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。

import urllib.request as ur
from urllib.request import Request
from bs4 import BeautifulSoup as bs
import re


def gethtml(url):
    header = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'}
    req = Request(url, headers=header)
    html = ur.urlopen(req).read().decode('utf-8')
    return html

def getinfo(html):
    soup = bs(html,'html.parser')
    info = soup.select('.detail_left_cnt #infodata p')
    # for i in range(3):
    #     info[i] = info[i].text
    # print(info)

    return info


if __name__=="__main__":
    url = "https://kandian.youth.cn/index/detail?sign=ev0EmQzwYx4qZjo"
    html1 = gethtml(url)
    info = getinfo(html1)
    for i in info:
        f = open('info2.txt', 'a+', encoding='utf-8')
        f.write(re.sub('s+', '', i.get_text()))
        f.close()

import jieba

from wordcloud import WordCloud
import matplotlib.pyplot as d


info = open('info2.txt','r',encoding='utf-8').read()
text = ''
text += ' '.join(jieba.lcut(info))
window = WordCloud(font_path='C:WindowsFontsSTZHONGS.TTF',background_color='White',max_words=50)
window.generate_from_text(text)
d.imshow(window)
# p.imshow(wc.recolor(color_func=00ff00))
d.axis("off")
d.show()
window.to_file('hdz.jpg')