Python抓取博客园首页文章列表（带分页）

__author__ = 'Administrator'
import urllib.request
import re
from bs4 import BeautifulSoup
import time

########################################################
#
#              抓取博客园首页推荐文章列表http://www.cnblogs.com
#
#             鹿伟伟
#
########################################################
class CnblogsUtils(object):
def __init__(self):
user_agent='Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36'
self.headers ={'Cache-Control':'max-age=0',
'Connection':'keep-alive',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'User-Agent':user_agent,
}
def getPage(self,url=None):
request=urllib.request.Request(url,headers=self.headers)
response=urllib.request.urlopen(request)
soup=BeautifulSoup(response.read(),"html.parser")
#print(soup.prettify())
return soup
def parsePage(self,url=None,pageNo=None):
soup=self.getPage(url+pageNo)
itemBlog=soup.find_all("div",{"class":"post_item"})
#print(itemBlog.__len__())
#print(itemBlog[10])
blog=CnblogsUtils()
print("+++++++++++++++++++++++++++第",pageNo,"页++++++++++++++++++++++++++++")
for i,blogInfo in enumerate(itemBlog):
#print(blogInfo)
blog.num=i
blog.url=blogInfo.find("h3").find("a").get("href")
blog.title=blogInfo.find("h3").find("a").string
#print("++++++++++",blogInfo.find("div","post_item_foot").contents[2])
#去掉空格strip()
blog.time=blogInfo.find("div","post_item_foot").contents[2].strip()
blog.author=blogInfo.find("div","post_item_foot").find("a").string
print(blog.num+1,"标题：",blog.title,"作者：",blog.author,"详情：",blog.url,blog.time)

#######     执行    ########
if __name__ =="__main__":
#要抓取的网页地址'http://blog.csdn.net/?&page={}'.format(i+1),i+1)
url = "http://www.cnblogs.com/sitehome/p/"
cnblog=CnblogsUtils()
#cnblog.parsePage(url)
for i in range(0,10):
cnblog.parsePage(url,str(i+1))
time.sleep(3)