def getCollectionDocs(filename):
f = open(filename)
ls = f.readlines()
f.close()
ls = [l.strip() for l in ls]
docsL = eventUtils.getWebpageText(ls)
return docsL
def getCollectionDocs(filename):
f = open(filename)
ls = f.readlines()
f.close()
ls = [l.strip() for l in ls]
docsL = eventUtils.getWebpageText(ls)
return docsL
def getCollectionDocs(self,inputURLs):
#f = open(inputURLs)
#ls = f.readlines()
#f.close()
#ls = [l.strip() for l in ls]
ls = inputURLs
docsL = eventUtils.getWebpageText(ls)
return docsL
def getText(self):
if self.text != '':
return self.text
else:
r = utils.getWebpageText(self.URL)[0]
if r:
self.text = r['text']
self.title = r['title']
return self.text
def getText(self):
if self.text != '':
return self.text
else:
r = utils.getWebpageText(self.URL)[0]
if r:
self.text = r['text']
self.title = r['title']
return self.text
def getCollectionDocs(self, inputURLs):
#f = open(inputURLs)
#ls = f.readlines()
#f.close()
#ls = [l.strip() for l in ls]
ls = inputURLs
docsL = eventUtils.getWebpageText(ls)
return docsL
def buildModel(self,seedURLs,num):
#docs = downloadRawDocs(seedURLs)
td = getWebpageText(seedURLs)
docs = [t['text'] + " "+ t['title'] for t in td if t.has_key('text')]
docs = getTokenizedDocs(docs)
self.n = len(docs)
docs_bow = [self.doc2bow(doc) for doc in docs]
#vocab = self.buildVocab(docs_bow)
self.buildVocabIndex(docs_bow)
selected = self.selectImportantWords_tf(num)
print selected
wordsList = self.index.keys()
selected_words = [wordsList[k[1]] for k in selected]
print selected_words
self.model = (selected,selected_words)
def __init__(self,url,pageId):
self.pageUrl = url
self.pageId = pageId
self.text = ""
self.title = ""
self.outgoingUrls=[]
self.soup = None
res = utils.getWebpageText(url[1])[0]
if res:
self.text = res['text']
self.title = res['title']
self.soup = BeautifulSoup(res['html'])
'''
try:
headers = { 'User-Agent' : 'Mozilla/5.0 (Windows NT 5.1; rv:10.0.1) Gecko/20100101 Firefox/10.0.1'}
req = urllib2.Request(url[1], None, headers)
page = urllib2.urlopen(req).read()
except urllib2.HTTPError:
print sys.exc_info()[0]
self.text = "Error"
return
except urllib2.URLError:
print sys.exc_info()[0]
self.text = "Error"
return
except ValueError:
print sys.exc_info()[0]
self.text = "Error"
return
except :
print sys.exc_info()[0]
self.text = "Error"
return
'''
'''
def buildProbEventModel(self,urlsList,topK):
docsList = eventUtils.getWebpageText(urlsList) #self.getCollectionDocs(urlsList)
t = ''
#docsTotalFreqs=[]
docsEntities=[]
docsEntitiesFreq = []
entitiesProb = {}
# Convert each doc to tokens, locations, dates lists and their corresponding frequency distributions
# Also produces the total frequency for each document of each list (tokens, locations, and dates)
for doc in docsList:
if doc.has_key('text'):
t = doc['text']
if doc.has_key('title'):
t =doc['title']+ " "+t
if t:
#print 'Reading ' + t[:100]
ents = eventUtils.getEntities(t)[0]
docEnt = {}
docEnt['LOCATION']={}
if 'LOCATION' in ents:
docEnt['LOCATION'] = ents['LOCATION']
docEnt['DATE']={}
if 'DATE' in ents:
docEnt['DATE'] = ents['DATE']
toks = eventUtils.getTokens(t)
docEnt['Topic'] = toks
docsEntities.append(docEnt)
docEntFreq = {}
#docTotals = {}
for k in docEnt:
docEntFreq[k] = eventUtils.getFreq(docEnt[k])
#totalFreq = sum([v for _,v in docEntFreq[k].items()])
#docTotals[k] = totalFreq
docsEntitiesFreq.append(docEntFreq)
#docsTotalFreqs.append(docTotals)
# Collection-level frequency for each entity(tokens, locations, dates)
#Calculating prob for each item in each entity lists (tokens, locations, and dates) as
# freq of item in all docs / total freq of all terms in that list
entitiesProb['LOCATION']={}
entitiesProb['DATE']={}
entitiesProb['Topic']={}
for docEntFreq in docsEntitiesFreq:
for entity in docEntFreq:
for val in docEntFreq[entity]:
if val in entitiesProb[entity]:
entitiesProb[entity][val] += docEntFreq[entity][val]
else:
entitiesProb[entity][val] = docEntFreq[entity][val]
for ent in entitiesProb:
allvalsFreq = sum([v for _,v in entitiesProb[ent].items()])
for k in entitiesProb[ent]:
#entitiesProb[ent][k] = (1.0 + (entitiesProb[ent][k] *1.0)) / (docsTotalFreqs[ent] + allDocsTotal[ent])
entitiesProb[ent][k] = (1.0 + (entitiesProb[ent][k] *1.0)) / (len(entitiesProb[ent]) + allvalsFreq)
#self.probEvtModel = entitiesProb
mle = self.getMLEEventEntities(entitiesProb,10)
for k in mle:
print k, mle[k]
self.probEvtModel = {}
for k in mle:
self.probEvtModel[k] = dict(mle[k])#entitiesProb[k][:topK]
self.eDisDic = self.probEvtModel['Topic']
locToks = self.probEvtModel['LOCATION'].keys()
locToks = eventUtils.getStemmedWords(locToks)
self.locDic = dict(zip(locToks,self.probEvtModel['LOCATION'].values()))
dToks = self.probEvtModel['DATE'].keys()
dToks = eventUtils.getStemmedWords(dToks)
self.dDic = dict(zip(dToks,self.probEvtModel['DATE'].values()))
return docsEntities, entitiesProb
f.close()
print "file saved"
#warcFile = warc.file.name
#print warcFile
#texts = utils.expandWarcFile(warcFile)
texts = utils.expandWarcFile(warcFile)
else:
texts = utils.expandWarcFile(warcFile)
urls = form.getvalue('urls')
#if not urls:
# urls = 'http://www.nbcnews.com/storyline/ebola-virus-outbreak/why-its-not-enough-just-eradicate-ebola-n243891\nhttp://www.npr.org/blogs/thetwo-way/2014/11/09/362770821/maine-nurse-to-move-out-of-state-following-ebola-quarantine-row'
if urls:
webpagesURLs = urls.split('\n')
webpagesText = utils.getWebpageText(webpagesURLs)
texts = [t['text'] for t in webpagesText if t.has_key('text') and len(t['text'])>0]
print texts
#Get LDA Topics
ldaTopics = utils.getLDATopics(texts)
#Get Frequent Tokens
sortedTokensFreqs = utils.getFreqTokens(texts)
#Get Indicative tokens
sortedToksTFDF = utils.getIndicativeWords(texts)
'''
filteredToksTFDF = []
toks = " ".join([])
from eventUtils import getWebpageText
f = open('seedsURLs_z_543-noTweets.txt','r')
urls = f.readlines()
f.close()
urls = [u.strip() for u in urls]
texts = getWebpageText(urls)
i = 0
for p in texts:
if p.has_key('text'):
ftext = open("webpages/"+str(i) + ".txt", "w")
ftext.write(p['text'].encode("utf-8"))
ftext.close()
i+=1