利用BeautifulSoup抓取新浪网页新闻的内容

#coding = ‘utf-8‘

import requests
from bs4 import BeautifulSoup
import sys
reload(sys)
sys.setdefaultencoding("utf-8")

#抓取web页面
url = "http://news.sina.com.cn/china/"
res = requests.get(url)
res.encoding = ‘utf-8‘

#放进soup里面进行网页内容剖析
soup = BeautifulSoup(res.text, "html.parser")
elements = soup.select(‘.news-item‘)
    
#抓取需要的内容并且放入文件中
#抓取的内容有时间，内容文本，以及内容的链接
fname = "F:/asdf666.txt"
try:
    f = open(fname, ‘w‘)
    for element in elements:
        if len(element.select(‘h2‘)) > 0:
            f.write(element.select(‘.time‘)[0].text)
            f.write(element.select(‘h2‘)[0].text)
            f.write(element.select(‘a‘)[0][‘href‘])
            f.write(‘\n\n‘)
    

    f.close()
except Exception, e:
    print e
else:
    pass
finally:
    pass