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)

我选了附近松田学校的校园网来爬取

2.用python 编写爬虫程序，从网络上爬取相关主题的数据。

# -*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup as bs



def gettext(url):
    header = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.117 Safari/537.36'}
    html = requests.get(url, headers=header).content

    soup = bs(html, 'html.parser')
    info = soup.select('div.newList.black01 a')
    a = []
    for i in info:
        a.append(i.text)
        print(i.text)
    return a


if __name__ == '__main__':
    url = "http://www.sontan.net/newsCenter.do"
    #html = getreq(url)
    info = gettext(url)
    print(info)
    for i in info:
        print(i)
        f = open('i.txt', 'a+',encoding='utf-8')
        f.write(i)
        f.write('\n')
        f.close()

 

3.对爬了的数据进行文本分析，生成词云。

import jieba
import PIL
from wordcloud import WordCloud
import matplotlib.pyplot as p
import os

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

 

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。

一开始遇到的问题很多，做函数的时候发现自己的基本功非常的不扎实，甚至在导入库方面的知识也很匮乏，好在在同学的帮助下，我还是顺利的完成了任务。感觉做大数据爬取还是很有意思的，不过在爬其他网站的时候经常爬不到东西，应该是被限制了访问，这个问题以后再去深究吧。

6.最后提交爬取的全部数据、爬虫及数据分析源代码。

 

# -*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup as bs



def gettext(url):
    header = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.117 Safari/537.36'}
    html = requests.get(url, headers=header).content

    soup = bs(html, 'html.parser')
    info = soup.select('div.newList.black01 a')
    a = []
    for i in info:
        a.append(i.text)
        print(i.text)
    return a


if __name__ == '__main__':
    url = "http://www.sontan.net/newsCenter.do"
    #html = getreq(url)
    info = gettext(url)
    print(info)
    for i in info:
        print(i)
        f = open('i.txt', 'a+',encoding='utf-8')
        f.write(i)
        f.write('\n')
        f.close()



import jieba
import PIL
from wordcloud import WordCloud
import matplotlib.pyplot as p
import os

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