• Research background
• Related principles
• design idea
• Implementation process
• Result display
• Summarize your feelings
• source code

https://www.24en.com/novel/classics/jane-eyre/2002.html

from bs4 import BeautifulSoup  # Web page parsing
import urllib.request, urllib.error  # Specify URL
import jieba    # participle
from matplotlib import pyplot as plt  # Visualization of drawing data
from wordcloud import WordCloud     # Word cloud
from PIL import Image       # Image processing
import numpy as np      # Matrix operation
import xlwt  # EXCEL processing

#Get the number of words with length and more letters
def get_count_len(items, length: int):
    count_len_more = 0
    count_text = 0 # Number of words in this list
    for word, count in items:
        count_text += count
        if len(word) >= length:
            count_len_more += count
    return  count_len_more, count_text

def sort_dir(dictionary):
    items = list(dictionary.items())
    items.sort(key=lambda x: x[1],
               reverse=True) 
    return items

def make_dictionary(text_en):
    words = text_en.split()
    dictionary = {}
    for word in words:
        dictionary[word] = dictionary.get(word, 0) + 1 
    return dictionary

 1 # -*- coding = UTF-8 -*-
 2 # @Time : 2022/01/03 13:39
 3 # @Author : butupi
 4 # @File : to_wordcloud.py
 5 # @Software : PyCharm
 6 
 7 import jieba    # participle
 8 from matplotlib import pyplot as plt  # Visualization of drawing data
 9 from wordcloud import WordCloud     # Word cloud
10 from PIL import Image       # Image processing
11 import numpy as np      # Matrix operation
12 
13 
14 #---------------------------------
15 #Get Chinese and English articles
16 def get_text(path_en, path_zh):
17     text_en = ""
18     text_zh = ""
19     with open(path_en, "r", encoding="utf-8") as f:
20         for line in f.readlines():
21             text_en += line.rstrip("\n")
22     # print(text_en)
23     with open(path_zh, "r", encoding="utf-8") as f:
24         for line in f.readlines():
25             text_zh += line.rstrip("\n")
26     return text_en, text_zh
27 
28 #---------------------------------
29 
30 #jieba participle
31 def cut_text(text):
32     cut = jieba.cut(text)
33     cut_words = ' '.join(cut)
34     # print(type(cut_words))
35     # print(len(cut_words))
36     return cut_words
37 
38 #---------------------------------
39 #Get a list of stop words
40 def get_stop_words(filepath):
41     stop_words = [line.strip() for line in open(filepath, 'r', encoding='utf-8').readlines()]
42     return stop_words
43 
44 #Remove stop words
45 def move_stop_words(text, path):
46     stop_words = get_stop_words(path)
47     out_str = ''
48     for word in text:
49         if word not in stop_words:
50             if word != '\t' and '\n':
51                 out_str += word
52     return out_str
53 #-----------------------------------
54 
55 #Generate word cloud
56 def get_word_cloud(source_path, dest_path, out_str):
57     #Get background picture
58     img = Image.open(source_path)
59     #Convert pictures to arrays
60     img_array = np.array(img)
61     #Word cloud attribute
62     wc = WordCloud(
63         background_color='white',
64         mask=img_array,
65         font_path="msyh.ttc"       # font
66     ).generate_from_text(out_str)
67 
68     #Draw picture
69     fig = plt.figure(1)
70     plt.imshow(wc)      # Display as word cloud
71     plt.axis('off')     # Do not display coordinates
72     #plt.show()  # Displays the generated word cloud picture
73     #Export to file
74     plt.savefig(dest_path, dpi=500)
75 
76 #-------------------------------
77 def main():
78     #get_text
79     text_en, text_zh = get_text("wbfx.txt", "Jane Eyre.txt")
80 
81     #jieba
82     cut_words = cut_text(text_zh)
83 
84     #move_stop_words
85     out_str = move_stop_words(cut_words, 'stop_word.txt')
86 
87     #wordcloud
88     get_word_cloud('zh-tree.jpg', 'zh-tree-out.jpg', out_str)
89     get_word_cloud('en-bj.png', 'en-bj-out.png', text_en)
90 
91 
92 #---------------------------------
93 if __name__ == '__main__':
94     main()

