reading corpus

corpus_read.py

import sys
import time
import glob
import codecs
import matplotlib.pyplot as plt
import requests

# Books present
books = sorted(glob.glob("data/harrypotter/*.txt"))

print "Available Books: \n"
for i in books:
    print i.split("/")[2].split("_")[0]

# Read data from all books to single corpus variable
temp = ""
t = ""
chars = []
book_raw = []
for book in books:
    with codecs.open(book, "rb", "utf-8") as infile:
        temp = infile.read()
        book_raw.append(temp)

        
# Available Books: 

# Book 1 - The Philosopher's Stone
# Book 2 - The Chamber of Secrets
# Book 3 - The Prisoner of Azkaban
# Book 4 - The Goblet of Fire
# Book 5 - The Order of the Phoenix
# Book 6 - The Half Blood Prince
# Book 7 - The Deathly Hallows