获取一篇新闻的全部信息

import requests
from bs4 import BeautifulSoup
from datetime import datetime
import re

url = ‘http://news.gzcc.cn/html/2018/xiaoyuanxinwen_1109/10359.html‘



# 获取新闻的全部信息
def newsinformation(url):
    news = requests.get(url)
    news.encoding = ‘utf-8‘
    newSoup = BeautifulSoup(news.text,‘html.parser‘)

    #获取新闻标题
    title = newSoup.select(‘.show-title‘)[0].text
    print(‘标题：‘ + title)

    # 获取新闻发布的相关信息
    newInfo = newSoup.select(‘.show-info‘)[0].text
    #print(newInfo)

    # 发布时间
    newDate = newInfo.split()[0].lstrip(‘发布时间:‘)
    newTime = newInfo.split()[1]
    newDateTime = newDate + ‘ ‘ + newTime
    print(‘发布时间：‘ + newDateTime)

    # 作者
    author = newInfo.split()[2]
    print(author)

    # 审核
    examine = newInfo.split()[3]
    print(examine)

    # 来源
    source = newInfo.split()[4]
    print(source)

    # 获取点击次数的url
    id = re.findall(‘(d{1,7})‘,url)[-1]
    clickUrl = ‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(id)
    click = requests.get(clickUrl)
    newClick = int(click.text.split(‘.html‘)[-1].lstrip("(‘").rstrip("‘);"))  # 获取点击次数
    print(‘点击次数：‘)
    print(newClick)

newsinformation(url)