糗事百科爬虫

最新推荐文章于 2021-09-26 22:34:18 发布

IceFire

最新推荐文章于 2021-09-26 22:34:18 发布

阅读量617

点赞数

分类专栏：其他

本文链接：https://blog.youkuaiyun.com/Heu_Ice_Fire/article/details/44131325

版权

其他专栏收录该内容

14 篇文章

订阅专栏

__author__ = 'think'

# -*- coding:utf-8 -*-
import urllib
import urllib2
import re
import thread
import time


class QSBK:


    def __init__(self):
        self.pageIndex = 1
        self.user_agent =  'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:35.0)'
        self.headers = { 'User-Agent' : self.user_agent }
        self.stories = []
        self.enable = False

    def getPage(self,pageIndex):
        try:
            url = 'http://www.qiushibaike.com/8hr/page/' + str(pageIndex) + '?s=4752404'
            request = urllib2.Request(url,headers = self.headers)
            response = urllib2.urlopen(request)
            pageCode = response.read().decode('utf-8')
            return pageCode

        except urllib2.URLError, e:
            if hasattr(e,"reason"):
                print u"Wrong  ",e.reason
                return None


    def getPageItems(self,pageIndex):
        pageCode = self.getPage(pageIndex)
        if not pageCode:
            print "Loading Wrong...."
            return None
        pattern = re.compile('<div.*?class="author.*?>.*?<a.*?</a>.*?<a.*?>(.*?)</a>.*?<div.*?class'+
                         '="content".*?title="(.*?)">(.*?)</div>(.*?)<div class="stats.*?class="number">(.*?)</i>',re.S)
        items = re.findall(pattern,pageCode)
        pageStories = []
        for item in items:
            haveImg = re.search("img",item[3])
            if not haveImg:
              pageStories.append([item[0].strip(),item[1].strip(),item[2].strip(),item[4].strip()])
        return pageStories


    def loadPage(self):
        if self.enable == True:
            if len(self.stories) < 2:
                pageStories = self.getPageItems(self.pageIndex)
                if pageStories:
                    self.stories.append(pageStories)
                    self.pageIndex += 1


    def getOneStory(self,pageStories,page):
        for story in pageStories:
            input = raw_input()
            self.loadPage()
            if input == "Q":
                self.enable = False
                return
            print u"Page %d\tUser:%s\tTime:%s\n%s\nLick:%s\n" %(page,story[0],story[1],story[2],story[3])


    def start(self):
        print u""
        self.enable = True
        self.loadPage()

        nowPage = 0
        while self.enable:
            if len(self.stories)>0:
                pageStories = self.stories[0]
                nowPage += 1
                del self.stories[0]
                self.getOneStory(pageStories,nowPage)


spider = QSBK()
spider.start()