爬取校园新闻首页的新闻

1. 用requests库和BeautifulSoup库，爬取校园新闻首页新闻的标题、链接、正文。

2. 分析字符串，获取每篇新闻的发布时间，作者，来源，摄影等信息。

3. 将其中的发布时间由str转换成datetime类型。

4. 将完整的代码及运行结果截图发布在作业上。

#-*- coding: UTF-8 -*-
import requests
from bs4 import BeautifulSoup
from datetime import datetime

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:
     print(news.select('.news-list-title'))

for news in soup.select('li'):
    if len(news.select('.news-list-title')) > 0:
     title = news.select('.news-list-title')[0].text
     dt = news.select('.news-list-info')[0].contents[0].text
     a = news.select('a')[0].attrs['href']
     print(title, dt, a)

for news in soup.select('li'):
    if len(news.select(".news-list-title")) > 0:
        title = news.select('.news-list-title')[0].text
        dt = news.select('.news-list-info')[0].contents[0].text
        a = news.select('a')[0].attrs['href']
        print(title,dt,a)

for news in soup.select("li"):
    if len(news.select(".news-list-title")) > 0:
        a = news.select('a')[0].attrs['href']#新闻链接
        title = news.select('.news-list-title')[0].text#标题
        res1 = requests.get(a)
        res1.encoding = 'utf-8'
        soup1 = BeautifulSoup(res1.text,'html.parser')
        dt = soup1.select('.show-info')[0].text#时间
        print(title,'
',dt,'
')
        print(soup1.select('#content')[0].text)#内容
        t1 = dt.lstrip('发布时间:')[:19]
        i = dt.find('来源：')
        if i>0:
            s=dt[dt.find('来源：'):].split()[0].lstrip('来源：')
            a = dt[dt.find('作者：'):].split()[0].lstrip('作者：')
            p = dt[dt.find('摄影：'):].split()[0].lstrip('摄影：')
            print(t1,a,s,p)
        break
str = '2018-03-30 17:10:12 '
datetime.strptime(str,'%Y-%m-%d %H:%M:%S ')
print('
',str)