This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: UTF-8 -*- | |
import sqlite3 | |
from sqlite3 import Error | |
import urllib | |
import HTMLParser | |
import html2text | |
import re | |
from os import listdir | |
from os.path import isfile, join | |
from collections import Counter |