#coding=utf-8
import requests
from bs4 import BeautifulSoup
# res = requests.get('http://news.sina.com.cn/china/')
# res.encoding = 'utf-8'
#print type(res)
# print res.text
html_sample = '' \
'<html>' \
'<body>' \
'<h1 id="title">Hello World </h1>' \
'<a href="#" class="link">This is link1</a>' \
'<a href="# link2" class="link">This is link2</a>' \
'</body>' \
'</html>'
soup = BeautifulSoup(html_sample,'html.parser')
#print type(soup)
print soup.text小爬蟲
#coding=utf-8
import requests
from bs4 import BeautifulSoup
res = requests.get('http://news.sina.com.cn/china/')
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text,'html.parser')
# print res.text
for news in soup.select('.news-item'):
newsh2 = news.select('h2')
if len(newsh2) > 0:
h2 = news.select('h2')[0].text
a = news.select('a')[0]['href']
time = news.select('.time')[0].text
print time,h2,a
