1. 用requests库和BeautifulSoup库，爬取校园新闻首页新闻的标题、链接、正文。
import requests
from bs4 import BeautifulSoup
from datetime import datetime
res = requests.get(‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘)
res.encoding = ‘utf-8‘
soup = BeautifulSoup(res.text,‘html.parser‘)
for news in soup.select(‘li‘):
if len(news.select(‘.news-list-title‘))>0:
t = news.select(‘.news-list-title‘)[0].text #标题
a = news.select(‘a‘)[0].attrs[‘href‘] # 链接
resd = requests.get(a)
resd.encoding = ‘utf-8‘
soupd = BeautifulSoup(resd.text, ‘html.parser‘) # 打开新闻详情页
c = soupd.select(‘#content‘)[0].text # 正文
print(t,a,c)
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。
info = soupd.select(‘.show-info‘)[0].text
print(info)
3. 将其中的发布时间由str转换成datetime类型。
dt = info.lstrip(‘发布时间:‘)[:19] # 发布时间
dati = datetime.strptime(dt, ‘%Y-%m-%d %H:%M:%S‘)
print(dati)
4. 将完整的代码及运行结果截图发布在作业上。
import requests
from bs4 import BeautifulSoup
from datetime import datetime
res = requests.get(‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘)
res.encoding = ‘utf-8‘
soup = BeautifulSoup(res.text,‘html.parser‘)
for news in soup.select(‘li‘):
if len(news.select(‘.news-list-title‘))>0:
t = news.select(‘.news-list-title‘)[0].text #标题
a = news.select(‘a‘)[0].attrs[‘href‘] # 链接
resd = requests.get(a)
resd.encoding = ‘utf-8‘
soupd = BeautifulSoup(resd.text, ‘html.parser‘) # 打开新闻详情页
c = soupd.select(‘#content‘)[0].text # 正文
#print(t,a,c)
info = soupd.select(‘.show-info‘)[0].text
#print(info)
dt = info.lstrip(‘发布时间:‘)[:19] # 发布时间
dati = datetime.strptime(dt, ‘%Y-%m-%d %H:%M:%S‘)
print(t,a,c,info,dati)
break
