import requests
from bs4 import BeautifulSoup
from datetime import datetime
import re
url = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
res = requests.get(url)
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text, 'html.parser')


def getClick(newsUrl):
    newId = re.search('\_(.*).html', newsUrl).group(1).split('/')[1]
    click = requests.get('http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newId))
    return click.text.split('.html')[-1].lstrip("('").rstrip("');")


def getNews(newsUrl):
    f = re.search('作者:((.{3}\s){1,3})', info).group(1)
    date = re.search('(\d{4}.\d{2}.\d{2}\s\d{2}.\d{2}.\d{2})', info).group(1)
    i = re.search('审核:((.{3}\s){1,3})', info).group(1)
    l = re.search('来源:((.{3}\s){1,3})', info).group(1)
    m = re.search('摄影:((..{3}\s){1,3})',info).group(1)
    count = getClick(newsUrl)
    dateTime = datetime.strptime(date, '%Y-%m-%d %H:%M:%S')
    print('发布时间:{0}'.format(dateTime))
    print('作者:{0}'.format(f))
    print('审核:{0}' .format(i))
    print('来源:{0}' .format(l))
    print('摄影:{0}' .format(m))
    print('点击:{0}' .format(count) + '')



for news in soup.select('li'):
    if len(news.select('.news-list-title')) > 0:
        link = news.a.attrs['href']
        t = news.select('.news-list-title')[0].text
        d = news.select('.news-list-description')[0].text
        newsUrl = news.select('a')[0]['href']
        res = requests.get(newsUrl)
        res.encoding = 'utf-8'
        soupb = BeautifulSoup(res.text, 'html.parser')
        info = soupb.select('.show-info')[0].text
        e = soupb.select('.show-content')[0].text

        print('标题:' + t)
        print('链接:' + newsUrl)
        print('描述:' + d)
        print('正文:' + e)
        getNews(newsUrl)
        break
 

Copyright © 2024 170何强
Powered by .NET 8.0 on Kubernetes