 1 # -*- coding = utf-8 -*-
 2 # @Time : 2022/01/03 20:45
 3 # @Author : butupi
 4 # @File : word_frequency.py
 5 # @Software : PyCharm
 6 
 7 import xlwt  # EXCEL handle
 8 
 9 #Get English articles(Replace special characters)
10 def get_text(path_en):
11     text_en = ""
12     with open(path_en, "r", encoding="utf-8") as f:
13         for line in f.readlines():
14             text_en += line.rstrip("\n")
15     #a lowercase letter
16     text_en = text_en.lower()
17     #Replace special characters
18     for ch in '!"#$&()*+,-./:;<=>?@[\\]^_{|}·~\'''':
19         text_en = text_en.replace(ch, " ")
20     return text_en
21 
22 
23 #Process text into dictionary
24 def make_dictionary(text_en):
25     words = text_en.split()
26     dictionary = {}
27     for word in words:
28         dictionary[word] = dictionary.get(word, 0) + 1  # counts.get (word,0)+ 1 Means yes word The default value is 0,+1 Be able to accumulate times; No, word Returns 0 when.
29     return dictionary
30 
31 #sort
32 def sort_dir(dictionary):
33     items = list(dictionary.items())
34     items.sort(key=lambda x: x[1],
35                reverse=True)  # lambda x:x[0]For tuples in the list( key)to sort Sort, x:x[1]Represents the value of the dictionary( values)to sort Sort, reverse=true Indicates descending order
36     return items
37 
38 #obtain length Number of words with letters or more
39 def get_count_len(items, length: int):
40     count_len_more = 0
41     count_text = 0 # Number of words in this list
42     for word, count in items:
43         count_text += count
44         if len(word) >= length:
45             count_len_more += count
46     return  count_len_more, count_text
47 
48 #Save to EXCEL In the table
49 def save_sheet(path, items):
50     workbook = xlwt.Workbook(encoding="utf-8")
51     worksheet = workbook.add_sheet("word_frequency")
52     worksheet.write(0, 0, "word")
53     worksheet.write(0, 1, "Number of occurrences")
54     for i in range(0, len(items)):
55         worksheet.write(i+1, 0, items[i][0])
56         worksheet.write(i+1, 1, items[i][1])
57     workbook.save(path)
58 
59 #Count word and word frequency
60 def main():
61     text_en = get_text("wbfx.txt")
62 
63     #The word frequency of the processed text is counted and stored in the dictionary
64     dictionary = make_dictionary(text_en)
65 
66     #Arrange the dictionaries in descending order to get a list with elements of( k-v)tuple(Words, frequency)
67     items = sort_dir(dictionary)
68 
69     #The statistical results are saved as a list type, sorted by word frequency from high to low, and the first 15 bits are output
70     print("Jane Eyre's English novels Jane Eyre Top 15 word frequency rankings")
71     for i in range(15):
72         word, count = items[i]
73         print("{0}\t\t{1:<8}{2:>5}".format(i+1, word, count))
74 
75     #Save to Excel In the table
76     save_sheet("word_frequency.xls", items)
77 
78     #6 Number of words with letter length and above
79     length_word = 6
80     count_six_more, count_text = get_count_len(items, length_word)
81     #print(word, count)  # Words with 6 letters + and their frequency
82     print()
83     print("In the English text of Jane Eyre's Novels"+str(length_word)+"The number of words with letters or more is:\t"+str(count_six_more)+" individual")
84     print("Jane Eyre's Novels Jane-Eyre The total number of words in the text is:\t"+str(count_text)+" individual")
85 
86 
87 if __name__ == '__main__':
88     main()