#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup
from datetime import datetime
import re


res = requests.get('http://news.sina.com.cn/o/2017-12-01/doc-ifyphtze3020095.shtml')
res.encoding = 'utf-8'

#列印文章標題
soup = BeautifulSoup(res.text , 'html.parser')
print(soup.select('#artibodyTitle')[0].text)

#獲取文章發表時間
timesource = soup.select('#navtimeSource')[0].contents[0].strip()

#獲取文章來源
#wsource = soup.select('#navtimeSource')[0].contents[1].text.strip()
wsource = soup.select('#navtimeSource span a')[0].text

#獲取文章來源連結 
wa = soup.select('#navtimeSource span a')[0].get('href')

#時字串轉時間格式
dt = datetime.strptime(timesource,'%Y年%m月%d日%H:%M')
#時間格式轉字串  
#dtstr = dt.strftime('%Y-%m-%d %H:%M:%S')  
#將時間，來源，連結依次列印  
print(dt,wsource,wa)


#取得文章內容
#方式1  
'''
article = []
for p in soup.select('#artibody p')[:-1]:
	article.append(p.text)

print(' '.join(article))
'''
#方式2  
print(' '.join(p.text.strip() for p in soup.select('#artibody p')[:-1]))


#選取新聞編輯者名稱
print(soup.select('.article-editor')[0].text)
#print(soup.select('.article-editor')[0].text.lstrip('責任編輯：'))


#剖析新聞識別符號
#方法1
newsurl = 'http://news.sina.com.cn/o/2017-12-01/doc-ifyphtze3020095.shtml'
newsid = newsurl.split('/')[-1].rstrip('.shtml').lstrip('doc-i')
print('newsid =',newsid)
'''
#方法2
m = re.search('doc-i(.+).shtml',newsurl)
print(m.group(0))
print(m.group(1))
'''
 

結果展示：