获取博客园首页的博客列表,获取博客首页,#! /usr/bin/
文章由Byrx.net分享于2019-03-23 07:03:41
获取博客园首页的博客列表,获取博客首页,#! /usr/bin/
#! /usr/bin/env python#coding:gbk"""获取博客园首页的博客列表"""from pyquery import PyQuery as pqfor p in range(1,2): print "正在获取第",p,"页" doc=pq(url=r'http://www.cnblogs.com/p'+str(p)) a=doc(".post_item") f=open("c:\\\\cnbloglist.txt","a") for i in a: try: print pq(i).find("h3").text() ,pq(i).find(".post_item_foot").text() #, pq(i).find("span.article_comment").text() , pq(i).find("span.article_view").text() f.write(pq(i).find("h3").text().encode("gbk")+"\\n") except: pass f.close()#该片段来自于http://byrx.net
评论关闭