一个完整的大作业

1.选一个自己感兴趣的主题。

2.网络上爬取相关的数据。

3.进行文本分析，生成词云。

4.对文本分析结果解释说明。

5.写一篇完整的博客，附上源代码、数据爬取及分析结果，形成一个可展示的成果。

我选取的主题是校园的新闻网http://news.gzcc.cn/html/xiaoyuanxinwen/，然后用python语言在网络上爬取相关的数据。

import requests
from bs4 import BeautifulSoup
import jieba
import matplotlib.pyplot as plt
def getHTMLText(url):
    try:
        r = requests.get(url, timeout = 25)
        r.raise_for_status()
        #r.encoding = 'utf-8'
        return r.text
    except:
        return ""
def getContent(url):
    html = getHTMLText(url)
    # print(html)
    soup = BeautifulSoup(html, "html.parser")
    title = soup.select("div.hd > h1")
    print(title[0].get_text())
    time = soup.select("div.a_Info > span.a_time")
    print(time[0].string)
    author = soup.select("div.qq_articleFt > div.qq_toolWrap > div.qq_editor")
    print(author[0].get_text())
    paras = soup.select("div.Cnt-Main-Article-QQ > p.text")
    for para in paras:
        if len(para) > 0:
            print(para.get_text())
            print()
    fo = open("can.txt", "w+")
    fo.writelines(title[0].get_text() + "\n")
    fo.writelines(time[0].get_text() + "\n")
    for para in paras:
        if len(para) > 0:
            fo.writelines(para.get_text() + "\n\n")
    fo.writelines(author[0].get_text() + '\n')
    fo.close()
    article = {
        'Title' : title[0].get_text(),
        'Time' : time[0].get_text(),
        'Paragraph' : paras,
        'Author' : author[0].get_text()
    }
    print(article)
def main():
    url = "http://news.gzcc.cn/html/xiaoyuanxinwen/"
    getContent(url);
main()

　　

import requests
from bs4 import BeautifulSoup
from wordcloud import WordCloud
import re
import sys
import jieba
import matplotlib.pyplot as plt
 
non_bmp_map = dict.fromkeys(range(0x10000, sys.maxunicode + 1), 0xfffd)
txt = open('can.txt',"r",encoding='utf-8').read()

ex = {}
 
ls = []
words = jieba.lcut(txt)
counts = {}
for word in words:
    ls.append(word)
    if len(word) == 1:
        continue
    else:
        counts[word] = counts.get(word,0)+1
for word in ex:
    del(counts[word])
     
items = list(counts.items())
items.sort(key = lambda x:x[1], reverse = True)
for i in range(20):
    word , count = items[i]
    print ("{:<10}{:>5}".format(word,count))
 
mywc = WordCloud().generate(word)

plt.imshow(mywc)
plt.axis("off")
plt.show()