import json
import re
import time
from http.cookies import SimpleCookie
from imageio import imread
from wordcloud import WordCloud
import jieba.analyse
def word_segment(text):
#
jieba.analyse.set_stop_words("./stopwords.txt")
words = jieba.cut(text)
from collections import Counter
result = Counter(words).most_common(20)
print(result)
tags = jieba.analyse.extract_tags(text, topK=20)
print(tags)
if __name__ == '__main__':
text = open("text.txt", encoding="utf-8").read()
word_segment(text)
pass
def word_cloud(texts):
"""
"""
data = " ".join(text for text in texts)
mask_img = imread('./python-logo.png', flatten=True)
wordcloud = WordCloud(
font_path='/Library/Fonts//.ttf',
background_color='white',
mask=mask_img
).generate(data)
plt.imshow(wordcloud)
plt.axis('off')
plt.savefig('./wordcloud.jpg', dpi=600)
def cookie(s):
from http.cookies import SimpleCookie
rawdata = s
cookie = SimpleCookie()
cookie.load(rawdata)
# Even though SimpleCookie is dictionary-like, it internally uses a Morsel object
# which is incompatible with requests. Manually construct a dictionary instead.
cookies = {}
for key, morsel in cookie.items():
cookies[key] = morsel.value
return cookie
def format_duration(duration):
"""
:param duration
"""
total_seconds = int(duration / 1000)
minute = total_seconds // 60
seconds = total_seconds % 60
return f'{minute:02}:{seconds:02}'