提取某一页所有段子
# -*- coding:utf-8 -*-
import urllib
import urllib2
import re
page = 1
url = 'http://www.qiushibaike.com/hot/page/' + str(page)
user_agent = 'haha/4.0 (compatible; MSIE 5.5; Windows NT)'
headers = { 'User-Agent' : user_agent }
try:
request = urllib2.Request(url,headers = headers)
response = urllib2.urlopen(request)
content = response.read().decode('utf-8')
pattern=re.compile('h2>(.*?)</h2.*?<span>(.*?)</.*?number">(.*?)</.*?number">(.*?)<', re.S)
items = re.findall(pattern,content)
for item in items:
print u"----------------------------------------\n发布人：%s内容：%s赞：%s\t评论数：%s\n"%(item[0],item[1],item[2],item[3])
except urllib2.URLError, e:
if hasattr(e,"code"):
print e.code
if hasattr(e,"reason"):
print e.reason2.完善交互
按下回车，读取一个段子，显示出段子的发布人，内容，评论个数，点赞个数。
# -*- coding:utf-8 -*-
import urllib
import urllib2
import re
import thread
import time
class QSBK:
def __init__(self):
self.pageIndex = 1
#初始化 ua
self.user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)'
#初始化 headers
self.headers = { 'user-Agent' : self.user_agent }
#存放段子
self.stories = []
#是否继续运行
self.enable = False
#根据索引获得页面代码
def getPage(self,pageIndex):
try:
url = 'http://www.qiu' \
'shibaike.com/hot/page' + str(pageIndex)
#构建请求request
request = urllib2.Request(url,headers = self.headers)
#利用urlopen获取页面代码
response = urllib2.urlopen(request)
#将页面转化为UTF-8编码
pageCode = response.read().decode('utf-8')
return pageCode
except urllib2.URLError,e:
if hasattr(e,"reason"):
print u"连接失败，错误原因",e.reason
return None
#根据页面代码，返回段子列表
def getPageItems(self,pageIndex):
pageCode = self.getPage(pageIndex)
if not pageCode:
print "页面加载失败。。。"
return None
pattern = re.compile('h2>(.*?)</h2.*?<span>(.*?)</.*?number">(.*?)</.*?number">(.*?)<', re.S)
#pattern = re.compile('h2>(.*?)</h2.*?content">(.*?)</.*?number">(.*?)</', re.S)
items = re.findall(pattern,pageCode)
#用来存储每页的段子
pageStories = []
#遍历正则表达式匹配的信息
for item in items:
pageStories.append([item[0].strip(),item[1].strip(),item[2].strip(),item[3].strip()])
return pageStories
#加载并提取页面的内容，加入到列表中
def loadPage(self):
#如果当前未看的页数少于两页，则加载新一页
if self.enable == True:
if len(self.stories) < 2:
#获取新一页
pageStories = self.getPageItems(self.pageIndex)
#将该页面存放在全局list中
if pageStories:
self.stories.append(pageStories)
#页码索引加一
self.pageIndex += 1
#调用该方法，每次回车输出一个段子
def getOneStory(self,pageStories,page):
#遍历
for story in pageStories:
#等待用户输入
input = raw_input()
#判断是否要加载新页面
self.loadPage()
#输入"quit"则程序结束
if input == "quit":
self.enable = False
return
print u"第%d页\n----------------------------------------\n发布人：%s\n内容：%s\n赞：%s\t评论数：%s\n"%(page,story[0],story[1],story[2],story[3])
#开始方法
def start(self):
print u"正在读取，回车查看新段子，quit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()
