tomd.py

import html2text
import csv
import unicodedata
#from unidecode import unidecode
#print unidecode(u"\u5317\u4EB0")
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
h = html2text.HTML2Text()
# Ignore converting links from HTML
#h.ignore_links = True
#print h.handle("<p>Hello, <a href='http://earth.google.com/'>world</a>!")

with open("toc.csv", "rb") as csvfile:
    reader = csv.reader(csvfile, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
    for row in reader:
        # print(row)
        filename = "index.php?id="+row[0]
        print(filename)
        with open (filename, "r") as file:
            content = file.read()
            #print(h.handle(content))
            markdown_filename = row[1].replace(' ', '_').replace('!', '').replace(':', '').replace('\'', '')
            print(markdown_filename)