html2csv.py

#!/usr/bin/python

from BeautifulSoup import BeautifulSoup
import feedparser, glob, codecs, csv, sys
from xml.dom.minidom import parse, parseString

i = 8888

for htmlFile in glob.glob('*.html'):
    #print htmlFile
    soup = BeautifulSoup (codecs.open(htmlFile,"rb").read(), convertEntities=BeautifulSoup.HTML_ENTITIES)
    for question in soup.findAll("div", { "class" : "question" }):
        i += 1
        reponse = question.parent.findNextSibling ('div', {'class': 'bloc_reponse'}).find ("div", { "class" : "reponse" }).renderContents().replace('\\n', "\n")
        print repr(i)+',"'+htmlFile+'","'+question.renderContents().strip().replace ('"', '""')+'","'+reponse.strip().replace('"', '""')+'"'