import string
def printHTMLfile(body,title):
''' create a standard html page with titles, header etc.
and add the body (an html box) to that page. File created is title+'.html'
'''
fd = open(title+'.html','w')
theStr="""
"""+title+"""
"""+title+'
'+'\n'+body+'\n'+"""
Last modified: Fri Oct 10 10:09:41 EDT 2008
"""
fd.write(theStr)
fd.close()
def makeHTMLbox(body):
''' make and HTML box that has all the words in it
'''
boxStr = """%s
"""
return boxStr % (body)
def makeHTMLword(word,cnt,high,low):
''' make a word with a font size to be placed in the box. Font size is scaled
between htmlBig and htmlLittle (to be user set). high and low represent the high
and low counts in the document. cnt is the cnt of the word
'''
htmlBig = 96
htmlLittle = 14
ratio = (cnt-low)/float(high-low)
fontsize = htmlBig*ratio + (1-ratio)*htmlLittle
fontsize = int(fontsize)
wordStr = '%s'
return wordStr % (str(fontsize), word)
def cleanStr(aStr):
aStr = aStr.strip()
aStr = aStr.lower()
for char in string.punctuation:
if char in aStr:
aStr = aStr.replace(char,'')
return aStr
def setDictionary(fields,bDict,iDict,pDict,curDict):
if fields[0]=='IFILL:':
fields.remove('IFILL:')
return iDict
elif fields[0]=='PALIN:':
fields.remove('PALIN:')
return pDict
elif fields[0]=='BIDEN:':
fields.remove('BIDEN:')
return bDict
else:
return curDict
def extractTopX(theDict,num):
lst = [(value,key) for key,value in theDict.items()]
lst.sort()
lst = lst[-num:]
lst = [(word,cnt) for cnt,word in lst]
return lst
fd = open('stop2.txt')
stopList = [line.strip() for line in fd]
fd.close()
palinDict={}
bidenDict={}
ifillDict={}
presentDict={}
fd = open('debate.txt')
for line in fd:
fields = line.strip().split()
if not fields:
continue
presentDict = setDictionary(fields,bidenDict,ifillDict,palinDict,presentDict)
for f in fields:
f = cleanStr(f)
if f not in stopList and f:
try:
presentDict[f]+=1
except KeyError:
presentDict[f]=1
l=extractTopX(bidenDict,40)
least = l[0][1]
most =l[-1][1]
l.sort()
body = [makeHTMLword(w,cnt,most,least) for w,cnt in l]
body=' '.join(body)
body = makeHTMLbox(body)
printHTMLfile(body,'biden')
l=extractTopX(palinDict,40)
least = l[0][1]
most =l[-1][1]
l.sort()
body = [makeHTMLword(w,cnt,most,least) for w,cnt in l]
body=' '.join(body)
body = makeHTMLbox(body)
printHTMLfile(body,'palin')
fd.close()