def googleSearch(title):
'''
It is the function of the application that make the request at google WS using
getting the first url of response.
@param title: the title of the article to serach for
@return: the first url
'''
_query=title
# create SOAP proxy object
google = SOAPProxy(_url, _namespace)
# call search method over SOAP proxy
results = google.doGoogleSearch( _license_key, _query,
_start, _maxResults,
_filter, _restrict,
_safeSearch, _lang_restrict, '', '' )
# display results
# print 'google search for " ' + _query + ' "\n'
# print 'estimated result count: ' + str(results.estimatedTotalResultsCount)
# print ' search time: ' + str(results.searchTime) + '\n'
# print 'results ' + str(_start + 1) + ' - ' + str(_start + _maxResults) +':\n'
numresults = len(results.resultElements)
if numresults:
url = results.resultElements[0].URL
else:
url= "#"
return url
def googleSearch(title):
'''
It is the function of the application that make the request at google WS using
getting the first url of response.
@param title: the title of the article to serach for
@return: the first url
'''
# create SOAP proxy object
google = SOAPProxy(_url, _namespace)
_query= google.doSpellingSuggestion( _license_key, title )
if _query == None:
_query=title
# call search method over SOAP proxy
results = google.doGoogleSearch( _license_key, _query,
_start, _maxResults,
_filter, _restrict,
_safeSearch, _lang_restrict, '', '' )
# display results
# print 'google search for " ' + _query + ' "\n'
# print 'estimated result count: ' + str(results.estimatedTotalResultsCount)
# print ' search time: ' + str(results.searchTime) + '\n'
# print 'results ' + str(_start + 1) + ' - ' + str(_start + _maxResults) +':\n'
numresults = len(results.resultElements)
if numresults:
for i in range(numresults):
url = results.resultElements[i].URL
r = re.compile("http://(.*)\.pdf",re.IGNORECASE)
if (r.match(url)):
url = r.match(url).group()
type = "pdf"
return (url,type,_query)
else:
r = re.compile("http://citeseer.ist.psu.edu/")
if(r.match(url)):
type = "citeseer"
return (url,type,_query)
else:
r = re.compile("http://portal.acm.org/")
if(r.match(url)):
type = "acm"
return (url,type,_query)
else:
r = re.compile("http://doi.ieeecomputersociety/")
if(r.match(url)):
type = "doi"
return (url,type,_query)
else:
pass
type = "default"
return (url,type,_query)
else:
url= "#"
type = None
return (url,type,_query)
