爬虫大作业

1.选一个自己感兴趣的主题或网站。(所有同学不能雷同)

2.用python 编写爬虫程序，从网络上爬取相关主题的数据。

3.对爬了的数据进行文本分析，生成词云。

4.对文本分析结果进行解释说明。

5.写一篇完整的博客，描述上述实现过程、遇到的问题及解决办法、数据分析思想及结论。

6.最后提交爬取的全部数据、爬虫及数据分析源代码。

#encoding=gbk
lyric= ''
f=open('./励志歌曲歌词.txt','r')
for i in f:
    lyric+=f.read()

加入#encoding=gbk是为了防止后面操作报错SyntaxError: Non-UTF-8 code starting with 'xc0'
然后用jieba分词来对歌曲做分词提取出词频高的词

import jieba.analyse
result=jieba.analyse.textrank(lyric,topK=50,withWeight=True)
keywords = dict()
for i in result:
    keywords[i[0]]=i[1]
print(keywords)

from PIL import Image,ImageSequence
import numpy as np
import matplotlib.pyplot as plt
from wordcloud import WordCloud,ImageColorGenerator
image= Image.open('./tim.jpg')
graph = np.array(image)
wc = WordCloud(font_path='./fonts/simhei.ttf',background_color='White',max_words=50,mask=graph)
wc.generate_from_frequencies(keywords)
image_color = ImageColorGenerator(graph)
plt.imshow(wc)
plt.imshow(wc.recolor(color_func=image_color))
plt.axis("off")
plt.show()

保存生成图片

wc.to_file('dream.png')

完整代码：

#encoding=gbk
import jieba.analyse
from PIL import Image,ImageSequence
import numpy as np
import matplotlib.pyplot as plt
from wordcloud import WordCloud,ImageColorGenerator
lyric= ''
f=open('./励志歌曲歌词.txt','r')
for i in f:
    lyric+=f.read()


result=jieba.analyse.textrank(lyric,topK=50,withWeight=True)
keywords = dict()
for i in result:
    keywords[i[0]]=i[1]
print(keywords)


image= Image.open('./tim.jpg')
graph = np.array(image)
wc = WordCloud(font_path='./fonts/simhei.ttf',background_color='White',max_words=50,mask=graph)
wc.generate_from_frequencies(keywords)
image_color = ImageColorGenerator(graph)
plt.imshow(wc)
plt.imshow(wc.recolor(color_func=image_color))
plt.axis("off")
plt.show()
wc.to_file('dream.png')