Python XML.findall方法代码示例

# 需要导入模块: from xml.etree.ElementTree import XML [as 别名]
# 或者: from xml.etree.ElementTree.XML import findall [as 别名]
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

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

# 需要导入模块: from xml.etree.ElementTree import XML [as 别名]
# 或者: from xml.etree.ElementTree.XML import findall [as 别名]
    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

# 需要导入模块: from xml.etree.ElementTree import XML [as 别名]
# 或者: from xml.etree.ElementTree.XML import findall [as 别名]
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

# 需要导入模块: from xml.etree.ElementTree import XML [as 别名]
# 或者: from xml.etree.ElementTree.XML import findall [as 别名]
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

# 需要导入模块: from xml.etree.ElementTree import XML [as 别名]
# 或者: from xml.etree.ElementTree.XML import findall [as 别名]
	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

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

# 需要导入模块: from xml.etree.ElementTree import XML [as 别名]
# 或者: from xml.etree.ElementTree.XML import findall [as 别名]
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]

# 需要导入模块: from xml.etree.ElementTree import XML [as 别名]
# 或者: from xml.etree.ElementTree.XML import findall [as 别名]
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]

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

# 需要导入模块: from xml.etree.ElementTree import XML [as 别名]
# 或者: from xml.etree.ElementTree.XML import findall [as 别名]
    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

# 需要导入模块: from xml.etree.ElementTree import XML [as 别名]
# 或者: from xml.etree.ElementTree.XML import findall [as 别名]
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

# 需要导入模块: from xml.etree.ElementTree import XML [as 别名]
# 或者: from xml.etree.ElementTree.XML import findall [as 别名]
    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

# 需要导入模块: from xml.etree.ElementTree import XML [as 别名]
# 或者: from xml.etree.ElementTree.XML import findall [as 别名]
 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

# 需要导入模块: from xml.etree.ElementTree import XML [as 别名]
# 或者: from xml.etree.ElementTree.XML import findall [as 别名]
	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