参考了晚上很多资料 就是抓取http://m.i21st.cn/speaking/oraltraining_1.html这个网站上的英语资料 ,没事练练英语~哈哈~
# -*- coding: utf-8 -*-
import urllib2
import urllib
import re
import thread
import time
class HTML_Model:
def __init__(self):
self.page = 1
self.pages = []
#self.myTool = HTML_Tool()
self.enable = False
def GetPage(self,page):
myUrl = "http://m.i21st.cn/speaking/oraltraining_" + page +".html"
myResponse = urllib2.urlopen(myUrl)
myPage = myResponse.read()
#encode的作用是将unicode编码转换成其他编码的字符串
#decode的作用是将其他编码的字符串转换成unicode编码
unicodePage = myPage.decode("utf-8")
# 找出所有class="content"的div标记
#re.S是任意匹配模式,也就是.可以匹配换行符
myItems = re.findall("</div><a.*?href='(.*?)'.*?class='h3'>(.*?)</a>",unicodePage,re.S)
items = []
for item in myItems:
items.append([item[0].replace("\n",""),item[1].replace("\n","")])
return items
def LoadPage(self):
while self.enable:
if len(self.pages) < 2:
try:
myPage = self.GetPage(str(self.page))
self.page += 1
self.pages.append(myPage)
except:
print '无法显示新的资料!'
else:
time.sleep(1)
def ShowPage(self,q,page):
for items in q:
print u'第%d页' % page , items[1]
#——————————————————————
myUrl = "http://m.i21st.cn" + str(items[0])
myResponse = urllib2.urlopen(myUrl)
myPage = myResponse.read()
#encode的作用是将unicode编码转换成其他编码的字符串
#decode的作用是将其他编码的字符串转换成unicode编码
unicodePage = myPage.decode("utf-8")
#myItems = re.findall("</div><a.*?href='(.*?)'.*?class='h3'>(.*?)</a>",unicodePage,re.S)
temp = re.findall("<a.*?id='contentbegin'.*?name='contentbegin'></a>(.*?)</div>",unicodePage,re.S)
temp1=temp[0].encode("utf-8")
temp2=re.findall("<br.*?/>(.*?)</p>",temp1,re.S)
temp3=temp2[0].decode("utf-8")
#myItems = re.findall("<br.*?/>[\n](.*?)<br.*?/>(.*?)",temp1,re.S)
temp4 =str(temp3.encode("gbk"))
temp4=temp4.replace("'","")
temp4=temp4.replace("<br />","")
temp4=temp4.replace("<strong>","")
temp4=temp4.replace("</strong>","")
temp4=temp4.replace("&rsquo","")
temp4=temp4.replace("&ldquo","")
temp4=temp4.replace("&rdquo","")
text=temp4.replace(";","'")
#————————————————————————————————————————
# print self.myTool.Replace_Char(items[1])
print text
myInput = raw_input()
if myInput == "quit":
self.enable = False
break
def Start(self):
self.enable = True
page = self.page
print u'正在加载中请稍候......'
# 新建一个线程在后台加载段子并存储
thread.start_new_thread(self.LoadPage,())
while self.enable:
if self.pages:
nowPage = self.pages[0]
del self.pages[0]
self.ShowPage(nowPage,page)
page += 1
#----------- 程序的入口处 -----------
print u"""
---------------------------------------
程序:英语学习—爬虫
语言:Python2.7
作者:xiantian
功能:按下回车依次浏览今日的英语资料
---------------------------------------
"""
print u'请按下回车浏览今日新的内容:'
raw_input(' ')
myModel = HTML_Model()
myModel.Start()