paddinglist = ('# ' * (n//2))
fullwordlist[:0] = paddinglist
fullwordlist.extend(paddinglist)
ngrams = dh.getNGrams(fullwordlist, n)
worddict = dh.nGramsToKWICDict(ngrams)
# create tag cloud
cloudsize = 40
maxfreq = sorteddict[0][0]
minfreq = sorteddict[cloudsize][0]
freqrange = maxfreq - minfreq
tempstring = ''
resorteddict = dh.reSortFreqDictAlpha(sorteddict[:cloudsize])
for k in resorteddict:
kfreq = k[0]
klabel = dh.undecoratedHyperlink('#'+k[1], k[1])
scalingfactor = (kfreq - minfreq) / float(freqrange)
tempstring += dh.scaledFontSizeSpan(klabel, scalingfactor)
outstring = dh.defaultCSSDiv(tempstring) + '<br />'
# create KWIC listings for each item
for k in resorteddict:
klabel = k[1]
tempstring = ''
tempstring += '<a name=\"%s\">%s</a> ' % (klabel, klabel)
tempstring += dh.undecoratedHyperlink('#', '[back]')
outstring += dh.defaultCSSDiv(tempstring, opt='font-size : 24px;')
outstring += '<p><pre>'
for t in worddict[klabel]:
outstring += dh.prettyPrintKWIC(t)
outstring += '<br />'
biodict[bioid] = dh.normalizeFrenchAccents(bioname)
# make directory to store downloaded pages if one doesn't exist
if os.path.exists('iroquois') == 0: os.mkdir('iroquois')
# download a local copy of each bio
urlprefix = 'http://www.biographi.ca/EN/ShowBioPrintable.asp?BioId='
for b in biodict:
print "Processing bioid: " + str(b)
url = urlprefix + str(b)
outfile = 'iroquois/dcb-' + str(b) + '.html'
if os.path.isfile(outfile) == 0:
response = urllib2.urlopen(url)
html = response.read()
f = open(outfile, 'w')
f.write(html)
f.close
time.sleep(2)
else:
print "File already downloaded"
sys.stdout.flush()
# create a page of links to local copies
outstring = ''
for b in biodict:
outfile = 'dcb-' + str(b) + '.html'
outstring += dh.undecoratedHyperlink('iroquois/'+outfile, str(b))
outstring += ' ' * 4
outstring += biodict[b]
outstring += "<br />"
dh.wrapStringInHTML("get-iroquois-bios", searchresultfile, outstring)