爬取校园新闻首页的新闻

Posted 2020-10-29 099吴海经

import requests
from bs4 import BeautifulSoup

url = \'http://news.gzcc.cn/html/xiaoyuanxinwen/\'
res = requests.get(url)
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
        time = news.select(\'.news-list-info\')[0].contents[0].text
        a = news.select(\'a\')[0].attrs[\'href\']
        print(a,title,time)
        break
res1 = requests.get(a)
res1.encoding = \'utf-8\'
soup1 = BeautifulSoup(res1.text, \'html.parser\')
sp1 = soup1.select(\'#content\')[0].text
info = soup1.select(\'.show-info\')[0].text
print(info)
dt = info.lstrip(\'发布时间：\')[1:20]
print(dt)
ly = info.find(\'来源：\')
if ly>0:
    s = info[info.find(\'来源：\'):].split()[0].lstrip(\'来源：\')
print(s)
ly = info.find(\'摄影：\')
if ly>0:
    s = info[info.find(\'摄影：\'):].split()[0].lstrip(\'摄影：\')
print(s)

from datetime import datetime
str = dt
da = datetime.strptime(str,\'%Y-%m-%d %H:%M:%S\')
now = datetime.now()
type(now)
print(now.strftime(\'%Y-%m-%d %H:%M:%S\'))