# _*_ coding:utf-8 _*_
import urllib2
import re
from datetime import datetimeclass QSBK:def __init__(self):self.pageIndex = 1self.user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'self.headers = {'User-Agent':self.user_agent}self.stories = []self.enable = Falsedef getPage(self,pageIndex):try:url = 'http://www.qiushibaike.com/hot/page'+str(pageIndex)request = urllib2.Request(url,headers = self.headers)response = urllib2.urlopen(request)pageCode = response.read().decode('utf-8')return pageCodeexcept urllib2.URLError,e:if hasattr(e,'reason'):print u"QSBK connect Error,reason: ",e.reasonreturn Nonedef getPageItems(self,pageIndex):pageCode = self.getPage(pageIndex)if not pageCode:print "Page Loading Error..."return Nonepattern = re.compile('<div.*?author clearfix">.*?<a.*?<img.*?>(.*?)</a>.*?<a.*?<h2>(.*?)</h2>.*?</a>.*?<div.*?'+'content">(.*?)<!--(.*?)-->.*?</div>.*?<div class="stats.*?class="number">(.*?)</i>',re.S)items = re.findall(pattern,pageCode)pageStories = []for item in items:haveImg = re.search("img",item[0])if not haveImg:replaceBR = re.compile('<br/>')text = re.sub(replaceBR,"\n",item[2])pageStories.append([item[1].strip(),text.strip(),item[3].strip(),item[4].strip()])return pageStoriesdef loadPage(self):if self.enable == True:if len(self.stories) < 2:pageStories = self.getPageItems(self.pageIndex)if pageStories:self.stories.append(pageStories)self.pageIndex += 1def getOneStory(self,pageStories,page):for story in pageStories:input = raw_input()self.loadPage()if input == 'Q':self.enable = Falsereturnprint u"第%d页\t发布人：%s\t发布时间：%s\t赞：%s\n%s" %(page,story[0],datetime.fromtimestamp(int(story[2])),story[3],story[1])def start(self):print u"正在读取糗事百科，按回车查看新段子，Q退出"self.enable = Trueself.loadPage()nowPage = 0while self.enable:if len(self.stories)>0:pageStories = self.stories[0]nowPage += 1del self.stories[0]self.getOneStory(pageStories,nowPage)spider = QSBK()
spider.start()