[已解决]词云

故梦L

1. import requests
   
2. from requests.exceptions import RequestException
   
3. from lxml import etree
   
4. import time
   
5. import jieba
   
6. import wordcloud
   
7. import re
   
8. from collections import Counter
   
9. 
   
10. headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36',
    
11.            'Referer': 'https://www.cangqionglongqi.com/wukongzhuan/',
    
12.            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8'}
    
13. 
    
14. def get_page(url):
    
15.     """请求网页内容"""
    
16.     try:
    
17.         response = requests.get(url, headers=headers)
    
18.         if response.status_code == 200:
    
19.             response.encoding = response.apparent_encoding
    
20.             return response.text
    
21.         return None
    
22.     except RequestException as error:
    
23.         print('报错:',error)
    
24.         exit()
    
25.         
    
26. def parser_page_url(html_href):
    
27.     """
    
28.     解析链接、章节
    
29.     :param link_href:链接
    
30.     :param list_chapter:章节
    
31.     """
    
32.     page_content = etree.HTML(html_href)
    
33.     link_href = page_content.xpath('//*[@id="list"]/dl/dd/a/@href')
    
34.     list_chapter = page_content.xpath('//*[@id="list"]/dl/dd/a/text()')
    
35.     return (link_href, list_chapter)
    
36. 
    
37. def parser_content(url):
    
38.     """解析小说内容"""
    
39.     html_content = get_page(url)
    
40.     content = ''
    
41.     if html_content:
    
42.         page_contents = etree.HTML(html_content)
    
43.         contents = page_contents.xpath('//*[@id="content"]/text()')
    
44.         for i in contents:
    
45.             content += (i+'\n')
    
46.         return content.replace('\xa0'*5,'\n')
    
47. 
    
48. def get_urls():
    
49.     """
    
50.     拼接url
    
51.     :params urls:各个章节的url
    
52.     """
    
53.     url = 'https://www.cangqionglongqi.com/wukongzhuan/'
    
54.     html = get_page(url)
    
55.     hrefs,chapters = parser_page_url(html)
    
56.     urls = [url + href for href in hrefs]
    
57.     return (urls,chapters)
    
58. 
    
59. def write_txt(writer, chapt):
    
60.     """保存在txt文件"""
    
61.     with open('悟空传.txt','a',encoding='utf-8') as file:
    
62.         file.write('*'*10+chapt+'*'*10)
    
63.         file.write(writer)
    
64. 
    
65. def jiebas(dict=dict()):
    
66.     """jieba分析小说并提取出现次数较多的词语    """
    
67.     file = open('悟空传.txt','r',encoding='utf-8').read()
    
68.     replace_text = re.sub('\W','',file)
    
69.     words = jieba.lcut(replace_text)
    
70.     c = Counter(words)
    
71.     common_c = c.most_common(200)
    
72.     for key, value in common_c:
    
73.         if len(key) >= 2: #提取大于两个词的词语
    
74.             dict[key] = value
    
75.     return dict
    
76. 
    
77. def wordclouds(dict):
    
78.     """生成词云"""
    
79.     w = wordcloud.WordCloud()
    
80.     w.generate_from_frequencies(dict)
    
81.     w.to_file('wukongzhuan.jpg')
    
82. 
    
83. if __name__ == '__main__':
    
84.     page_urls, page_chapter = get_urls()
    
85.     for num in range(len(page_urls)-1):
    
86.         print('正在抓取%s' % page_chapter[num])
    
87.         write = parser_content(page_urls[num])
    
88.         write_txt(write, page_chapter[num])
    
89.         time.sleep(15)
    
90.     print('抓取完成')
    
91.     print('生成词云')
    
92.     dict1 = jiebas()
    
93.     wordclouds(dict1)
    
94.     print('完成')
    

复制代码

为什么生成的词云不含有中文，各位大佬回答下啊

最佳答案

月排行榜 / 总排行榜

Charles未晞

2018-8-7 18:53:11

手动添加一下支持中文的字体。比如：

1. font = r'C:\Windows\Fonts\simfang.ttf'
   
2. wc = WordCloud(collocations=False, font_path=font, width=1400, height=1400, margin=2).generate(text.lower())

复制代码

跳转到最佳答案楼层

Charles未晞

手动添加一下支持中文的字体。比如：

1. font = r'C:\Windows\Fonts\simfang.ttf'
   
2. wc = WordCloud(collocations=False, font_path=font, width=1400, height=1400, margin=2).generate(text.lower())

复制代码