[python爬虫]使用Python爬取网易新闻

分两步：

①爬取网易新闻标题和链接

②存入mysql中

上代码！

# -*- coding: utf-8 -*-
"""
Created on Thu Apr 06 17:04:37 2017

@author: Administrator
"""

# -*- coding: utf-8 -*-
"""
Created on Thu Apr 06 15:00:19 2017

@author: Administrator
"""

import pandas as pd
from mysql import connector
import urllib2
import re
from bs4 import BeautifulSoup
import time
url="http://www.163.com"
html=urllib2.urlopen(url).read()
soup=BeautifulSoup(html)
links=soup.find_all(name="a",attrs={"href":re.compile("http://news")})
z=[]
for i in links:
    z.append((i.get("href"),
              i.get_text(),
             time.strftime("%Y-%m-%d %X", time.localtime())))
df=pd.DataFrame(z)
df.columns=["news_url","news_title","record_time"] #df列名要和mysql中的字段名一致
"""*************