Python爬取《冰雪奇缘2》豆瓣影评

 1 import urllib.request
 2 from bs4 import BeautifulSoup
 3 ?
 4 def getHtml(url):
 5     """获取url页面"""
 6     headers = {‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36‘}
 7     req = urllib.request.Request(url,headers=headers)
 8     req = urllib.request.urlopen(req)
 9     content = req.read().decode(‘utf-8‘)
10     return content
11 ?
12 def getComment(url):
13     """解析HTML页面"""
14     html = getHtml(url)
15     soupComment = BeautifulSoup(html, ‘html.parser‘)
16     comments = soupComment.findAll(‘span‘, ‘short‘)
17     onePageComments = []
18     for comment in comments:
19         onePageComments.append(comment.getText()+‘\n‘)
20     return onePageComments
21 ?
22 if __name__ == ‘__main__‘:
23     f = open(‘冰雪奇缘2.txt‘, ‘w‘, encoding=‘utf-8‘)
24     for page in range(10):  # 豆瓣爬取多页评论需要验证。
25         url = ‘https://movie.douban.com/subject/25887288/comments?start=‘ + str(20*page) + ‘&limit=20&sort=new_score&status=P‘
26         print(‘第%s页的评论:‘ % (page+1))
27         print(url + ‘\n‘)
28         for i in getComment(url):
29             f.write(i)
30             print(i)
31         print(‘\n‘)

1 import matplotlib.pyplot as plt
2 from wordcloud import WordCloud
3 from scipy.misc import imread
4 import jieba
5 ?
6 text = open("冰雪奇缘2.txt","rb").read()
7 #结巴分词
8 wordlist = jieba.cut(text,cut_all=False)
9 wl = " ".join(wordlist)

 1 #设置词云
 2 wc = WordCloud(background_color = "white", #设置背景颜色
 3                mask = imread(‘black_mask.png‘),  #设置背景图片
 4                max_words = 2000, #设置最大显示的字数
 5                stopwords = ["的", "这种", "这样", "还是","就是", "这个", "没有" , "一个" , "什么", "电影", "一部","第一部", "第二部"], #设置停用词
 6                font_path = "C:\Windows\Fonts\simkai.ttf",  # 设置为楷体 常规
 7         #设置中文字体，使得词云可以显示（词云默认字体是“DroidSansMono.ttf字体库”，不支持中文）
 8                max_font_size = 60,  #设置字体最大值
 9                random_state = 30, #设置有多少种随机生成状态，即有多少种配色方案
10     )
11 myword = wc.generate(wl)#生成词云
12 wc.to_file(‘result.png‘)
13 ?
14 #展示词云图
15 plt.imshow(myword)
16 plt.axis("off")
17 plt.show()