python之nntp服务器组
[*]http://www.newzbot.com/serverlist.php?since=ALL&orderby=kps&sortorder=desc&show_maxgroup=on&show_post=on&show_kps=on&show_created=on
这是可以找到当前有哪些服务器的地方网址，
这个项目的目的就是收集信息，并且将其生成一个html的报告（当然也可以是其他的形式的报告），完成代码如下
[*]'''''
[*]Created on 2012-7-18
[*]
[*]@author: mars
[*]'''
[*]import nntplib
[*]from nntplib import NNTP
[*]from time import time,strftime,localtime
[*]from email import message_from_string
[*]from urllib import urlopen
[*]import textwrap
[*]import re
[*]
[*]day=24*60*60
[*]def wrap(string,max=70):
[*] #make the string to the max linewidth
[*] return '\n'.join(textwrap.wrap(string))+'\n'
[*]class NewsAgent:
[*] #can get the new project and announce to the object fo the new from the souuce of the news
[*] def __init__(self):
[*] self.sources=[]
[*] self.destinations=[]
[*] def addSource(self,source):
[*] self.sources.append(source)
[*] def addDestination(self,dest):
[*] self.destinations.append(dest)
[*] def distribute(self):
[*] items=[]
[*] for source in self.sources:
[*] items.extend(source.getItems())
[*] for dest in self.destinations:
[*] dest.receiveItems(items)
[*]class NewsItem:
[*] #simle news project including tile and text
[*] def __init__(self,title,body):
[*] self.title=title
[*] self.body=body
[*]
[*]class NNTPSource:
[*] #the nntp source
[*] def __init__(self,servername,group,window):
[*] self.servername=servername
[*] self.group=group
[*] self.window=window
[*] def getItems(self):
[*] start=localtime(time()-self.window*day)
[*] date=strftime('%y%m%d',start)
[*] hour=strftime('%H%M%S',start)
[*]
[*] server=NNTP(self.servername)
[*]
[*] ids=server.group(self.group)
[*] #ids=server.newnews(self.group, date, hour)
[*]
[*] for id in ids:
[*] lines=server.article(id)
[*] message=message_from_string('\n'.join(lines))
[*]
[*] title=message['subject']
[*] body=message.get_payload()
[*] if message.is_multipart():
[*] body=body
[*]
[*] yield NewsItem(title,body)
[*]
[*] server.quit()
[*]
[*]class SimpleWebSource:
[*] #user the reto fetch thr source from the webpage
[*] def __init__(self,url,titlePattern,bodyPattern):
[*] self.url=url
[*] self.titlePattern=re.compile(titlePattern)
[*] self.bodyPattern=re.compile(bodyPattern)
[*] def getItems(self):
[*] text=urlopen(self.url).read()
[*] titles=self.titlePattern.findall(text)
[*] bodies=self.bodyPattern.findall(text)
[*] for title,body in zip(titles,bodies):
[*] yield NewsItem(title.wrap(body))
[*]class PlainDestination:
[*] #make it to the pure text
[*] def receiveItems(self,items):
[*] for item in items:
[*] print item.title
[*] #print '-'*len(subject)
[*] #print '-'*len(item.title)
[*] print item.body
[*] #print 'fuck&&&&&&&bitch'
[*]class HTMLDestination:
[*] # make it to the html
[*] 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</h1>
[*] """
[*]
[*] print >> out, '<ul>'
[*] id = 0
[*] for item in items:
[*] id += 1
[*] print >> out, '<li><a href="#%i">%s</a></li>' % (id, item.title)
[*] print >> out, '</ul>'
[*]
[*] id = 0
[*] for item in items:
[*] id += 1
[*] print >> out, '<h2><a name="%i">%s</a></h2>' % (id, item.title)
[*] print >> out, '<pre>%s</pre>' % item.body
[*]
[*] print >> out, """
[*] </body>
[*] </html>
[*] """
[*]
[*]class runDefaultSetup():
[*] #the soucecan modify by yourself
[*] agent=NewsAgent()
[*] #bbc_url='http://www.chinanews.com/'
[*] bbc_url='http://www.bbc.co.uk/news/'
[*] #bbc_url='http://www.bbc.co.uk/text_only.stm'
[*] 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)
[*]
[*] agent.addSource(bbc)
[*] #cong gmane.comp.python.announce get the nntpsource
[*]
[*] clpa_server='news.gmane.org'
[*] clpa_group='gmane.comp.python.apple'
[*]
[*] clpa_window=1
[*] clpa=NNTPSource(clpa_server,clpa_group,clpa_window)
[*] agent.addSource(clpa)
[*]
[*]
[*] #add the text and html target
[*] agent.addDestination(PlainDestination())
[*]
[*] agent.addDestination(HTMLDestination('news.html'))
[*]
[*] #public
[*] agent.distribute()
[*]if __name__=='__main__':
[*] runDefaultSetup()
[*]
[*]
[*]
其实这个程序呢 在第二版的教程上有，不过呢 那个给出的服务器不能用，所以在文章的开始的时候我就给出了 可以找到服务器地址的地方，比如我这里用的就是
clpa_server='news.gmane.org'
clpa_group='gmane.comp.python.apple'
这个！
当然这段代码我也稍微说下，最开始的类NewsAgent,接着是NewsItem,NNTPSource,SimpleWebSource,PlainDestination,HTMLDestination和runDefaultSetup
程序一运行就开始跑的是runDefaultSetup，这里就将NewsAgent实例化为agent，SimpleWebSource的3个参数分别是url， > 随后将bbc作为参数，调用agent的addsource。同样的道理完成了nntpsouce这一块。
最后就是就是调用agent.addDestionation。最后HTMLDestionation以news.html作为生成报告的html文本！
页:
[1]