结合Python网络爬虫做一个今日新闻小程序(爬虫马赛克)

核心代码

requests.get 下载html网页
bs4.BeautifulSoup 分析html内容

from requests import get
from bs4 import BeautifulSoup as bs
from datetime import datetime as dt
 
def Today(style=1):
 date = dt.today()
 if style!=1: return f'{date.month}月{date.day}日'
 return f'{date.year}-{date.month:02}-{date.day:02}'
 
def SinaNews(style=1):
 url1 = 'http://news.***.com.cn/'
 if style==1: url1 += 'world'
 elif style==2: url1 += 'china'
 else: url1='https://mil.news.sina.com.cn/'
 text = get(url1)
 text.encoding='uft-8'
 soup = bs(text.text,'html.parser')
 aTags = soup.find_all("a")
 return [(t.text,t['href']) for t in aTags if Today() in str(t)]

爬取标题

>>> for i,news in enumerate(SinaNews(1)):
print(f'No{i+1}:',news[0])

No1: 外媒：*****
No2: 日媒：******
......

.......

内容已马赛克！！！
>>>

首次做爬虫，为了方便下手找一个不用破解网页的某新闻网站，下载网页就能直接取得内容。其中的国际、国内和军事新闻三个网页作内容源，requests.get下载网页后，分析所得html文本，所有<a href=...>标记带日期刚好所需要的。

爬取正文

然后再根据url下载正文网页，分析可知id=‘article'的<div>层就是正文所在位置，.get_text()是取得文本的关键函数，然后适当做一些格式处理：

>>> def NewsDownload(url):
 html = get(url)
 html.encoding='uft-8'
 soup = bs(html.text,'html.parser')
 text = soup.find('div',id='article').get_text().strip()
 text = text.replace('点击进入专题：','相关专题：')
 text = text.replace('　　','\n　　')
 while '\n\n\n' in text:
  text = text.replace('\n\n\n','\n\n')
 return text
 
>>> url = 'https://******/w/2021-09-29/doc-iktzqtyt8811588.shtml'
>>> NewsDownload(url)
'原标题：******************************************************'
>>>

界面代码

使用内置的图形界面库 tkinter 控件 Text 、Listbox、Scrollbar、Button。设置基本属性、放置位置、绑定命令，然后调试到程序完工！

源代码 News.pyw ：其中涉及的网站名称已马赛克！

from requests import get
from bs4 import BeautifulSoup as bs
from datetime import datetime as dt
from os import path
import tkinter as tk
 
def Today(style=1):
 date = dt.today()
 if style!=1: return f'{date.month}月{date.day}日'
 return f'{date.year}-{date.month:02}-{date.day:02}'
 
def SinaNews(style=1):
 url1 = 'http://news.****.com.cn/'
 if style==1: url1 += 'world'
 elif style==2: url1 += 'china'
 else: url1='https://mil.****.com.cn/'
 text = get(url1)
 text.encoding='uft-8'
 soup = bs(text.text,'html.parser')
 aTags = soup.find_all("a")
 return [(t.text,t['href']) for t in aTags if Today() in str(t)]
 
def NewsList(i):
 global news
 news = SinaNews(i)
 tList.delete(0,tk.END)
 for idx,item in enumerate(news):
  tList.insert(tk.END,f'{idx+1:03} {item[0]}')
 tText.config(state=tk.NORMAL)
 tText.delete(0.0,tk.END)
 tText.config(state=tk.DISABLED)
 NewsShow(0)
 
def NewsList1(): NewsList(1)
def NewsList2(): NewsList(2)
def NewsList3(): NewsList(3)
 
def NewsShow(idx):
 if idx!=0:
  idx = tList.curselection()[0]
 title,url = news[idx][0],news[idx][1]
 html = get(url)
 html.encoding='uft-8'
 soup = bs(html.text,'html.parser')
 text = soup.find('div',id='article').get_text().strip()
 text = text.replace('点击进入专题：','相关专题：')
 text = text.replace('　　','\n　　')
 while '\n\n\n' in text:
  text = text.replace('\n\n\n','\n\n')
 tText.config(state=tk.NORMAL)
 tText.delete(0.0,tk.END)
 tText.insert(tk.END, title+'\n\n'+text)
 tText.config(state=tk.DISABLED)
 
def InitWindow(self,W,H):
 Y = self.winfo_screenheight()
 winPosition = str(W)+'x'+str(H)+'+8+'+str(Y-H-100)
 self.geometry(winPosition)
 icoFile = 'favicon.ico'
 f = path.exists(icoFile)
 if f: win.iconbitmap(icoFile)
 self.resizable(False,False)
 self.wm_attributes('-topmost',True)
 self.title(bTitle[0])
 SetControl()
 self.update()
 self.mainloop()
 
def SetControl():
 global tList,tText
 tScroll = tk.Scrollbar(win, orient=tk.VERTICAL)
 tScroll.place(x=450,y=320,height=300)
 tList = tk.Listbox(win,selectmode=tk.BROWSE,yscrollcommand=tScroll.set)
 tScroll.config(command=tList.yview)
 for idx,item in enumerate(news):
  tList.insert(tk.END,f'{idx+1:03} {item[0]}')
 tList.place(x=15,y=320,width=435,height=300)
 tList.select_set(0)
 tList.focus()
 bW,bH = 70,35 #按钮的宽高
 bX,bY = 95,270 #按钮的坐标
 tBtn1 = tk.Button(win,text=bTitle[1],command=NewsList1)
 tBtn1.place(x=bX,y=bY,width=bW,height=bH)
 tBtn2=tk.Button(win,text=bTitle[2],command=NewsList2)
 tBtn2.place(x=bX+100,y=bY,width=bW,height=bH)
 tBtn3 = tk.Button(win,text=bTitle[3],command=NewsList3)
 tBtn3.place(x=bX+200,y=bY,width=bW,height=bH)
 tScroll2 = tk.Scrollbar(win, orient=tk.VERTICAL)
 tScroll2.place(x=450,y=10,height=240)
 tText = tk.Text(win,yscrollcommand=tScroll2.set)
 tScroll2.config(command=tText.yview)
 tText.place(x=15,y=10,width=435,height=240)
 tText.config(state=tk.DISABLED,bg='azure',font=('宋体', '14'))
 NewsShow(0)
 tList.bind("<Double-Button-1>",NewsShow)
 
if __name__=='__main__':
 
 win = tk.Tk()
 bTitle = ('今日新闻','国际新闻','国内新闻','军事新闻')
 news = SinaNews()
 InitWindow(win,480,640)

奉上全部代码，在此就不作详细分析了，如有需要请留言讨论。我的使用环境 Win7+Python3.8.8 下可以无错运行！文中涉及网站名称已打上马赛克，猜不出名字的可以私下里问我。