一个完整的大作业

1.选一个自己感兴趣的主题。

我选取动漫资讯进行爬虫操作，爬取网站‘’http://news.dmzj.com/‘’。

2.网络上爬取相关的数据。

爬取此网页中的新闻标题，来源和时间。

import requests
from bs4 import BeautifulSoup


url = 'http://news.dmzj.com/'
res = requests.get(url)
res.encoding='utf-8'   
soup=BeautifulSoup(res.text,'html.parser')



for news in soup.select('.briefnews_con_li'):
    if len(news.select('h3'))>0:
        title=news.select('h3')[0].text
        url=news.select('a')[0]['href'] 

        resd=requests.get(url)
        resd.encoding='utf-8'
        soupd=BeautifulSoup(resd.text,'html.parser')
        time=soupd.select('.data_time')[0].text                       
        source=soupd.select('.data_from')[0].text
        #p = soupd.select('.news_content_con')[0].text
        print(title,url,time,source)
      

 

3.进行文本分析，生成词云。

import requests
import jieba
from bs4 import BeautifulSoup
import re

url = 'http://news.dmzj.com/'
res = requests.get(url)
res.encoding='utf-8'   
soup=BeautifulSoup(res.text,'html.parser')



for news in soup.select('.briefnews_con_li'):
    if len(news.select('h3'))>0:
        title=news.select('h3')[0].text
        url=news.select('a')[0]['href']
     

        resd=requests.get(url)
        resd.encoding='utf-8'
        soupd=BeautifulSoup(resd.text,'html.parser')
        p = soupd.select('.news_content_con')[0].text
        #print(p)
        break

words = jieba.lcut(p)
ls = []
counts = {}
for word in words:
    ls.append(word)
    if len(word) == 1:
        continue
    else:
        counts[word] = counts.get(word,0)+1
items = list(counts.items())
items.sort(key = lambda x:x[1], reverse = True)
for i in range(10):
    word , count = items[i]
    print ("{:<5}{:>2}".format(word,count))

from wordcloud import WordCloud
import matplotlib.pyplot as plt    
cy = WordCloud(font_path='msyh.ttc').generate(p)#wordcloud默认不支持中文，这里的font_path需要指向中文字体
plt.imshow(cy, interpolation='bilinear')
plt.axis("off")
plt.show()

 

4.对文本分析结果解释说明

 对文本进行分词，将词汇写入词云中让人更好地了解文本的主要内容和主题。

 

5.完整代码

import requests
from bs4 import BeautifulSoup
from datetime import datetime
import pandas
import sqlite3



def getdetail(url):
    resd=requests.get(url)
    resd.encoding='utf-8'
    soupd=BeautifulSoup(resd.text,'html.parser')
    news={}
    news['url']=url
    news['title']=soupd.select('h1')[0].text
    news['time']=soupd.select('.data_time')[0].text                       
    news['source']=soupd.select('.data_from')[0].text
    #news['p'] = soupd.select('.news_content_con')[0].text
    return(news)
    



def onepage(pageurl):
    res = requests.get(pageurl)
    res.encoding='utf-8'   
    soup=BeautifulSoup(res.text,'html.parser')
    newsls = []
    for news in soup.select('.briefnews_con_li'):
        if len(news.select('h3'))>0:
            newsls.append(getdetail(news.select('a')[0]['href']))
    return(newsls)

#print(onepage('http://news.dmzj.com/'))  
      
newstotal = []
dmurl='http://news.dmzj.com/'
newstotal.extend(onepage(dmurl))

res = requests.get(dmurl)
res.encoding= 'utf-8'
soup=BeautifulSoup(res.text,'html.parser')


for i in range(2,3):
    listurl='http://news.dmzj.com/p{}.html'.format(i)
    newstotal.extend(onepage(listurl))

df = pandas.DataFrame(newstotal)
df.to_excel('dmnews.xlsx')

with sqlite3.connect('dmnewsdb.sqlite') as db:
    df.to_sql('dmnewsdb8',con = db)