标签：爬虫
# 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 10.0; Win64; x64)‘
self.headers = {‘User-Agent‘ :self.user_agent}
self.stories = []
self.enable = False
def 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 pageCode
except urllib2.URLError,e:
if hasattr(e,"reason"):
print "error",e.reason
return None
def getPageItems(self,pageIndex):
pageCode = self.getPage(pageIndex)
if not pageCode:
print "page load error"
return None
pattern = re.compile(‘h2>(.*?)</h2.*?content">(.*?)</.*?number">(.*?)</‘,re.S)
items = re.findall(pattern,pageCode)
pageStories = []
for item in items:
pageStories.append([item[0].strip(),item[1].strip(),item[2].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"第%d页\t发布人：%s\t 赞：%s\n%s" %(page,story[0],story[2],story[1])
def start(self):
print u‘正在读取，回车查看，Q退出‘
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()
C:\python.exe C:/python_test/qiubai.py
正在读取，回车查看，Q退出
第1页发布人：匿名用户 赞：1909
跟着后面，感觉压力好大
第1页发布人：花殇随风飞 赞：440
我只是忘了给你带夜宵，你用得着用这样的眼神看我么……
标签：爬虫
原文地址：http://bjzby.blog.51cto.com/4084070/1794535
