import requests url=‘http://localhost:63342/zjc/news.html?_ijt=p2l5n0shp613m01ad0jlpobino‘ res=requests.get(url) res.encoding=‘utf-8‘ from bs4 import BeautifulSoup soup=BeautifulSoup(res.text,‘html.parser‘)
取出h1标签的文本
print(soup.h1.text)
取出a标签的链接
s=soup.a.attrs[‘href‘] print(s)
取出所有li标签的所有内容
s=soup.select(‘li‘) print(s)
取出一条新闻的标题、链接、发布时间、来源
s0=soup.select(‘.news-list-title‘)[0].text s1=soup.body.li.a.attrs[‘href‘] s2=soup.select(‘.news-list-info‘)[0].contents[0].text s3=soup.select(‘.news-list-info‘)[0].contents[1].text print(s0+"\n"+s1+"\n"+s2+"\n"+s3)
