re.compile(r".*b\d+.zip")
if regex.match(filename):
self.linux.append(base_url + artifact.find("relativePath").text)
def _getDescriptors(smiles):
keys = defaultChemicalSpace.keys()
vals = []
for key in keys:
dnames = defaultChemicalSpace[key]
url = descriptorBaseUrl + "." + key + "/" + smiles
xml = "".join(urllib.urlopen(url).readlines())
root = XML(xml)
values = root.findall("Descriptor")
for value in values:
if value.get("name") in dnames:
vals.append(float(value.get("value")))
return vals
def get_pmid_from_doi(doiStr):
doiSearchStr = re.sub("/doi/", "", doiStr)
doiSearchStr = re.sub("/full", "", doiSearchStr)
searchLink = "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term=%s[aid]" % (doiSearchStr)
try:
handle = urlopen(searchLink)
data = handle.read()
xml = XML(data) # convert to an xml object so we can apply x-path search fxns to it
pmidList = [x.text for x in xml.findall(".//Id")] # find xml "Id" elements
if len(pmidList) > 1:
pmidList = []
except Exception, e:
pmidList = []
def _get_group_ids(self):
"""
helper to fetch the set of geonetwork
groups.
"""
# get the ids of the groups.
get_groups_url = self.base + "srv/en/xml.info?" + urllib.urlencode({'type': 'groups'})
request = urllib2.Request(get_groups_url)
response = self.urlopen(request)
doc = XML(response.read())
groups = {}
for gp in doc.findall('groups/group'):
groups[gp.find('name').text.lower()] = gp.attrib['id']
return groups
def _get_operation_ids(self):
"""
helper to fetch the set of geonetwork
'operations' (privileges)
"""
# get the ids of the operations
get_ops_url = self.base + "srv/en/xml.info?" + urllib.urlencode({'type': 'operations'})
request = urllib2.Request(get_ops_url)
response = self.urlopen(request)
doc = XML(response.read())
ops = {}
for op in doc.findall('operations/operation'):
ops[op.find('name').text.lower()] = op.attrib['id']
return ops
def getProcess(processName):
xmlfile = os.popen("wmic.exe process list /format:rawxml.xsl")
xmlcontent = ''
for line in xmlfile.readlines():
xmlcontent += line
root = XML(xmlcontent)
for instance in root.findall('RESULTS/CIM/INSTANCE'):
for property in instance.findall('PROPERTY'):
if property.attrib['NAME'] == 'CommandLine':
value = property.find('VALUE')
if value != None and value.text.find(processName) != -1:
return instance
def analyze(self, url, text=None):
if text:
args = {'uri': url,
'appId': self.api_key,
'text': text}
else:
args = {'uri': url,
'appId': self.api_key}
args_enc = urllib.urlencode(args)
output = urllib.urlopen(self.url, args_enc).read()
results = []
if output:
dom = XML(output)
aliases = []
for alias in dom.findall('.//alias'):
aliases.append(alias.text)
for entity in dom.findall('.//entity'):
name = entity.find('name')
try:
if float(entity.attrib['score']) < self.relevance:
continue
except KeyError:
pass
if name != None:
if name.text in aliases:
continue
cname = entity.find('canonicalName')
if cname != None:
name = cname
if name == None:
continue
else:
if name.text in results:
continue
results.append(name.text)
return results
