# html-to-kwic-2.py
import dh
# create dictionary of n-grams
n = 7
url = 'file:///C:/Documents%20and%20Settings/HP_Administrator/Desktop/ProgrammingHistorian/dcb-34298.html'
# url = 'http://www.biographi.ca/EN/ShowBioPrintable.asp?BioId=34298'
text = dh.webPageToText(url)
fullwordlist = ('# ' * (n//2)).split()
fullwordlist += dh.stripNonAlphaNum(text)
fullwordlist += ('# ' * (n//2)).split()
ngrams = dh.getNGrams(fullwordlist, n)
worddict = dh.nGramsToKWICDict(ngrams)
# output KWIC and wrap with HTML
target = 'iroquois'
outstr = '<pre>'
if worddict.has_key(target):
for k in worddict[target]:
linkname = dh.prettyPrintKWIC(k)
keywords = dh.removeStopwords(k, dh.stopwords)
outstr += dh.keywordListToGoogleSearchLink(keywords, linkname)
# outstr += '<br />'
else:
outstr += 'Keyword not found in source'
outstr += '</pre>'
dh.wrapStringInHTML('html-to-kwic-2', url, outstr)
# 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 />'
outstring += '</pre></p>'
# open in Firefox
dh.wrapStringInHTML("html-to-tag-cloud-kwic", url, outstring)#!/usr/bin/env python
# html-to-kwic.py
import dh
# create dictionary of n-grams
n = 7
# NB Local copy; clean this up!
url = 'file:///C:/Documents%20and%20Settings/HP_Administrator/Desktop/ProgrammingHistorian/dcb-34298.html'
# url = 'http://www.biographi.ca/EN/ShowBioPrintable.asp?BioId=34298'
text = dh.webPageToText(url)
fullwordlist = ('# ' * (n//2)).split()
fullwordlist += dh.stripNonAlphaNum(text)
fullwordlist += ('# ' * (n//2)).split()
ngrams = dh.getNGrams(fullwordlist, n)
worddict = dh.nGramsToKWICDict(ngrams)
# output KWIC and wrap with HTML
target = 'dictionary'
outstr = '<pre>'
if worddict.has_key(target):
for k in worddict[target]:
outstr += dh.prettyPrintKWIC(k)
outstr += '<br />'
else:
outstr += 'Keyword not found in source'
outstr += '</pre>'
dh.wrapStringInHTML('html-to-kwic', url, outstr)
