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: print(news) break for news in soup.select('li'): if len(news.select('.news-list-title'))>0: t=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(dt,t,a)
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。
for news in soup.select('li'): if len(news.select('.news-list-litle'))>0: t = 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(dt, t, a) break for news in soup.select('li'): if len(news.select('.news-list-title'))>0: t = news.select('.news-list-title')[0].text a = news.select('a')[0].attrs['href'] print(a) resd = requests.get(a) resd.encoding ='utf-8' soupd = BeautifulSoup(resd.text,'html.parser') print(soupd.select('.show-info')[0].text) break
3. 将其中的发布时间由str转换成datetime类型。
import requests from bs4 import BeautifulSoup from datetime import datetime gzccurl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/' res = requests.get(gzccurl) 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 url = news.select('a')[0]['href'] time = news.select('.news-list-info')[0].contents[0].text dt = datetime.strptime(time,'%Y-%m-%d') source = news.select('.news-list-info')[0].contents[1].text print(dt,' ',title,' ',url,' ',source,' ')