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 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: 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'] #连接 print(d, t, a) # 通过连接获取新闻网页 res2 = requests.get(a) res2.encoding = 'utf-8' soup2 = BeautifulSoup(res2.text, 'html.parser') # 取得新闻正文 z=soup2.select('#content')[0].text print(z) break
运行结果如图所示:
2. 分析字符串,获取每篇新闻的发布时间,作者,来源等信息。
#取得发布时间、作者等数据项 info=soup2.select('.show-info')[0].text # print(info) dt = info.lstrip('发布时间:')[:19] at = info[info.find('作者:'):].split()[0].lstrip('作者:') sh = info[info.find('审核:'):].split()[0].lstrip('审核:') ly = info[info.find('来源:'):].split()[0].lstrip('来源:') print(dt, at, sh, ly)
运行结果如下:
3. 将其中的发布时间由str转换成datetime类型。
from datetime import datetime dati = datetime.strptime(dt, '%Y-%m-%d %H:%M:%S') print(dati, dati.strftime('%Y/%m/%d'))
运行结果如图所示:
4. 将完整的代码及运行结果截图发布在作业上
# -*- coding: UTF-8 -*- # -*- author: wang -*- 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: #时间 d = news.select('.news-list-info')[0].contents[0].text t = news.select('.news-list-title')[0].text #标题 a = news.select('a')[0].attrs['href'] #连接 print(d, t, a) # 通过连接获取新闻网页 res2 = requests.get(a) res2.encoding = 'utf-8' soup2 = BeautifulSoup(res2.text, 'html.parser') # 取得新闻正文 z=soup2.select('#content')[0].text print(z) #取得发布时间、作者等数据项 info=soup2.select('.show-info')[0].text print(info) dt = info.lstrip('发布时间:')[:19] at = info[info.find('作者:'):info.find('审核:')].split()[0].lstrip('作者:') sh = info[info.find('审核:'):].split()[0].lstrip('审核:') ly = info[info.find('来源:'):].split()[0].lstrip('来源:') print(dt,at,sh,ly) from datetime import datetime dati = datetime.strptime(dt, '%Y-%m-%d %H:%M:%S') # print(type(dati)) print(dati, dati.strftime('%Y/%m/%d')) break
运行代码如图所示: