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】
