def initSearchClient(self):
print 'initialize search....'
http = HttpTransport()
opener = urllib2.build_opener(HTTPSudsPreprocessor(self.SID))
http.urlopener = opener
self.client['search'] = Client(self.url['search'], transport = http)
print 'searching initializtion done'
def search_lite(fieldtag, searchterm, ver, count, SID):
#fieldtag must be 'PN = ' or 'CD ='
http = HttpTransport()
opener = urllib2.build_opener(HTTPSudsPreprocessor(SID))
http.urlopener = opener
client_obj = Client(SEARCH_LITE_URL[int(ver - 2)], transport = http, retxml = True)
query = fieldtag + '=' + searchterm
#construct query and retrieve field parameters
qparams = {
'databaseId' : 'DIIDW',
'userQuery' : query,
'queryLanguage' : 'en',
'editions' : [{
'collection' : 'DIIDW',
'edition' : 'CDerwent',
},{
'collection' : 'DIIDW',
'edition' : 'MDerwent',
},{
'collection' : 'DIIDW',
'edition' : 'EDerwent',
}]
}
rparams = {
'count' : count, # 1-500
'firstRecord' : 1,
'sortField' : [{
'name' : 'TC',
'sort' : 'D',
}]
}
result = client_obj.service.search(qparams, rparams)
return result
def citingArticles(UID, SID):
url = client = {}
start_time = time.time()
http = HttpTransport()
opener = urllib.request.build_opener(HTTPSudsPreprocessor(SID))
http.urlopener = opener
url['citingArticles'] = 'http://search.webofknowledge.com/esti/wokmws/ws/WokSearch?wsdl'
client['citingArticles'] = Client(url['citingArticles'], transport=http)
databaseId = "WOS"
uid = UID
queryLanguage = "en"
editions = None
timeSpan = {'begin': "2003-01-01",
'end': "2017-12-31"}
rparams = {'count': 100,
'firstRecord': 1,
'viewField': {'collectionName': 'WOS',
'fieldName': ['pub_info', 'titles']}}
check_time(start_time)
return client['citingArticles'].service.citingArticles(databaseId, uid, editions, timeSpan, queryLanguage, rparams)
def _add_sid(self):
"""Create URL opener with authentication token as header."""
opener = urllib2.build_opener()
opener.addheaders = [('Cookie', 'SID="' + self.sid_token + '"')]
http = HttpTransport()
http.urlopener = opener
self._establish_search_client(http)
def auth(ver, type, username, password):
if ver == 2:
if type == 'up':
auth_client = Client(AUTH_URL_ver2, username = username, password = password) #version 2.0
SID = auth_client.service.authenticate()
return SID
elif type == 'ip':
auth_client = Client(AUTH_URL_ver2)
SID = auth_client.service.authenticate()
return SID
else:
print "Type either 'ip' or 'up'. 'ip' for ip access, 'up' for username/password access"
elif ver == 3:
if type == 'up':
username_password = ['username_password'][username]
#Your username/password from a purchased subscription should go here!
auth = HttpTransport()
auth_sender = urllib2.build_opener(HTTPAuthSender(username_password))
auth.urlopener = auth_sender
auth_client = Client(AUTH_URL_ver3, transport = auth)
SID = auth_client.service.authenticate()
return SID
elif type == 'ip':
auth_client = Client(AUTH_URL_ver3) #comment out if using username, password. #version 3.0
SID = auth_client.service.authenticate()
return SID
else:
print "Type either 'ip' or 'up'. 'ip' for ip access, 'up' for username/password access. username is an integer, password can be a null value for version 3."
else:
print "Authentication failed. Invalid version. Your request was not supported by this authentication module."
def _add_sid(self):
"""Create URL opener with authentication token as header."""
