def getWikiOutlinks(sourcewiki, html, outlinksDict):
if( len(html) == 0 ):
return outlinksDict
try:
soup = BeautifulSoup(html, 'html.parser')
anchorTags = soup.find_all('a')
for tag in anchorTags:
if( tag.has_attr('href') == False ):
continue
if( tag['href'].find('wikipedia') == -1 ):
continue
link = tag['href']
link = unquote(link)
outlinksDict.setdefault(link, 0)
outlinksDict[link] += 1
except:
genericErrorInfo()
return outlinksDict
def searchKwordWindowsOpt(text, k, left, right, skipBothFlag=False):
tokens = []
try:
tokens = getTokenizer(text)
except:
genericErrorInfo()
counts = {'left': 0, 'both': 0}
kWordWindows = []
for i in range(len(tokens)):
if (i % k == 0):
kWordWindows.append([])
kWordWindows[-1].append(tokens[i])
counts['left'] = len(kWordWindows)
if (skipBothFlag == False):
for win in kWordWindows:
if (left in win and right in win):
counts['both'] += 1
return counts
def getHTMLPaths():
pathnames = []
try:
infile = open('wiki-small-html-files.txt', 'r')
pathnames = infile.readlines()
infile.close()
except:
genericErrorInfo()
return pathnames
def getKwordWindowsOpt(text, k):
tokens = []
try:
tokens = getTokenizer(text)
except:
genericErrorInfo()
kWordWindows = []
for i in range(len(tokens)):
if (i % k == 0):
kWordWindows.append([])
kWordWindows[-1].append(tokens[i])
return kWordWindows
