糗事百科爬虫

糗事百科爬虫-爬取段子

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


# 糗事百科爬虫类
class QSBK:
    def __init__(self):
        self.pageIndex = 1
        self.user_agent = 'Mozilla/5.0 (Windows NT 6.1; WOW64)'
        self.headers = {'User-Agent': self.user_agent}
        self.stories = []
        self.enable = False

    def getPage(self, pageIndex):
        try:
            url = "http://www.qiushibaike.com/text/page/" + str(pageIndex)
            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"连接糗事百科失败,错误原因", e.reason
                return None

    def getPageItems(self, pageIndex):
        pageCode = self.getPage(pageIndex)
        if not pageCode:
            print "页面加载失败...."
            return None
        pattern = re.compile('<div class="author clearfix">.*?<h2>(.*?)</h2>.*?<div class="content">.*?'
                             '<span>(.*?)</span>.*?<div class="stats">.*?class="number">(.*?)</i>', re.S)
        items = re.findall(pattern, pageCode)
        pageStories = []
        for i in range(len(items)):
            # print i, items[i][0], ":", items[i][1], items[i][2]
            pageStories.append([items[i][0].strip(), items[i][1].strip(), items[i][2].strip()])
        return pageStories

    # 加载并提取页面的内容，加入到列表中
    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

    # 调用该方法，每次敲回车打印输出一个段子
    def getOneStory(self, pageStories, page):
        # 遍历一页的段子
        for story in pageStories:
            # 等待用户输入
            input = raw_input()
            # 如果输入Q则程序结束
            if input == "Q":
                self.enable = False
                return
            print u"第%d页\t发布人:%s\t赞:%s\n%s" % (page, story[0], story[2], story[1])

    # 开始方法
    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 = True
        # 局部变量，控制当前读到了第几页
        nowPage = 0
        while self.enable:
            if len(self.stories) > 0:
                pageStories = self.stories[0]
                nowPage += 1
                del self.stories[0]
                self.getOneStory(pageStories, nowPage)
            else:
                self.loadPage()
spider = QSBK()
spider.start()

【参考资料】

1. 博主 http://cuiqingcai.com/1052.html