opener = urllib2.build_opener()
opener.addheaders = [('Cookie', 'SID="'+self.sid_token+'"')]
http = HttpTransport()
http.urlopener = opener
self._establish_search_client(http)
def conectar(self):
url = 'http://ws01.reclameaqui.com.br/webservice.php?wsdl'
t = HttpTransport()
proxy = urllib2.ProxyHandler({'http': 'http://5.9.41.147:6680'})
opener = urllib2.build_opener(proxy)
t.urlopener = opener
self.client = Client(
url, transport=t, username=self.username, password=self.password)
def citedReferencesRetrieve(queryId, SID, start_count):
url = client = {}
start_time = time.time()
http = HttpTransport()
opener = urllib.request.build_opener(HTTPSudsPreprocessor(SID))
http.urlopener = opener
url['citedReferencesRetrieve'] = 'http://search.webofknowledge.com/esti/wokmws/ws/WokSearch?wsdl'
client['citedReferencesRetrieve'] = Client(url['citedReferencesRetrieve'], transport=http)
rparams = {'count': 100,
'firstRecord': start_count}
check_time(start_time)
return client['citedReferencesRetrieve'].service.citedReferencesRetrieve(queryId, rparams)
def search(query, SID):
url = client = {}
http = HttpTransport()
opener = urllib2.build_opener(HTTPSudsPreprocessor(SID))
http.urlopener = opener
url['search'] = 'http://search.webofknowledge.com/esti/wokmws/ws/WokSearch?wsdl'
client['search'] = Client(url['search'], transport=http)
qparams = {'databaseId': 'WOS', 'userQuery': query, 'queryLanguage': 'en'}
rparams = {
'count': 100, # 1-100
'firstRecord': 1
}
return client['search'].service.search(qparams, rparams)
def search(fieldtag, searchterm, ver, count, SID):
'''
Makes a search query to the database.
:param fieldtag: fieldtag must be 'PN = ' or 'CD ='
:param searchterm: search term. in this case, the patent number.
:param ver: version 2 or 3. refer to the thomson reuters documentation.
:param count: requested retrieval count.
:param SID: Session ID.
:return: output xml.
'''
http = HttpTransport()
opener = urllib2.build_opener(HTTPSudsPreprocessor(SID))
http.urlopener = opener
client_obj = Client(SEARCH_URL[int(ver - 2)], transport = http, retxml = True)
query = fieldtag + '=' + searchterm
#construct query and retrieve field parameters
qparams = {
'databaseId' : 'DIIDW',
'userQuery' : query,
'queryLanguage' : 'en',
'editions' : [{
'collection' : 'DIIDW',
'edition' : 'CDerwent',
},{
'collection' : 'DIIDW',
'edition' : 'MDerwent',
},{
'collection' : 'DIIDW',
'edition' : 'EDerwent',
}]
}
rparams = {
'count' : count, # 1-500
'firstRecord' : 1,
'sortField' : [{
'name' : 'Relevance',
'sort' : 'D',
}]
}
result = client_obj.service.search(qparams, rparams)
return result
def retrieveById(UID, SID):
url = client = {}
start_time = time.time()
http = HttpTransport()
opener = urllib.request.build_opener(HTTPSudsPreprocessor(SID))
http.urlopener = opener
url['retrieveById'] = 'http://search.webofknowledge.com/esti/wokmws/ws/WokSearch?wsdl'
client['retrieveById'] = Client(url['retrieveById'], transport=http)
databaseId = "WOS"
uid = UID
queryLanguage = "en"
rparams = {'count': 1,
'firstRecord': 1}
check_time(start_time)
return client['retrieveById'].service.retrieveById(databaseId, uid, queryLanguage, rparams)
def retrieveById(UID, SID):
url = client = {}
start_time = time.time()
http = HttpTransport()
opener = urllib.request.build_opener(HTTPSudsPreprocessor(SID)) #build_opener returns OpenerDirector object
http.urlopener = opener #hands OpenerDirector object to http
url['retrieveById'] = 'http://search.webofknowledge.com/esti/wokmws/ws/WokSearch?wsdl'
client['retrieveById'] = Client(url['retrieveById'], transport=http)
databaseId = "WOS" # qparams?!
uid = UID
queryLanguage = "en"
rparams = {'count': 1, # retrieve 1 result instead of 100
'firstRecord': 1}
check_time(start_time) #where does this come from?!
return client['retrieveById'].service.retrieveById(databaseId, uid, queryLanguage, rparams)
def search(query, SID):
url = client = {}
start_time = time.time()
http = HttpTransport()
opener = urllib.request.build_opener(HTTPSudsPreprocessor(SID)) #build_opener returns an OpenerDirector instance
http.urlopener = opener
url['search'] = 'http://search.webofknowledge.com/esti/wokmws/ws/WokSearch?wsdl'
client['search'] = Client(url['search'], transport=http)
qparams = {'databaseId': 'WOS',
'userQuery': query,
'queryLanguage': 'en'} # parameters of our query. there are optional parameters such as time etc
rparams = {'count': 100,
'firstRecord': 1}
check_time(start_time)
return client['search'].service.search(qparams, rparams) # constructs query and returns list ish thing with id as first element, result, etc.
