Python BeautifulSoup 抓取博客园首页精华

标签：

#coding:utf-8
‘‘‘
Created on 2015?-4-5

@author: Administrator
‘‘‘
from bs4 import BeautifulSoup
import urllib2
import sys
reload(sys)
sys.setdefaultencoding(‘utf-8‘)

‘‘‘
爬虫函数
‘‘‘
def GetCnBlog(cnt):
    url=‘http://www.cnblogs.com/sitehome/p/‘
    if cnt<1 or cnt>20:
        return None
    pages=[]
    for i in xrange(1,cnt):
        url=url+str(i)
        content_stream=urllib2.urlopen(url)
        soup =BeautifulSoup(content_stream)
       
        h3=soup.find_all(‘h3‘)
        for h in h3:
            p=h.text+‘      ‘+ h.find(‘a‘)[‘href‘]+‘\r\n‘
            pages.append(p)
    return pages
def Save(p):
    f=file(‘C:\\pages.txt‘,‘w‘)
    f.writelines(p)
    f.close()
if __name__==‘__main__‘:
    ps= GetCnBlog(10)
    Save(ps)

http://files.cnblogs.com/files/kun2008/setuptools-0.6c11.win32-py2.7.zip

Python BeautifulSoup 抓取博客园首页精华

标签：

原文地址：http://www.cnblogs.com/kun2008/p/4394261.html