def get_page_id(v):
pageid = None
#http://it.wikipedia.org/w/api.php?action=query&titles=Abbazia_di_San_Galgano&format=json
#{"query":{"normalized":[{"from":"Abbazia_di_San_Galgano","to":"Abbazia di San Galgano"}],"pages":{"83117":{"pageid":83117,"ns":0,"title":"Abbazia di San Galgano"}}}}
queryurl = UrlBuilder(domain=WPDOMAIN,path="w/api.php",params="action=query")
queryurl.set_attr('titles',v)
queryurl.set_attr('format','json')
query=queryurl.build()
for ntry in range(1,MAXTRIES):
print "Request no. %d - Requesting %s" %(ntry,query)
jsonpage = urllib2.urlopen(query)
try:
jobj = json.load(jsonpage)
pageid = int(jobj['query']['pages'].keys()[0])
break
except Exception as e:
print e
pageid = None
time.sleep(5)
continue
return pageid
def query_api():
queryurl = UrlBuilder(domain=WPDOMAIN,path="w/api.php",params="action=query")
queryurl.set_attr('generator','embeddedin')
queryurl.set_attr('geititle',WPTNAME)
queryurl.set_attr('einamespace','0')
queryurl.set_attr('geilimit','500')
queryurl.set_attr('format','xml')
inlist=list()
while True:
print "Requesting %s" %queryurl.build()
infile = urllib2.urlopen(queryurl.build())
inxml = infile.read()
xml = parseString(inxml)
pagelist=xml.getElementsByTagName("page")
for page in pagelist:
inlist.append(page.getAttribute("title"))
querycont=xml.getElementsByTagName("embeddedin")
if len(querycont) == 0:
break
geicontinue=querycont[0].getAttribute("geicontinue")
queryurl.set_attr("geicontinue",geicontinue)
time.sleep(5)
return inlist
u'FineCostr',
u'Demolizione',
u'Sito',
u'lat',
u'long'
]
"""
Utility functions
"""
_jsonu = UrlBuilder(
domain="json.it.dbpedia.org",
path="annotate/resource/json/it%3A{wp-page}",
params="filter=__type:template"
)
_jsonu.set_attr('flags','-Extractors,Structure,')
_jsonbaseurl=_jsonu.build()
def get_jsonpedia_page(v):
"""
Gets the corrisponding JSONpedia page (only templates)
for Wikipedia article titled 'v'.
Tries MAXTRIES times or returns none.
"""
vsafe = v.replace(' ','_')
jsonurl = _jsonbaseurl.replace('{wp-page}',urllib.quote(vsafe))
for ntry in range(1,MAXTRIES):
try:
print "Request no. %d: requesting: %s" %(ntry,jsonurl)
jsonpage = urllib2.urlopen(jsonurl)
break