def search(query, SID):
url = client = {}
http = HttpTransport()
opener = urllib2.build_opener(HTTPSudsPreprocessor(SID))
http.urlopener = opener
url['search'] = 'http://search.webofknowledge.com/esti/wokmws/ws/WokSearch?wsdl'
client['search'] = Client(url['search'], transport = http)
qparams = {
'databaseId' : 'WOS',
'userQuery' : query,
'queryLanguage' : 'en'
}
rparams = {
'count' : 100, # 1-100
'firstRecord' : 1
}
return client['search'].service.search(qparams, rparams)
def retrieve(queryId, SID, start_count, namespace):
url = client = {}
start_time = time.time()
http = HttpTransport()
opener = urllib.request.build_opener(HTTPSudsPreprocessor(SID))
http.urlopener = opener
url['retrieve'] = 'http://search.webofknowledge.com/esti/wokmws/ws/WokSearch?wsdl'
client['retrieve'] = Client(url['retrieve'], transport=http)
if namespace == "FullRecord":
rparams = {'count': 100,
'firstRecord': start_count}
else:
rparams = {'count': 100,
'firstRecord': start_count,
'viewField': {'collectionName': 'WOS',
'fieldName': ['pub_info', 'titles']}}
check_time(start_time)
return client['retrieve'].service.retrieve(queryId, rparams)
def retrieve_by_id_lite(input_term, ver, start_record, max_count, SID):
'''
This is a method used for lite services.
:param input_term: input search term.
:param ver: Version 2 or 3. Refer to Thomson Reuters Documentation for details.
:param start_record: starting record point
:param max_count: maximum request count
:param SID: Session ID.
:return: output xml
'''
http = HttpTransport()
opener = urllib2.build_opener(HTTPSudsPreprocessor(SID))
http.urlopener = opener
client_obj = Client(SEARCH_LITE_URL[int(ver - 2)], transport = http, retxml = True)
rparams = {
'count' : max_count, # 1-100
'firstRecord' : start_record,
'sortField' : [{
'name' : 'Relevance',
'sort' : 'D',
}]
}
cited_results = client_obj.service.retrieveById('DIIDW', input_term, 'en', rparams)
return cited_results
def __init__(self,options,config_file=None,session="DWE"):
"""Datastream SOAP Client
>>> ds=Datastream()
"""
_set_debug(logging.WARN,
'suds.resolver',
'suds.metrics',
'suds.xsd.sxbasic',
'suds.xsd.query',
'suds.client',
'suds.wsdl',
'suds.transport.http',
'suds.mx.core',
'suds.umx.typed',
'suds.xsd.schema',
'suds.xsd.sxbase',
'suds.mx.literal')
if config_file is None:
if exists(expanduser('~/.dwe.conf')):
config_file = expanduser('~/.dwe.conf')
os.chmod(config_file,stat.S_IRUSR | stat.S_IWUSR)
else:
config_file = DEFAULT_DSTREAM_CONF_FILE
config_file = expanduser(expandvars(config_file))
self._options = options
if not exists(config_file):
LOGGER.info('no configuration for datastream (%s). using BITS path',config_file)
config_file = join(BITS_ETC,DEFAULT_BITS_CONF_FILE)
self.config_file = config_file
if not exists(self.config_file):
raise IOError, 'Datastream Configuration File not Found %s' % config_file
dstream_info = get_session(config_file,session,
secure=True,
url='http://dataworks.thomson.com/dataworks/enterprise/1.0/webServiceClient.asmx?WSDL',
user=(None,ValueError),
password=(None,ValueError),
realm=''
)
self._auth=dstream_info
t = HttpTransport()
### Proxy if any
#
proxy_info = get_proxy()
if proxy_info:
pip={
'http':proxy_info['proxy'],
'https':proxy_info['proxy'],
}
proxy = urllib2.ProxyHandler(pip)
# opener = urllib2.build_opener(SocksiPyHandler(socks.PROXY_TYPE_SOCKS4, 'localhost', 8080))
opener = urllib2.build_opener(proxy)
urllib2.install_opener(opener)
t.urlopener = opener
LOGGER.debug('proxy info for http: %s',pip['http'])
#
#
###
try:
Client.__init__(self,self._auth['url'],transport=t)
except urllib2.URLError, exc:
LOGGER.error('{}: No connection to {}'.format(self._options.job,self._auth['url']))
raise exc
def initSearchClient(self):
http = HttpTransport()
opener = urllib2.build_opener(HTTPSudsPreprocessor(self.SID))
http.urlopener = opener
self.client['search'] = Client(self.url['search'], transport = http)
def initSearchClient(self):
http = HttpTransport()
opener = urllib2.build_opener(HTTPSudsPreprocessor(self.SID))
http.urlopener = opener
self.client['search'] = Client(self.url['search'], transport=http)
