Spring23SeniorProjectII/freq.py at main · mmmoore3/Spring23SeniorProjectII · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
import nltk
nltk.download('punkt')
s = input('Enter the file name which contains a sentence: ')
file1 = open(s)
sentence = file1.read()
file1.close()
p = input('Enter the file name which contains a paragraph: ')
file2 = open(p)
paragraph = file2.read()
file2.close()

import urllib.request
from bs4 import BeautifulSoup
url = input('Enter URL of Webpage: ')
print( '\n' )
url_request = urllib.request.Request(url)
url_response = urllib.request.urlopen(url)
webpage_data = url_response.read()
soup = BeautifulSoup(webpage_data, 'html.parser')

print('<------------------------------------------Initial Contents of Sentence are-------------------------------------------> \n')
print(sentence)
print( '\n' )

print('<------------------------------------------Initial Contents of Paragraph are-------------------------------------------> \n')
print(paragraph)
print( '\n' )

print('<------------------------------------------Initial Contents of Webpage are---------------------------------------------> \n')
print(soup)
print( '\n' )


web_page_paragraph_contents=soup('p')
web_page_data = ''
for para in web_page_paragraph_contents:
	web_page_data = web_page_data + str(para.text)

print('<------------------------------------------Contents enclosed between the paragraph tags in the web page are---------------------------------------------> \n')
print(web_page_data)
print('\n')

from nltk.tokenize import word_tokenize
import re
sentence_without_punctuations = re.sub(r'[^\w\s]', '', sentence)
paragraph_without_punctuations = re.sub(r'[^\w\s]', '', paragraph)
web_page_paragraphs_without_punctuations = re.sub(r'[^\w\s]', '', web_page_data)
print('<------------------------------------------Contents of sentence after removing punctuations---------------------------------------------> \n')
print(sentence_without_punctuations)
print('\n')
print('<------------------------------------------Contents of paragraph after removing punctuations---------------------------------------------> \n')
print(paragraph_without_punctuations)
print('\n')
print('<------------------------------------------Contents of webpage after removing punctuations-----------------------------------------------> \n')
print(web_page_paragraphs_without_punctuations)
print('\n')

sentence_after_tokenizing = word_tokenize(sentence_without_punctuations)
paragraph_after_tokenizing = word_tokenize(paragraph_without_punctuations)
webpage_after_tokenizing = word_tokenize(web_page_paragraphs_without_punctuations)
print('<------------------------------------------Contents of sentence after tokenizing----------------------------------------------> \n')
print(sentence_after_tokenizing)
print( '\n' )
print('<------------------ ------------------------Contents of paragraph after tokenizing---------------------------------------------> \n')
print(paragraph_after_tokenizing)
print( '\n' )
print('<------------------------------------------Contents of webpage after tokenizing-----------------------------------------------> \n')
print(webpage_after_tokenizing)
print( '\n' )

from nltk.corpus import stopwords
nltk.download('stopwords')
nltk_stop_words = stopwords.words('english')
sentence_without_stopwords = [i for i in sentence_after_tokenizing if not i.lower() in nltk_stop_words]
paragraph_without_stopwords = [j for j in paragraph_after_tokenizing if not j.lower() in nltk_stop_words]
webpage_without_stopwords = [k for k in webpage_after_tokenizing if not k.lower() in nltk_stop_words]
print('<------------------------------------------Contents of sentence after removing stopwords---------------------------------------------> \n')
print(sentence_without_stopwords)
print( '\n' )
print('<------------------------------------------Contents of paragraph after removing stopwords---------------------------------------------> \n')
print(paragraph_without_stopwords)
print( '\n' )
print('<------------------------------------------Contents of webpage after removing stopwords-----------------------------------------------> \n')
print(webpage_without_stopwords)
print( '\n' )

from nltk.stem.porter import PorterStemmer
stemmer = PorterStemmer()
sentence_after_stemming = []
paragraph_after_stemming = []
webpage_after_stemming = [] #creating empty lists for storing stemmed words
for word in sentence_without_stopwords:
	sentence_after_stemming.append(stemmer.stem(word))
for word in paragraph_without_stopwords:
	paragraph_after_stemming.append(stemmer.stem(word))
for word in webpage_without_stopwords:
	webpage_after_stemming.append(stemmer.stem(word))
print('<------------------------------------------Contents of sentence after doing stemming---------------------------------------------> \n')
print(sentence_after_stemming)
print( '\n' )
print('<------------------------------------------Contents of paragraph after doing stemming---------------------------------------------> \n')
print(paragraph_after_stemming)
print( '\n' )
print('<------------------------------------------Contents of webpage after doing stemming-----------------------------------------------> \n')
print(webpage_after_stemming)
print( '\n' )


from textblob import TextBlob
final_words_sentence=[]
final_words_paragraph=[]
final_words_webpage=[]

for i in range(len(sentence_after_stemming)):
	final_words_sentence.append(0)
	present_word=sentence_after_stemming[i]
	b=TextBlob(sentence_after_stemming[i])
	if str(b.correct()).lower() in nltk_stop_words:
		final_words_sentence[i]=present_word
	else:
		final_words_sentence[i]=str(b.correct())
print('<------------------------------------------Contents of sentence after correcting misspelled words-----------------------------------------------> \n')
print(final_words_sentence)
print('\n')

for i in range(len(paragraph_after_stemming)):
	final_words_paragraph.append(0)
	present_word = paragraph_after_stemming[i]
	b = TextBlob(paragraph_after_stemming[i])
	if str(b.correct()).lower() in nltk_stop_words:
		final_words_paragraph[i] = present_word
	else:
		final_words_paragraph[i] = str(b.correct())
print('<------------------------------------------Contents of paragraph after correcting misspelled words-----------------------------------------------> \n')
print(final_words_paragraph)
print('\n')

for i in range(len(webpage_after_stemming)):
	final_words_webpage.append(0)
	present_word = webpage_after_stemming[i]
	b = TextBlob(webpage_after_stemming[i])
	if str(b.correct()).lower() in nltk_stop_words:
		final_words_webpage[i] = present_word
	else:
		final_words_webpage[i] = str(b.correct())
print('<------------------------------------------Contents of webpage after correcting misspelled words-----------------------------------------------> \n')
print(final_words_webpage)
print('\n')

from collections import Counter
sentence_count = Counter(final_words_sentence)
paragraph_count = Counter(final_words_paragraph)
webpage_count = Counter(final_words_webpage)
print('<------------------------------------------Frequency of words in sentence ---------------------------------------------> \n')
print(sentence_count)
print( '\n' )
print('<------------------------------------------Frequency of words in paragraph ---------------------------------------------> \n')
print(paragraph_count)
print( '\n' )
print('<------------------------------------------Frequency of words in webpage -----------------------------------------------> \n')
print(webpage_count)