畫圖顯示：

import jieba
from wordcloud import WordCloud
import matplotlib.pyplot as plt

txt = open("zuihou.txt","r",encoding=‘utf-8‘).read()
wordlist = jieba.lcut(txt)

 

wl_split=" ".join(wordlist)
mywc = WordCloud().generate(wl_split)
plt.imshow(mywc)
plt.axis("off")
plt.show()

結果：

用requests庫和BeautifulSoup4庫，爬取校園新聞列表的時間、標題、鏈接、來源、詳細內容

爬蟲，網頁信息

import requests
from bs4 import BeautifulSoup

gzccurl = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
res = requests.get(gzccurl)
res.encoding = ‘utf-8‘

soup = BeautifulSoup(res.text,‘html.parser‘)
for news in soup.select(‘li‘):
    if len(news.select(‘.news-list-title‘))>0:
        title = news.select(‘
 
.news-list-title‘)[0].text
        url = news.select(‘a‘)[0][‘href‘]
        print(title,url)

結果：

加上時間：

for news in soup.select(‘li‘):
    if len(news.select(‘.news-list-title‘))>0:
        title = news.select(‘.news-list-title‘)[0].text
        url = news.select(‘a‘)[0][‘href‘]
        time = news.select(‘
 
.news-list-info‘)[0].contents[0].text
        
        print(time,title,url)

效果：

• 將其中的時間str轉換成datetime類型。
• 將取得詳細內容的代碼包裝成函數。

import requests
from bs4 import BeautifulSoup
from datetime import datetime

gzccurl = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
res = requests.get(gzccurl)
res.encoding = ‘utf-8‘

soup = BeautifulSoup(res.text,‘html.parser‘)
def getdetail(url):
    resd = requests.get(url)
    resd.encoding= ‘utf-8‘
    soupd = BeautifulSoup(resd.text,‘html.parser‘)
    return(soupd.select(‘.show-content‘)[0].text)

for news in soup.select(‘li‘):
    if len(news.select(‘.news-list-title‘))>0:
        title = news.select(‘.news-list-title‘)[0].text
        url = news.select(‘a‘)[0][‘href‘]
        time = news.select(‘.news-list-info‘)[0].contents[0].text
        dt = datetime.strptime(time,‘%Y-%m-%d‘)
        source = news.select(‘.news-list-info‘)[0].contents[1].text
        detail = getdetail(url)
        print(dt,title,url,source,detail)

結果：

• 選一個自己感興趣的主題，做類似的操作，為後面“爬取網絡數據並進行文本分析”做準備。

import requests
from bs4 import BeautifulSoup
from datetime import datetime

gzccurl = ‘http://www.lbldy.com/tag/gqdy/‘
res = requests.get(gzccurl)
res.encoding = ‘utf-8‘

soup = BeautifulSoup(res.text,‘html.parser‘)
def getdetail(url):
    resd = requests.get(url)
    resd.encoding= ‘utf-8‘
    soupd = BeautifulSoup(resd.text,‘html.parser‘)
    return(soupd.select(‘.show-content‘)[0].text)

for news in soup.select(‘h4‘):
    
        print(news)

結果：

requests庫和BeautifulSoup4庫爬取新聞列表