You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

83 lines
3.0 KiB
Python

# from __future__ import division
from nltk import sent_tokenize, word_tokenize, pos_tag
from nltk.probability import FreqDist
from nltk.corpus import stopwords
import nltk
import codecs
import base64
nltk.download('stopwords')
with open('treaty_file/russia-estonia.txt', 'r') as russia_file:
russia_text = russia_file.read()
russia_text_list = russia_text.split("\n\n")
t_default_stopwords = set(stopwords.words('english'))
t_custom_stopwords = set(codecs.open('t_stopwords.txt', 'r').read().splitlines())
t_all_stopwords = t_default_stopwords | t_custom_stopwords
print('''<!DOCTYPE>
<html>
<head>
<script src="https://code.jquery.com/jquery-3.5.0.min.js"></script>
<link rel="stylesheet" href="estonia.css">
<script src="highlight.js"></script>
<meta charset="utf-8">
<title></title>
</head>
<body>''')
#t_wrapper (second wrapper)
print('<div class="t_wrapper"><div class="t_intro">')
img_url = base64.b64encode(open('img/tartu.jpeg', 'rb').read()).decode('utf-8')
t_image = '<div class="t_img">Peace Treaty of Tartu, Estonia<br><img class="t_image" src="data:img/tartu.jpeg;base64,{}"></div>'.format(img_url)
print(t_image)
#t_info box
print('<div class ="t_info">')
t_infotext = [('Name of Treaty', 'Peace Treaty of Tartu'), ('Country of Origin', 'Russia'), ('Signed', 'February 2, 1920'), ('Location', 'Tartu, Estonia'), ('Word Counts', '2,104'), ('Type', 'bilateral peace treaty'), ('Original Source', '<a href="https://en.wikipedia.org/wiki/Treaty_of_Tartu_(Russian-Estonian)">link</a>'), ('Description', 'The Tartu Peace Treaty or Treaty of Tartu is a peace treaty between Estonia and Russian Soviet Federative Socialist Republic signed on 2 February 1920, ending the Estonian War of Independence.')]
for t_title, t_info in t_infotext:
print('<div class="t_info-{0}"><div class="info_t_title" ><b>{0}</b></div><div class="t_info_content">{1}</div></div><br>'.format(t_title, t_info))
print('</div></div>')
#Treaty text
print('<div class="t_paragraph">')
for t_paragraph in russia_text_list:
t_tokenized = word_tokenize(t_paragraph)
t_tagged = pos_tag(t_tokenized)
print('<p>')
for t_word, t_pos in t_tagged:
print('<span class="{0} {1}">{2}</span>'.format(t_pos.replace('.', 'dot').replace(',', 'comma').replace('(', 'marks').replace(')', 'marks').replace(':', 'marks').replace(';', 'marks'), t_word.replace('.', 'dot').replace(',', 'comma').replace('(', 'marks').replace(')', 'marks').replace(':', 'marks').replace(';', 'marks').lower(), t_word))
print('</p>')
print('</div>')
#treaty colonial top words list
print('<div class="t_top_words"><div class="t_top_words_title"><b>Frequent words</b></div>')
t_tokens_without_stopwords = nltk.FreqDist(words.lower() for words in t_tokenized if words.lower() not in t_all_stopwords)
t_frequency_word = FreqDist(t_tokens_without_stopwords)
t_top_words = t_tokens_without_stopwords.most_common(20)
for t_chosen_words, t_frequency in t_top_words:
print('<div class="t_chosen_words" >&nbsp;{}&nbsp;({}) </div>'.format(t_chosen_words, t_frequency))
print('</div></div></div>')
print('</div></div>')
print('''</body></html>''')