此博客以后永不更新阴险阴险阴险阴险阴险阴险 国内唯一更新博客在此处不在更新，谢谢，请看下面的地址和邮箱! 我的博客园：http://www.cnblogs.com/mhxy13867806343/ 欢迎访问！ 邮箱:mhxy13867806343@sina.cn/ 国内更新博客在:https://github.com/mhxy13867806343 微信公众号:pyjs
分类： Python/Ruby
2015-09-16 15:27:35
# -*- coding: utf-8 -*-
__author__ = 'Administrator'
:程序的用处有些类似于现在的博客订阅工具或者叫RSS订阅器。
#此题的链接: />
from nntplib import NNTP
import re,time,email,urllib,textwrap
day=24*60*60
def wrap(str1,max1=70):
return '\n'.join(textwrap.wrap(str1))+'\n'
class NewsAgent:
def __init__(self):
self.sources=[]
self.destinations=[]
def addSource(self,sou):
self.sources.append(sou)
def addDestination(self,dest):
self.destinations.append(dest)
def distribute(self):
items=[]
for sor in self.sources:
items.extend(sor.getItems())
for dest in self.destinations:
dest.receiveItems(items)
class NewsItem:
def __init__(self,title,body):
self.title=title
self.body=body
class NNPTSOurec:
def __init__(self,servername,group,windows):
self.server=servername
self.group=group
self.win=windows
def getItems(self):
start=time.localtime(time.time()-self.win*day)
data=time.strftime('%y%m%d',start)
hour=time.strftime('%H%M%S',start)
server=NNTP(self.server)
ids=server.newnews(self.group,data,hour)[1]
for id1 in ids:
lines=server.article(id1)[3]
message=email.message_from_string('\n'.join(lines))
title=message['subject']
body=message.get_payload()
if message.is_multipart():
body=body[0]
yield NewsItem(title,body)
server.quit()
class SimpleWebSource:
def __init__(self,url,titlePattern,bodyPattern):
self.url=url
self.titme1=titlePattern
self.body1=bodyPattern
def getItems(self):
text=urllib.urlopen(self.url).read()
titles=self.titme1.findall(text)
bodiles=self.body1.findall(text)
for title,body in zip(titles,bodiles):
yield NewsItem(title,wrap(body))
class PlainDestination:
def receiveItems(self,items):
for item in items:
print item.title
print '_'*len(item.title)
print item.body
class HTMLDestination:
def __init__(self,filename):
self.filename=filename
def receiveITems(self,items):
out=open(self.filename,'w')
print >>out,'''
<html>
<head>
<title>Today's News</title>
</head>
<body>
<h1>Today's News</hi>
'''
print >>out,'<ul>'
id1=0
for item in items:
id1+=1
print >>out,'<li><a href="#">%s</a></li>'%(id1,item.title)
print >>out,'</ul>'
id1=0
for item in items:
id1+=1
print >>out,'<h2><a href=%i>%s</a></h2>'%(id1,item.title)
print >>out,'<pre>%s</pre>'%(item.body)
print >>out,'''
</body>
</html>
'''
def runDefaultSetup():
arent=NewsAgent()
bbc_url=''
bbc_title = r'(?s)a href="[^"]*">\s*<b>\s*(.*?)\s*</b>'
bbc_body = r'(?s)</a>\s*<br/>\s*(.*?)\s*<'
bbc=SimpleWebSource(bbc_url,bbc_title,bbc_body)
arent.addSource(bbc)
clpa_server='news2.neva.ru'
clpa_group='alt.sex.telephone'
clpa_windows=1
clpa=NNPTSOurec(clpa_server,clpa_group,clpa_windows)
arent.addSource(clpa)
arent.addDestination(PlainDestination())
arent.addDestination(HTMLDestination('news_2015.html'))
arent.distribute()
runDefaultSetup()
我的错误，我的从的代码抄的，别人都对，我这边怎么是错误 的
Traceback (most recent call last):
File "G:/py_py/python_object_xyz/obj_python/obj_xml.py", line 112, in <module>
runDefaultSetup()
File "G:/py_py/python_object_xyz/obj_python/obj_xml.py", line 111, in runDefaultSetup
arent.distribute()
File "G:/py_py/python_object_xyz/obj_python/obj_xml.py", line 21, in distribute
items.extend(sor.getItems())
File "G:/py_py/python_object_xyz/obj_python/obj_xml.py", line 57, in getItems
titles=self.titme1.findall(text)
AttributeError: 'str' object has no attribute 'findall'
