import re # filein = open("../txt/2013-TARIC-nomenclature_index.txt","r") # read from an etherpad import urllib filein = urllib.urlopen('http://10.10.161.238/ether/p/encyclopedia/export/txt') with open("output/tabs-encyclopedia.html","w+") as fileout: fileout.write('
') for line in filein: line = re.sub(r"\s{8}", "\t", line) print line m = re.search(r"^\t*", line) # for tabs # m = re.search(r"\s{8}", line) # for 8 spaces as 1 tab if m: tab = len(m.group(0)) + 1 strtab = str(tab) line = line.replace("\t","") # print line, tab fontsize = 55/tab fontsize = str(fontsize) fontsize = str(12); # uncomment to set fixed fontsize fileout.write('
'+line+'
\n') fileout.write("""
""") fileout.close()