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
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:
d = news.select(‘.news-list-info‘)[0].contents[0].text #时间
t = news.select(‘.news-list-title‘)[0].text #标题
a = news.select(‘a‘)[0].attrs[‘href‘] #URL
print(d, t, a)
运行结果图：
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。
res2 = requests.get(a)
res2.encoding = ‘utf-8‘
soup2 = BeautifulSoup(res2.text,‘html.parser‘)
x = soup2.select(‘.show-content‘)[0].text
info = soup2.select(‘.show-info‘)[0].text.split()
# print(soup2.select(‘#content‘)[0].text)
s = info[0].lstrip(‘发布时间:‘) + " " + info[1] #发布时间
zz = info[2].lstrip(‘作者：‘) #作者
sh = info[3].lstrip(‘审核：‘) #审核
ly = info[4].lstrip("来源：") #来源
print(s,zz,sh,ly)
运行结果图：
3. 将其中的发布时间由str转换成datetime类型。
from datetime import datetime time = ‘2018-04-01 11:57:00‘ a = datetime.strptime(time, ‘%Y-%m-%d %H:%M:%S‘) print(type(a)) print(a, a.strftime(‘%Y/%m/%d‘))
运行结果图：
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:
d = news.select(‘.news-list-info‘)[0].contents[0].text #时间
t = news.select(‘.news-list-title‘)[0].text #标题
a = news.select(‘a‘)[0].attrs[‘href‘] #URL
print(d,t,a)
res2 = requests.get(a)
res2.encoding = ‘utf-8‘
soup2 = BeautifulSoup(res2.text,‘html.parser‘)
x = soup2.select(‘.show-content‘)[0].text
info = soup2.select(‘.show-info‘)[0].text.split()
# print(soup2.select(‘#content‘)[0].text)
s = info[0].lstrip(‘发布时间:‘) + " " + info[1] #发布时间
zz = info[2].lstrip(‘作者：‘) #作者
sh = info[3].lstrip(‘审核：‘) #审核
ly = info[4].lstrip("来源：") #来源
cc = datetime.strptime(s, ‘%Y-%m-%d %H:%M:%S‘)
print(cc,type(cc))
print(cc.strftime(‘%Y/%m/%d‘),zz,sh,ly)
运行结果图
