You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
27 lines
2.3 KiB
27 lines
2.3 KiB
import sys, os
|
|
from nltk import word_tokenize
|
|
from nltk import everygrams
|
|
from nltk import FreqDist
|
|
|
|
stopws = ['i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you', "you're", "you've", "you'll", "you'd", 'your', 'yours', 'yourself', 'yourselves', 'he', 'him', 'his', 'himself', 'she', "she's", 'her', 'hers', 'herself', 'it', "it's", 'its', 'itself', 'they', 'them', 'their', 'theirs', 'themselves', 'what', 'which', 'who', 'whom', 'this', 'that', "that'll", 'these', 'those', 'am', 'is', 'are', 'was', 'were', 'be', 'been', 'being', 'have', 'has', 'had', 'having', 'do', 'does', 'did', 'doing', 'a', 'an', 'the', 'and', 'but', 'if', 'or', 'because', 'as', 'until', 'while', 'of', 'at', 'by', 'for', 'with', 'about', 'against', 'between', 'into', 'through', 'during', 'before', 'after', 'above', 'below', 'to', 'from', 'up', 'down', 'in', 'out', 'on', 'off', 'over', 'under', 'again', 'further', 'then', 'once', 'here', 'there', 'when', 'where', 'why', 'how', 'all', 'any', 'both', 'each', 'few', 'more', 'most', 'other', 'some', 'such', 'no', 'nor', 'not', 'only', 'own', 'same', 'so', 'than', 'too', 'very', 's', 't', 'can', 'will', 'just', 'don', "don't", 'should', "should've", 'now', 'd', 'll', 'm', 'o', 're', 've', 'y', 'ain', 'aren', "aren't", 'couldn', "couldn't", 'didn', "didn't", 'doesn', "doesn't", 'hadn', "hadn't", 'hasn', "hasn't", 'haven', "haven't", 'isn', "isn't", 'ma', 'mightn', "mightn't", 'mustn', "mustn't", 'needn', "needn't", 'shan', "shan't", 'shouldn', "shouldn't", 'wasn', "wasn't", 'weren', "weren't", 'won', "won't", 'wouldn', "wouldn't", ",", ".", "?","!",":","(",")",">","<","@","#","``","/","–","''","‘","-","’", "DOCTYPE", "html", "!"]
|
|
|
|
|
|
path = "static/files/"
|
|
for path, subdirs, files in os.walk(path):
|
|
for name in files:
|
|
if name.endswith('html'):
|
|
file = os.path.join(path, name)
|
|
total = open("allhtml.txt", "a")
|
|
with open(file) as f:
|
|
content = f.read()
|
|
total.write(content)
|
|
total.close()
|
|
|
|
with open('allhtml.txt') as f:
|
|
content = f.read()
|
|
tokens = word_tokenize(content)
|
|
tokens = [token for token in tokens if token not in stopws]
|
|
freq_file=FreqDist(tokens)
|
|
listofwords = open("mostcommon.txt", "w+")
|
|
listofwords.write(str(freq_file.most_common(50)))
|
|
listofwords.close()
|
|
|